{ "audit": { "date": "2026-07-22", "flag_counts": { "duplicate": 41, "metadata_corrected": 1, "non_paper_or_multi_work": 6, "non_paper_type": 29, "unverified": 8, "vague_author": 45, "vague_author_corrected": 1, "wrong_supplied_mapping_corrected": 3 }, "id": "paper-curriculum-2026-07-22", "source": "internal curriculum identity and structure audit" }, "caveat": "Rows remain discovery records unless independently verified. Entries marked unverified_not_citable must not be presented as citable publications.", "counts": { "audit_flags": 134, "records": 1000, "records_with_flags": 126, "sections": 62 }, "edition": "audited-discovery-edition", "generated": "2026-07-22", "records": [ { "audit_flags": [], "authors": "Shannon", "id": 1, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": "https://people.math.harvard.edu/~ctm/home/text/others/shannon/entropy/entropy.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Mathematical%20Theory%20of%20Communication&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Mathematical%20Theory%20of%20Communication%20Shannon%201948", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Mathematical%20Theory%20of%20Communication&sort=relevance" }, "supplied_direct_url": "https://people.math.harvard.edu/~ctm/home/text/others/shannon/entropy/entropy.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "Information theory — entropy, bits, channel capacity", "title": "A Mathematical Theory of Communication", "work_type": "Research-paper candidate", "year": 1948, "year_display": "1948" }, { "audit_flags": [], "authors": "Turing", "id": 2, "links": { "canonical_url": "https://academic.oup.com/mind/article/LIX/236/433/986238", "corrected_by_audit": false, "direct_url": "https://academic.oup.com/mind/article/LIX/236/433/986238", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Computing%20Machinery%20and%20Intelligence&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Computing%20Machinery%20and%20Intelligence%20Turing%201950", "semantic_scholar": "https://www.semanticscholar.org/search?q=Computing%20Machinery%20and%20Intelligence&sort=relevance" }, "supplied_direct_url": "https://academic.oup.com/mind/article/LIX/236/433/986238" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "The Turing Test — can machines think?", "title": "Computing Machinery and Intelligence", "work_type": "Research-paper candidate", "year": 1950, "year_display": "1950" }, { "audit_flags": [], "authors": "McCulloch & Pitts", "id": 3, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": "https://www.cs.cmu.edu/~./epxing/Class/10715/reading/McCulloch.and.Pitts.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Logical%20Calculus%20of%20Ideas%20Immanent%20in%20Nervous%20Activity&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Logical%20Calculus%20of%20Ideas%20Immanent%20in%20Nervous%20Activity%20McCulloch%201943", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Logical%20Calculus%20of%20Ideas%20Immanent%20in%20Nervous%20Activity&sort=relevance" }, "supplied_direct_url": "https://www.cs.cmu.edu/~./epxing/Class/10715/reading/McCulloch.and.Pitts.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "First mathematical model of a neuron", "title": "A Logical Calculus of Ideas Immanent in Nervous Activity", "work_type": "Research-paper candidate", "year": 1943, "year_display": "1943" }, { "audit_flags": [], "authors": "Solomonoff", "id": 4, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=An%20Inductive%20Inference%20Machine&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=An%20Inductive%20Inference%20Machine%20Solomonoff%201957", "semantic_scholar": "https://www.semanticscholar.org/search?q=An%20Inductive%20Inference%20Machine&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "Foundations of algorithmic probability", "title": "An Inductive Inference Machine", "work_type": "Research-paper candidate", "year": 1957, "year_display": "1957" }, { "audit_flags": [], "authors": "Turing", "id": 5, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": "https://www.cs.virginia.edu/~robins/Turing_Paper_1936.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=On%20Computable%20Numbers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=On%20Computable%20Numbers%20Turing%201936", "semantic_scholar": "https://www.semanticscholar.org/search?q=On%20Computable%20Numbers&sort=relevance" }, "supplied_direct_url": "https://www.cs.virginia.edu/~robins/Turing_Paper_1936.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "Turing machine — theoretical basis of computation", "title": "On Computable Numbers", "work_type": "Research-paper candidate", "year": 1936, "year_display": "1936" }, { "audit_flags": [], "authors": "Dempster, Laird, Rubin", "id": 6, "links": { "canonical_url": "https://www.jstor.org/stable/2984875", "corrected_by_audit": false, "direct_url": "https://www.jstor.org/stable/2984875", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Maximum%20Likelihood%20from%20Incomplete%20Data%20via%20the%20EM%20Algorithm&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Maximum%20Likelihood%20from%20Incomplete%20Data%20via%20the%20EM%20Algorithm%20Dempster%201977", "semantic_scholar": "https://www.semanticscholar.org/search?q=Maximum%20Likelihood%20from%20Incomplete%20Data%20via%20the%20EM%20Algorithm&sort=relevance" }, "supplied_direct_url": "https://www.jstor.org/stable/2984875" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "EM algorithm for statistical estimation", "title": "Maximum Likelihood from Incomplete Data via the EM Algorithm", "work_type": "Research-paper candidate", "year": 1977, "year_display": "1977" }, { "audit_flags": [], "authors": "Tibshirani", "id": 7, "links": { "canonical_url": "https://www.jstor.org/stable/2346178", "corrected_by_audit": false, "direct_url": "https://www.jstor.org/stable/2346178", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Regression%20Shrinkage%20and%20Selection%20via%20the%20Lasso&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Regression%20Shrinkage%20and%20Selection%20via%20the%20Lasso%20Tibshirani%201996", "semantic_scholar": "https://www.semanticscholar.org/search?q=Regression%20Shrinkage%20and%20Selection%20via%20the%20Lasso&sort=relevance" }, "supplied_direct_url": "https://www.jstor.org/stable/2346178" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "L1 regularization for sparse models", "title": "Regression Shrinkage and Selection via the Lasso", "work_type": "Research-paper candidate", "year": 1996, "year_display": "1996" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as book or textbook, not as a research paper.", "severity": "warning" } ], "authors": "Barber", "id": 8, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Bayesian%20Reasoning%20and%20Machine%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Bayesian%20Reasoning%20and%20Machine%20Learning%20Barber%202012", "semantic_scholar": "https://www.semanticscholar.org/search?q=Bayesian%20Reasoning%20and%20Machine%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "Comprehensive Bayesian ML framework", "title": "Bayesian Reasoning and Machine Learning", "work_type": "Book or textbook", "year": 2012, "year_display": "2012" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as book or textbook, not as a research paper.", "severity": "warning" } ], "authors": "Cover & Thomas", "id": 9, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Elements%20of%20Information%20Theory&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Elements%20of%20Information%20Theory%20Cover%201991", "semantic_scholar": "https://www.semanticscholar.org/search?q=Elements%20of%20Information%20Theory&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "KL divergence, mutual information", "title": "Elements of Information Theory", "work_type": "Book or textbook", "year": 1991, "year_display": "1991" }, { "audit_flags": [], "authors": "Hastings", "id": 10, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Monte%20Carlo%20Sampling%20Methods%20Using%20Markov%20Chains&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Monte%20Carlo%20Sampling%20Methods%20Using%20Markov%20Chains%20Hastings%201970", "semantic_scholar": "https://www.semanticscholar.org/search?q=Monte%20Carlo%20Sampling%20Methods%20Using%20Markov%20Chains&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "MCMC methods foundational for probabilistic ML", "title": "Monte Carlo Sampling Methods Using Markov Chains", "work_type": "Research-paper candidate", "year": 1970, "year_display": "1970" }, { "audit_flags": [], "authors": "Geman & Geman", "id": 11, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Stochastic%20Relaxation%2C%20Gibbs%20Distributions%20and%20Bayesian%20Restoration%20of%20Images&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Stochastic%20Relaxation%2C%20Gibbs%20Distributions%20and%20Bayesian%20Restoration%20of%20Images%20Geman%201984", "semantic_scholar": "https://www.semanticscholar.org/search?q=Stochastic%20Relaxation%2C%20Gibbs%20Distributions%20and%20Bayesian%20Restoration%20of%20Images&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "Gibbs sampling", "title": "Stochastic Relaxation, Gibbs Distributions and Bayesian Restoration of Images", "work_type": "Research-paper candidate", "year": 1984, "year_display": "1984" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as book or textbook, not as a research paper.", "severity": "warning" } ], "authors": "Efron & Tibshirani", "id": 12, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=An%20Introduction%20to%20the%20Bootstrap&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=An%20Introduction%20to%20the%20Bootstrap%20Efron%201993", "semantic_scholar": "https://www.semanticscholar.org/search?q=An%20Introduction%20to%20the%20Bootstrap&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "Bootstrap methods for statistical inference", "title": "An Introduction to the Bootstrap", "work_type": "Book or textbook", "year": 1993, "year_display": "1993" }, { "audit_flags": [], "authors": "Aizerman, Braverman, Rozonoer", "id": 13, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Kernel%20Trick&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Kernel%20Trick%20Aizerman%201964", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Kernel%20Trick&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "Implicit high-dimensional mappings", "title": "The Kernel Trick", "work_type": "Research-paper candidate", "year": 1964, "year_display": "1964" }, { "audit_flags": [], "authors": "Golub & Reinsch", "id": 14, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Singular%20Value%20Decomposition%20and%20Least%20Squares%20Solutions&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Singular%20Value%20Decomposition%20and%20Least%20Squares%20Solutions%20Golub%201970", "semantic_scholar": "https://www.semanticscholar.org/search?q=Singular%20Value%20Decomposition%20and%20Least%20Squares%20Solutions&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "SVD foundations used everywhere in ML", "title": "Singular Value Decomposition and Least Squares Solutions", "work_type": "Research-paper candidate", "year": 1970, "year_display": "1970" }, { "audit_flags": [], "authors": "Mehta", "id": 15, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Random%20Matrices&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Random%20Matrices%20Mehta%201967", "semantic_scholar": "https://www.semanticscholar.org/search?q=Random%20Matrices&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 1, "section_title": "Mathematical & Statistical Foundations", "source_note": "Random matrix theory — used in deep learning theory", "title": "Random Matrices", "work_type": "Research-paper candidate", "year": 1967, "year_display": "1967" }, { "audit_flags": [], "authors": "Rosenblatt", "id": 16, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Perceptron%3A%20A%20Probabilistic%20Model%20for%20Information%20Storage%20and%20Organization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Perceptron%3A%20A%20Probabilistic%20Model%20for%20Information%20Storage%20and%20Organization%20Rosenblatt%201958", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Perceptron%3A%20A%20Probabilistic%20Model%20for%20Information%20Storage%20and%20Organization&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "First perceptron model", "title": "The Perceptron: A Probabilistic Model for Information Storage and Organization", "work_type": "Research-paper candidate", "year": 1958, "year_display": "1958" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as book or textbook, not as a research paper.", "severity": "warning" } ], "authors": "Minsky & Papert", "id": 17, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Perceptrons&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Perceptrons%20Minsky%201969", "semantic_scholar": "https://www.semanticscholar.org/search?q=Perceptrons&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "Limitations of single-layer perceptrons (XOR problem)", "title": "Perceptrons", "work_type": "Book or textbook", "year": 1969, "year_display": "1969" }, { "audit_flags": [], "authors": "Cover & Hart", "id": 18, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Nearest%20Neighbor%20Pattern%20Classification&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Nearest%20Neighbor%20Pattern%20Classification%20Cover%201967", "semantic_scholar": "https://www.semanticscholar.org/search?q=Nearest%20Neighbor%20Pattern%20Classification&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "k-NN algorithm", "title": "Nearest Neighbor Pattern Classification", "work_type": "Research-paper candidate", "year": 1967, "year_display": "1967" }, { "audit_flags": [], "authors": "Valiant", "id": 19, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Theory%20of%20the%20Learnable&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Theory%20of%20the%20Learnable%20Valiant%201984", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Theory%20of%20the%20Learnable&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "PAC learning theory", "title": "A Theory of the Learnable", "work_type": "Research-paper candidate", "year": 1984, "year_display": "1984" }, { "audit_flags": [], "authors": "Quinlan", "id": 20, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Induction%20of%20Decision%20Trees&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Induction%20of%20Decision%20Trees%20Quinlan%201986", "semantic_scholar": "https://www.semanticscholar.org/search?q=Induction%20of%20Decision%20Trees&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "ID3 algorithm — decision trees", "title": "Induction of Decision Trees", "work_type": "Research-paper candidate", "year": 1986, "year_display": "1986" }, { "audit_flags": [], "authors": "Boser, Guyon, Vapnik", "id": 21, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Training%20Algorithm%20for%20Optimal%20Margin%20Classifiers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Training%20Algorithm%20for%20Optimal%20Margin%20Classifiers%20Boser%201992", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Training%20Algorithm%20for%20Optimal%20Margin%20Classifiers&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "Support Vector Machines", "title": "A Training Algorithm for Optimal Margin Classifiers", "work_type": "Research-paper candidate", "year": 1992, "year_display": "1992" }, { "audit_flags": [], "authors": "Cortes & Vapnik", "id": 22, "links": { "canonical_url": "https://link.springer.com/article/10.1007/BF00994018", "corrected_by_audit": false, "direct_url": "https://link.springer.com/article/10.1007/BF00994018", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Support-Vector%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Support-Vector%20Networks%20Cortes%201995", "semantic_scholar": "https://www.semanticscholar.org/search?q=Support-Vector%20Networks&sort=relevance" }, "supplied_direct_url": "https://link.springer.com/article/10.1007/BF00994018" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "Soft-margin SVMs", "title": "Support-Vector Networks", "work_type": "Research-paper candidate", "year": 1995, "year_display": "1995" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as book or textbook, not as a research paper.", "severity": "warning" } ], "authors": "Vapnik", "id": 23, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Statistical%20Learning%20Theory&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Statistical%20Learning%20Theory%20Vapnik%201998", "semantic_scholar": "https://www.semanticscholar.org/search?q=Statistical%20Learning%20Theory&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "VC dimension, structural risk minimization", "title": "Statistical Learning Theory", "work_type": "Book or textbook", "year": 1998, "year_display": "1998" }, { "audit_flags": [], "authors": "Breiman", "id": 24, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Bagging%20Predictors&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Bagging%20Predictors%20Breiman%201996", "semantic_scholar": "https://www.semanticscholar.org/search?q=Bagging%20Predictors&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "Bootstrap aggregating for ensemble methods", "title": "Bagging Predictors", "work_type": "Research-paper candidate", "year": 1996, "year_display": "1996" }, { "audit_flags": [], "authors": "Breiman", "id": 25, "links": { "canonical_url": "https://link.springer.com/article/10.1023/A:1010933404324", "corrected_by_audit": false, "direct_url": "https://link.springer.com/article/10.1023/A:1010933404324", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Random%20Forests&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Random%20Forests%20Breiman%202001", "semantic_scholar": "https://www.semanticscholar.org/search?q=Random%20Forests&sort=relevance" }, "supplied_direct_url": "https://link.springer.com/article/10.1023/A:1010933404324" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "Random forest algorithm", "title": "Random Forests", "work_type": "Research-paper candidate", "year": 2001, "year_display": "2001" }, { "audit_flags": [], "authors": "Freund & Schapire", "id": 26, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Decision-Theoretic%20Generalization%20of%20On-Line%20Learning%20%28AdaBoost%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Decision-Theoretic%20Generalization%20of%20On-Line%20Learning%20%28AdaBoost%29%20Freund%201997", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Decision-Theoretic%20Generalization%20of%20On-Line%20Learning%20%28AdaBoost%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "AdaBoost — adaptive boosting", "title": "A Decision-Theoretic Generalization of On-Line Learning (AdaBoost)", "work_type": "Research-paper candidate", "year": 1997, "year_display": "1997" }, { "audit_flags": [], "authors": "Chen & Guestrin", "id": 27, "links": { "canonical_url": "https://arxiv.org/abs/1603.02754", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1603.02754.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=XGBoost%3A%20A%20Scalable%20Tree%20Boosting%20System&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=XGBoost%3A%20A%20Scalable%20Tree%20Boosting%20System%20Chen%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=XGBoost%3A%20A%20Scalable%20Tree%20Boosting%20System&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1603.02754.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "Gradient boosted trees at scale", "title": "XGBoost: A Scalable Tree Boosting System", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Friedman", "id": 28, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Greedy%20Function%20Approximation%3A%20A%20Gradient%20Boosting%20Machine&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Greedy%20Function%20Approximation%3A%20A%20Gradient%20Boosting%20Machine%20Friedman%202001", "semantic_scholar": "https://www.semanticscholar.org/search?q=Greedy%20Function%20Approximation%3A%20A%20Gradient%20Boosting%20Machine&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "Gradient boosting framework", "title": "Greedy Function Approximation: A Gradient Boosting Machine", "work_type": "Research-paper candidate", "year": 2001, "year_display": "2001" }, { "audit_flags": [], "authors": "Guyon & Elisseeff", "id": 29, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=An%20Introduction%20to%20Variable%20and%20Feature%20Selection&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=An%20Introduction%20to%20Variable%20and%20Feature%20Selection%20Guyon%202003", "semantic_scholar": "https://www.semanticscholar.org/search?q=An%20Introduction%20to%20Variable%20and%20Feature%20Selection&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "Feature selection methods", "title": "An Introduction to Variable and Feature Selection", "work_type": "Research-paper candidate", "year": 2003, "year_display": "2003" }, { "audit_flags": [], "authors": "Blei, Ng, Jordan", "id": 30, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": "https://www.jmlr.org/papers/volume3/blei03a/blei03a.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Latent%20Dirichlet%20Allocation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Latent%20Dirichlet%20Allocation%20Blei%202003", "semantic_scholar": "https://www.semanticscholar.org/search?q=Latent%20Dirichlet%20Allocation&sort=relevance" }, "supplied_direct_url": "https://www.jmlr.org/papers/volume3/blei03a/blei03a.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "Topic modeling", "title": "Latent Dirichlet Allocation", "work_type": "Research-paper candidate", "year": 2003, "year_display": "2003" }, { "audit_flags": [], "authors": "Shlens", "id": 31, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Tutorial%20on%20Principal%20Component%20Analysis&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Tutorial%20on%20Principal%20Component%20Analysis%20Shlens%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Tutorial%20on%20Principal%20Component%20Analysis&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "PCA explained", "title": "A Tutorial on Principal Component Analysis", "work_type": "Survey or review", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Hinton & Salakhutdinov", "id": 32, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Reducing%20the%20Dimensionality%20of%20Data%20with%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Reducing%20the%20Dimensionality%20of%20Data%20with%20Neural%20Networks%20Hinton%202006", "semantic_scholar": "https://www.semanticscholar.org/search?q=Reducing%20the%20Dimensionality%20of%20Data%20with%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "Autoencoders for dimensionality reduction", "title": "Reducing the Dimensionality of Data with Neural Networks", "work_type": "Research-paper candidate", "year": 2006, "year_display": "2006" }, { "audit_flags": [], "authors": "Arthur & Vassilvitskii", "id": 33, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=K-Means%2B%2B%3A%20The%20Advantages%20of%20Careful%20Seeding&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=K-Means%2B%2B%3A%20The%20Advantages%20of%20Careful%20Seeding%20Arthur%202007", "semantic_scholar": "https://www.semanticscholar.org/search?q=K-Means%2B%2B%3A%20The%20Advantages%20of%20Careful%20Seeding&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "Improved k-means initialization", "title": "K-Means++: The Advantages of Careful Seeding", "work_type": "Research-paper candidate", "year": 2007, "year_display": "2007" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as book or textbook, not as a research paper.", "severity": "warning" } ], "authors": "Rasmussen & Williams", "id": 34, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Gaussian%20Processes%20for%20Machine%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Gaussian%20Processes%20for%20Machine%20Learning%20Rasmussen%202006", "semantic_scholar": "https://www.semanticscholar.org/search?q=Gaussian%20Processes%20for%20Machine%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "Gaussian process foundations", "title": "Gaussian Processes for Machine Learning", "work_type": "Book or textbook", "year": 2006, "year_display": "2006" }, { "audit_flags": [], "authors": "Wolpert & Macready", "id": 35, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=No%20Free%20Lunch%20Theorems%20for%20Optimization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=No%20Free%20Lunch%20Theorems%20for%20Optimization%20Wolpert%201997", "semantic_scholar": "https://www.semanticscholar.org/search?q=No%20Free%20Lunch%20Theorems%20for%20Optimization&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 2, "section_title": "Classical Machine Learning Foundations", "source_note": "No universal best algorithm", "title": "No Free Lunch Theorems for Optimization", "work_type": "Research-paper candidate", "year": 1997, "year_display": "1997" }, { "audit_flags": [], "authors": "Rumelhart, Hinton, Williams", "id": 36, "links": { "canonical_url": "https://www.nature.com/articles/323533a0", "corrected_by_audit": false, "direct_url": "https://www.nature.com/articles/323533a0", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Learning%20Representations%20by%20Back-Propagating%20Errors&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Learning%20Representations%20by%20Back-Propagating%20Errors%20Rumelhart%201986", "semantic_scholar": "https://www.semanticscholar.org/search?q=Learning%20Representations%20by%20Back-Propagating%20Errors&sort=relevance" }, "supplied_direct_url": "https://www.nature.com/articles/323533a0" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Backpropagation algorithm", "title": "Learning Representations by Back-Propagating Errors", "work_type": "Research-paper candidate", "year": 1986, "year_display": "1986" }, { "audit_flags": [], "authors": "Hornik, Stinchcombe, White", "id": 37, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Multilayer%20Feedforward%20Networks%20are%20Universal%20Approximators&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Multilayer%20Feedforward%20Networks%20are%20Universal%20Approximators%20Hornik%201989", "semantic_scholar": "https://www.semanticscholar.org/search?q=Multilayer%20Feedforward%20Networks%20are%20Universal%20Approximators&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Universal approximation theorem", "title": "Multilayer Feedforward Networks are Universal Approximators", "work_type": "Research-paper candidate", "year": 1989, "year_display": "1989" }, { "audit_flags": [], "authors": "Rumelhart, Hinton, Williams", "id": 38, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Learning%20Internal%20Representations%20by%20Error%20Propagation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Learning%20Internal%20Representations%20by%20Error%20Propagation%20Rumelhart%201985", "semantic_scholar": "https://www.semanticscholar.org/search?q=Learning%20Internal%20Representations%20by%20Error%20Propagation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Detailed backprop with hidden layers", "title": "Learning Internal Representations by Error Propagation", "work_type": "Research-paper candidate", "year": 1985, "year_display": "1985" }, { "audit_flags": [], "authors": "Hinton", "id": 39, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Connectionist%20Learning%20Procedures&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Connectionist%20Learning%20Procedures%20Hinton%201989", "semantic_scholar": "https://www.semanticscholar.org/search?q=Connectionist%20Learning%20Procedures&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Survey of early neural network training", "title": "Connectionist Learning Procedures", "work_type": "Research-paper candidate", "year": 1989, "year_display": "1989" }, { "audit_flags": [ { "code": "wrong_supplied_mapping_corrected", "message": "The supplied link named a different work and is corrected in this edition.", "original_target_title": "A collaborative framework to exchange and share product information within a supply chain context", "severity": "resolved" } ], "authors": "Hinton, Osindero, Teh", "id": 40, "links": { "canonical_url": null, "corrected_by_audit": true, "direct_url": "https://www.cs.toronto.edu/~hinton/absps/fastnc.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Fast%20Learning%20Algorithm%20for%20Deep%20Belief%20Nets&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Fast%20Learning%20Algorithm%20for%20Deep%20Belief%20Nets%20Hinton%202006", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Fast%20Learning%20Algorithm%20for%20Deep%20Belief%20Nets&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/0706.0507.pdf" }, "publication_identity_status": "audit_corrected_discovery", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Deep belief networks — reignited deep learning", "title": "A Fast Learning Algorithm for Deep Belief Nets", "work_type": "Research-paper candidate", "year": 2006, "year_display": "2006" }, { "audit_flags": [], "authors": "Bengio et al.", "id": 41, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Greedy%20Layer-Wise%20Training%20of%20Deep%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Greedy%20Layer-Wise%20Training%20of%20Deep%20Networks%20Bengio%202007", "semantic_scholar": "https://www.semanticscholar.org/search?q=Greedy%20Layer-Wise%20Training%20of%20Deep%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Layer-wise pretraining", "title": "Greedy Layer-Wise Training of Deep Networks", "work_type": "Research-paper candidate", "year": 2007, "year_display": "2007" }, { "audit_flags": [], "authors": "Glorot & Bengio", "id": 42, "links": { "canonical_url": "https://proceedings.mlr.press/v9/glorot10a.html", "corrected_by_audit": false, "direct_url": "https://proceedings.mlr.press/v9/glorot10a.html", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Understanding%20the%20Difficulty%20of%20Training%20Deep%20Feedforward%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Understanding%20the%20Difficulty%20of%20Training%20Deep%20Feedforward%20Neural%20Networks%20Glorot%202010", "semantic_scholar": "https://www.semanticscholar.org/search?q=Understanding%20the%20Difficulty%20of%20Training%20Deep%20Feedforward%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": "https://proceedings.mlr.press/v9/glorot10a.html" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Xavier initialization", "title": "Understanding the Difficulty of Training Deep Feedforward Neural Networks", "work_type": "Research-paper candidate", "year": 2010, "year_display": "2010" }, { "audit_flags": [], "authors": "Nair & Hinton", "id": 43, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Rectified%20Linear%20Units%20Improve%20Restricted%20Boltzmann%20Machines&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Rectified%20Linear%20Units%20Improve%20Restricted%20Boltzmann%20Machines%20Nair%202010", "semantic_scholar": "https://www.semanticscholar.org/search?q=Rectified%20Linear%20Units%20Improve%20Restricted%20Boltzmann%20Machines&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "ReLU activation function", "title": "Rectified Linear Units Improve Restricted Boltzmann Machines", "work_type": "Research-paper candidate", "year": 2010, "year_display": "2010" }, { "audit_flags": [], "authors": "Glorot, Bordes, Bengio", "id": 44, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Deep%20Sparse%20Rectifier%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Deep%20Sparse%20Rectifier%20Neural%20Networks%20Glorot%202011", "semantic_scholar": "https://www.semanticscholar.org/search?q=Deep%20Sparse%20Rectifier%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Sparsity benefits of ReLU", "title": "Deep Sparse Rectifier Neural Networks", "work_type": "Research-paper candidate", "year": 2011, "year_display": "2011" }, { "audit_flags": [], "authors": "Goodfellow et al.", "id": 45, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Maxout%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Maxout%20Networks%20Goodfellow%202013", "semantic_scholar": "https://www.semanticscholar.org/search?q=Maxout%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Maxout activation", "title": "Maxout Networks", "work_type": "Research-paper candidate", "year": 2013, "year_display": "2013" }, { "audit_flags": [], "authors": "Hinton et al.", "id": 46, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Improving%20Neural%20Networks%20by%20Preventing%20Co-Adaptation%20of%20Feature%20Detectors&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Improving%20Neural%20Networks%20by%20Preventing%20Co-Adaptation%20of%20Feature%20Detectors%20Hinton%202012", "semantic_scholar": "https://www.semanticscholar.org/search?q=Improving%20Neural%20Networks%20by%20Preventing%20Co-Adaptation%20of%20Feature%20Detectors&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Dropout — first paper", "title": "Improving Neural Networks by Preventing Co-Adaptation of Feature Detectors", "work_type": "Research-paper candidate", "year": 2012, "year_display": "2012" }, { "audit_flags": [], "authors": "Srivastava et al.", "id": 47, "links": { "canonical_url": "https://jmlr.org/papers/v15/srivastava14a.html", "corrected_by_audit": false, "direct_url": "https://jmlr.org/papers/v15/srivastava14a.html", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Dropout%3A%20A%20Simple%20Way%20to%20Prevent%20Neural%20Networks%20from%20Overfitting&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Dropout%3A%20A%20Simple%20Way%20to%20Prevent%20Neural%20Networks%20from%20Overfitting%20Srivastava%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Dropout%3A%20A%20Simple%20Way%20to%20Prevent%20Neural%20Networks%20from%20Overfitting&sort=relevance" }, "supplied_direct_url": "https://jmlr.org/papers/v15/srivastava14a.html" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Dropout — comprehensive treatment", "title": "Dropout: A Simple Way to Prevent Neural Networks from Overfitting", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Ioffe & Szegedy", "id": 48, "links": { "canonical_url": "https://arxiv.org/abs/1502.03167", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1502.03167.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Batch%20Normalization%3A%20Accelerating%20Deep%20Network%20Training&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Batch%20Normalization%3A%20Accelerating%20Deep%20Network%20Training%20Ioffe%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Batch%20Normalization%3A%20Accelerating%20Deep%20Network%20Training&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1502.03167.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Batch normalization", "title": "Batch Normalization: Accelerating Deep Network Training", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Ba, Kiros, Hinton", "id": 49, "links": { "canonical_url": "https://arxiv.org/abs/1607.06450", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1607.06450.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Layer%20Normalization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Layer%20Normalization%20Ba%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Layer%20Normalization&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1607.06450.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Layer normalization", "title": "Layer Normalization", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Wu & He", "id": 50, "links": { "canonical_url": "https://arxiv.org/abs/1803.08494", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1803.08494.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Group%20Normalization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Group%20Normalization%20Wu%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Group%20Normalization&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1803.08494.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Group normalization", "title": "Group Normalization", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "LeCun, Bengio, Hinton", "id": 51, "links": { "canonical_url": "https://www.nature.com/articles/nature14539", "corrected_by_audit": false, "direct_url": "https://www.nature.com/articles/nature14539", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Deep%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Deep%20Learning%20LeCun%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Deep%20Learning&sort=relevance" }, "supplied_direct_url": "https://www.nature.com/articles/nature14539" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Landmark review of deep learning in Nature", "title": "Deep Learning", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Bengio, Courville, Vincent", "id": 52, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Representation%20Learning%3A%20A%20Review&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Representation%20Learning%3A%20A%20Review%20Bengio%202013", "semantic_scholar": "https://www.semanticscholar.org/search?q=Representation%20Learning%3A%20A%20Review&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Survey on learning representations", "title": "Representation Learning: A Review", "work_type": "Survey or review", "year": 2013, "year_display": "2013" }, { "audit_flags": [], "authors": "Montufar et al.", "id": 53, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=On%20the%20Number%20of%20Linear%20Regions%20of%20Deep%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=On%20the%20Number%20of%20Linear%20Regions%20of%20Deep%20Neural%20Networks%20Montufar%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=On%20the%20Number%20of%20Linear%20Regions%20of%20Deep%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Expressivity of deep networks", "title": "On the Number of Linear Regions of Deep Neural Networks", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "He et al.", "id": 54, "links": { "canonical_url": "https://arxiv.org/abs/1603.05027", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1603.05027.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Residual%20Learning%20%28Identity%20Mappings%20in%20Deep%20Residual%20Networks%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Residual%20Learning%20%28Identity%20Mappings%20in%20Deep%20Residual%20Networks%29%20He%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Residual%20Learning%20%28Identity%20Mappings%20in%20Deep%20Residual%20Networks%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1603.05027.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Pre-activation ResNets", "title": "Residual Learning (Identity Mappings in Deep Residual Networks)", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Frankle & Carlin", "id": 55, "links": { "canonical_url": "https://arxiv.org/abs/1803.03635", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1803.03635.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Lottery%20Ticket%20Hypothesis&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Lottery%20Ticket%20Hypothesis%20Frankle%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Lottery%20Ticket%20Hypothesis&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1803.03635.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 3, "section_title": "Neural Network Foundations", "source_note": "Sparse subnetworks in dense networks", "title": "The Lottery Ticket Hypothesis", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Robbins & Monro", "id": 56, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Stochastic%20Approximation%20Method&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Stochastic%20Approximation%20Method%20Robbins%201951", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Stochastic%20Approximation%20Method&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Stochastic gradient descent foundations", "title": "A Stochastic Approximation Method", "work_type": "Research-paper candidate", "year": 1951, "year_display": "1951" }, { "audit_flags": [], "authors": "Sutskever et al.", "id": 57, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=On%20the%20Importance%20of%20Initialization%20and%20Momentum%20in%20Deep%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=On%20the%20Importance%20of%20Initialization%20and%20Momentum%20in%20Deep%20Learning%20Sutskever%202013", "semantic_scholar": "https://www.semanticscholar.org/search?q=On%20the%20Importance%20of%20Initialization%20and%20Momentum%20in%20Deep%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Momentum in SGD", "title": "On the Importance of Initialization and Momentum in Deep Learning", "work_type": "Research-paper candidate", "year": 2013, "year_display": "2013" }, { "audit_flags": [], "authors": "Zeiler", "id": 58, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ADADELTA%3A%20An%20Adaptive%20Learning%20Rate%20Method&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ADADELTA%3A%20An%20Adaptive%20Learning%20Rate%20Method%20Zeiler%202012", "semantic_scholar": "https://www.semanticscholar.org/search?q=ADADELTA%3A%20An%20Adaptive%20Learning%20Rate%20Method&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Adaptive learning rates", "title": "ADADELTA: An Adaptive Learning Rate Method", "work_type": "Research-paper candidate", "year": 2012, "year_display": "2012" }, { "audit_flags": [], "authors": "Kingma & Ba", "id": 59, "links": { "canonical_url": "https://arxiv.org/abs/1412.6980", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1412.6980.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Adam%3A%20A%20Method%20for%20Stochastic%20Optimization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Adam%3A%20A%20Method%20for%20Stochastic%20Optimization%20Kingma%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Adam%3A%20A%20Method%20for%20Stochastic%20Optimization&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1412.6980.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Adam optimizer", "title": "Adam: A Method for Stochastic Optimization", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Loshchilov & Hutter", "id": 60, "links": { "canonical_url": "https://arxiv.org/abs/1711.05101", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1711.05101.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Decoupled%20Weight%20Decay%20Regularization%20%28AdamW%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Decoupled%20Weight%20Decay%20Regularization%20%28AdamW%29%20Loshchilov%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Decoupled%20Weight%20Decay%20Regularization%20%28AdamW%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1711.05101.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "AdamW — fixes weight decay in Adam", "title": "Decoupled Weight Decay Regularization (AdamW)", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Loshchilov & Hutter", "id": 61, "links": { "canonical_url": "https://arxiv.org/abs/1608.03983", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1608.03983.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SGDR%3A%20Stochastic%20Gradient%20Descent%20with%20Warm%20Restarts&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SGDR%3A%20Stochastic%20Gradient%20Descent%20with%20Warm%20Restarts%20Loshchilov%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=SGDR%3A%20Stochastic%20Gradient%20Descent%20with%20Warm%20Restarts&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1608.03983.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Cosine annealing learning rate schedule", "title": "SGDR: Stochastic Gradient Descent with Warm Restarts", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Smith", "id": 62, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Cyclical%20Learning%20Rates%20for%20Training%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Cyclical%20Learning%20Rates%20for%20Training%20Neural%20Networks%20Smith%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Cyclical%20Learning%20Rates%20for%20Training%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Cyclical learning rates", "title": "Cyclical Learning Rates for Training Neural Networks", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Smith & Topin", "id": 63, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Super-Convergence&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Super-Convergence%20Smith%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Super-Convergence&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Very fast training with large learning rates", "title": "Super-Convergence", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "You et al.", "id": 64, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Large%20Batch%20Training%20of%20Convolutional%20Networks%20%28LARS%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Large%20Batch%20Training%20of%20Convolutional%20Networks%20%28LARS%29%20You%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Large%20Batch%20Training%20of%20Convolutional%20Networks%20%28LARS%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Layer-wise adaptive rate scaling", "title": "Large Batch Training of Convolutional Networks (LARS)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "You et al.", "id": 65, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Large%20Batch%20Optimization%20%28LAMB%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Large%20Batch%20Optimization%20%28LAMB%29%20You%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Large%20Batch%20Optimization%20%28LAMB%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Layerwise Adaptive Moments for BERT training", "title": "Large Batch Optimization (LAMB)", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Foret et al.", "id": 66, "links": { "canonical_url": "https://arxiv.org/abs/2010.01412", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2010.01412.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Sharpness-Aware%20Minimization%20%28SAM%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Sharpness-Aware%20Minimization%20%28SAM%29%20Foret%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Sharpness-Aware%20Minimization%20%28SAM%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2010.01412.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Seeking flat minima for generalization", "title": "Sharpness-Aware Minimization (SAM)", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Ruder", "id": 67, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=An%20Overview%20of%20Gradient%20Descent%20Optimization%20Algorithms&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=An%20Overview%20of%20Gradient%20Descent%20Optimization%20Algorithms%20Ruder%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=An%20Overview%20of%20Gradient%20Descent%20Optimization%20Algorithms&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Comprehensive optimization survey", "title": "An Overview of Gradient Descent Optimization Algorithms", "work_type": "Survey or review", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Loshchilov & Hutter", "id": 68, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Fixing%20Weight%20Decay%20Regularization%20in%20Adam&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Fixing%20Weight%20Decay%20Regularization%20in%20Adam%20Loshchilov%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Fixing%20Weight%20Decay%20Regularization%20in%20Adam&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Weight decay vs L2 in Adam", "title": "Fixing Weight Decay Regularization in Adam", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Micikevicius et al.", "id": 69, "links": { "canonical_url": "https://arxiv.org/abs/1710.03740", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1710.03740.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mixed%20Precision%20Training&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mixed%20Precision%20Training%20Micikevicius%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mixed%20Precision%20Training&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1710.03740.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "FP16 training for speed and memory", "title": "Mixed Precision Training", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "NVIDIA", "id": 70, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Automatic%20Mixed%20Precision&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Automatic%20Mixed%20Precision%20NVIDIA%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Automatic%20Mixed%20Precision&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Practical mixed precision", "title": "Automatic Mixed Precision", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Chen et al.", "id": 71, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Gradient%20Checkpointing&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Gradient%20Checkpointing%20Chen%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Gradient%20Checkpointing&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Memory-efficient backprop", "title": "Gradient Checkpointing", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Li et al.", "id": 72, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Data%20Parallelism%20%28PyTorch%20Distributed%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Data%20Parallelism%20%28PyTorch%20Distributed%29%20Li%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Data%20Parallelism%20%28PyTorch%20Distributed%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Distributed data parallel training", "title": "Data Parallelism (PyTorch Distributed)", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Rajbhandari et al.", "id": 73, "links": { "canonical_url": "https://arxiv.org/abs/1910.02054", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1910.02054.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ZeRO%3A%20Memory%20Optimizations%20Toward%20Training%20Trillion%20Parameter%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ZeRO%3A%20Memory%20Optimizations%20Toward%20Training%20Trillion%20Parameter%20Models%20Rajbhandari%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=ZeRO%3A%20Memory%20Optimizations%20Toward%20Training%20Trillion%20Parameter%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1910.02054.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "ZeRO optimizer — memory efficient", "title": "ZeRO: Memory Optimizations Toward Training Trillion Parameter Models", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Rasley et al.", "id": 74, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeepSpeed&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeepSpeed%20Rasley%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeepSpeed&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Deep learning optimization library", "title": "DeepSpeed", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Shoeybi et al.", "id": 75, "links": { "canonical_url": "https://arxiv.org/abs/1909.08053", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1909.08053.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Megatron-LM%3A%20Training%20Multi-Billion%20Parameter%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Megatron-LM%3A%20Training%20Multi-Billion%20Parameter%20Language%20Models%20Shoeybi%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Megatron-LM%3A%20Training%20Multi-Billion%20Parameter%20Language%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1909.08053.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 4, "section_title": "Optimization & Training Techniques", "source_note": "Model parallelism for large LMs", "title": "Megatron-LM: Training Multi-Billion Parameter Language Models", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Fukushima", "id": 76, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Neocognitron%3A%20A%20Self-Organizing%20Neural%20Network%20Model&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Neocognitron%3A%20A%20Self-Organizing%20Neural%20Network%20Model%20Fukushima%201980", "semantic_scholar": "https://www.semanticscholar.org/search?q=Neocognitron%3A%20A%20Self-Organizing%20Neural%20Network%20Model&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Precursor to CNNs", "title": "Neocognitron: A Self-Organizing Neural Network Model", "work_type": "Research-paper candidate", "year": 1980, "year_display": "1980" }, { "audit_flags": [], "authors": "LeCun et al.", "id": 77, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": "https://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Gradient-Based%20Learning%20Applied%20to%20Document%20Recognition%20%28LeNet%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Gradient-Based%20Learning%20Applied%20to%20Document%20Recognition%20%28LeNet%29%20LeCun%201998", "semantic_scholar": "https://www.semanticscholar.org/search?q=Gradient-Based%20Learning%20Applied%20to%20Document%20Recognition%20%28LeNet%29&sort=relevance" }, "supplied_direct_url": "https://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "LeNet — CNNs for digit recognition", "title": "Gradient-Based Learning Applied to Document Recognition (LeNet)", "work_type": "Research-paper candidate", "year": 1998, "year_display": "1998" }, { "audit_flags": [], "authors": "Krizhevsky, Sutskever, Hinton", "id": 78, "links": { "canonical_url": "https://papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html", "corrected_by_audit": false, "direct_url": "https://papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ImageNet%20Classification%20with%20Deep%20CNNs%20%28AlexNet%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ImageNet%20Classification%20with%20Deep%20CNNs%20%28AlexNet%29%20Krizhevsky%202012", "semantic_scholar": "https://www.semanticscholar.org/search?q=ImageNet%20Classification%20with%20Deep%20CNNs%20%28AlexNet%29&sort=relevance" }, "supplied_direct_url": "https://papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "AlexNet — deep learning revolution", "title": "ImageNet Classification with Deep CNNs (AlexNet)", "work_type": "Research-paper candidate", "year": 2012, "year_display": "2012" }, { "audit_flags": [ { "code": "wrong_supplied_mapping_corrected", "message": "The supplied link named a different work and is corrected in this edition.", "original_target_title": "Multi-epoch VLBA H2O maser observations toward the massive YSOs AFGL 2591 VLA 2 and VLA 3", "severity": "resolved" } ], "authors": "Zeiler & Fergus", "id": 79, "links": { "canonical_url": "https://arxiv.org/abs/1311.2901", "corrected_by_audit": true, "direct_url": "https://arxiv.org/pdf/1311.2901.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Visualizing%20and%20Understanding%20Convolutional%20Networks%20%28ZFNet%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Visualizing%20and%20Understanding%20Convolutional%20Networks%20%28ZFNet%29%20Zeiler%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Visualizing%20and%20Understanding%20Convolutional%20Networks%20%28ZFNet%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1311.1901.pdf" }, "publication_identity_status": "audit_corrected_discovery", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "CNN visualization & understanding", "title": "Visualizing and Understanding Convolutional Networks (ZFNet)", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Simonyan & Zisserman", "id": 80, "links": { "canonical_url": "https://arxiv.org/abs/1409.1556", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1409.1556.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Very%20Deep%20Convolutional%20Networks%20%28VGGNet%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Very%20Deep%20Convolutional%20Networks%20%28VGGNet%29%20Simonyan%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Very%20Deep%20Convolutional%20Networks%20%28VGGNet%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1409.1556.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "VGG — depth matters", "title": "Very Deep Convolutional Networks (VGGNet)", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Szegedy et al.", "id": 81, "links": { "canonical_url": "https://arxiv.org/abs/1409.4842", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1409.4842.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Going%20Deeper%20with%20Convolutions%20%28GoogLeNet/Inception%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Going%20Deeper%20with%20Convolutions%20%28GoogLeNet/Inception%29%20Szegedy%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Going%20Deeper%20with%20Convolutions%20%28GoogLeNet/Inception%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1409.4842.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Inception modules", "title": "Going Deeper with Convolutions (GoogLeNet/Inception)", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "He et al.", "id": 82, "links": { "canonical_url": "https://arxiv.org/abs/1512.03385", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1512.03385.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Deep%20Residual%20Learning%20for%20Image%20Recognition%20%28ResNet%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Deep%20Residual%20Learning%20for%20Image%20Recognition%20%28ResNet%29%20He%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Deep%20Residual%20Learning%20for%20Image%20Recognition%20%28ResNet%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1512.03385.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Skip connections — 152 layers", "title": "Deep Residual Learning for Image Recognition (ResNet)", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Huang et al.", "id": 83, "links": { "canonical_url": "https://arxiv.org/abs/1608.06993", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1608.06993.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Densely%20Connected%20Convolutional%20Networks%20%28DenseNet%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Densely%20Connected%20Convolutional%20Networks%20%28DenseNet%29%20Huang%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Densely%20Connected%20Convolutional%20Networks%20%28DenseNet%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1608.06993.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Dense connections between layers", "title": "Densely Connected Convolutional Networks (DenseNet)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Xie et al.", "id": 84, "links": { "canonical_url": "https://arxiv.org/abs/1611.05431", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1611.05431.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Aggregated%20Residual%20Transformations%20%28ResNeXt%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Aggregated%20Residual%20Transformations%20%28ResNeXt%29%20Xie%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Aggregated%20Residual%20Transformations%20%28ResNeXt%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1611.05431.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Grouped convolutions at scale", "title": "Aggregated Residual Transformations (ResNeXt)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 961 ], "severity": "warning" } ], "authors": "Hu, Shen, Sun", "id": 85, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Squeeze-and-Excitation%20Networks%20%28SENet%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Squeeze-and-Excitation%20Networks%20%28SENet%29%20Hu%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Squeeze-and-Excitation%20Networks%20%28SENet%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Channel attention", "title": "Squeeze-and-Excitation Networks (SENet)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 747 ], "severity": "warning" } ], "authors": "Tan & Le", "id": 86, "links": { "canonical_url": "https://arxiv.org/abs/1905.11946", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1905.11946.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=EfficientNet%3A%20Rethinking%20Model%20Scaling&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=EfficientNet%3A%20Rethinking%20Model%20Scaling%20Tan%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=EfficientNet%3A%20Rethinking%20Model%20Scaling&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1905.11946.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Compound scaling for CNNs", "title": "EfficientNet: Rethinking Model Scaling", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Lin, Chen, Yan", "id": 87, "links": { "canonical_url": "https://arxiv.org/abs/1312.4400", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1312.4400.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Network%20In%20Network&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Network%20In%20Network%20Lin%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Network%20In%20Network&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1312.4400.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "1x1 convolutions", "title": "Network In Network", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Jaderberg et al.", "id": 88, "links": { "canonical_url": "https://arxiv.org/abs/1506.02025", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1506.02025.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Spatial%20Transformer%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Spatial%20Transformer%20Networks%20Jaderberg%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Spatial%20Transformer%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1506.02025.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Learnable spatial transformations", "title": "Spatial Transformer Networks", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Lin et al.", "id": 89, "links": { "canonical_url": "https://arxiv.org/abs/1612.03144", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1612.03144.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Feature%20Pyramid%20Networks%20for%20Object%20Detection&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Feature%20Pyramid%20Networks%20for%20Object%20Detection%20Lin%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Feature%20Pyramid%20Networks%20for%20Object%20Detection&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1612.03144.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Multi-scale feature pyramids", "title": "Feature Pyramid Networks for Object Detection", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Ren et al.", "id": 90, "links": { "canonical_url": "https://arxiv.org/abs/1506.01497", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1506.01497.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Faster%20R-CNN&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Faster%20R-CNN%20Ren%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Faster%20R-CNN&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1506.01497.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Region proposal networks", "title": "Faster R-CNN", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Redmon et al.", "id": 91, "links": { "canonical_url": "https://arxiv.org/abs/1506.02640", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1506.02640.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=You%20Only%20Look%20Once%20%28YOLO%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=You%20Only%20Look%20Once%20%28YOLO%29%20Redmon%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=You%20Only%20Look%20Once%20%28YOLO%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1506.02640.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Real-time object detection", "title": "You Only Look Once (YOLO)", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Liu et al.", "id": 92, "links": { "canonical_url": "https://arxiv.org/abs/1512.02325", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1512.02325.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SSD%3A%20Single%20Shot%20MultiBox%20Detector&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SSD%3A%20Single%20Shot%20MultiBox%20Detector%20Liu%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=SSD%3A%20Single%20Shot%20MultiBox%20Detector&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1512.02325.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Single-shot detection", "title": "SSD: Single Shot MultiBox Detector", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Lin et al.", "id": 93, "links": { "canonical_url": "https://arxiv.org/abs/1708.02002", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1708.02002.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Focal%20Loss%20for%20Dense%20Object%20Detection%20%28RetinaNet%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Focal%20Loss%20for%20Dense%20Object%20Detection%20%28RetinaNet%29%20Lin%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Focal%20Loss%20for%20Dense%20Object%20Detection%20%28RetinaNet%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1708.02002.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Focal loss — class imbalance", "title": "Focal Loss for Dense Object Detection (RetinaNet)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "He et al.", "id": 94, "links": { "canonical_url": "https://arxiv.org/abs/1703.06870", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1703.06870.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mask%20R-CNN&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mask%20R-CNN%20He%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mask%20R-CNN&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1703.06870.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Instance segmentation", "title": "Mask R-CNN", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Ronneberger et al.", "id": 95, "links": { "canonical_url": "https://arxiv.org/abs/1505.04597", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1505.04597.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=U-Net%3A%20CNNs%20for%20Biomedical%20Image%20Segmentation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=U-Net%3A%20CNNs%20for%20Biomedical%20Image%20Segmentation%20Ronneberger%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=U-Net%3A%20CNNs%20for%20Biomedical%20Image%20Segmentation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1505.04597.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "U-Net architecture", "title": "U-Net: CNNs for Biomedical Image Segmentation", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Long, Shelhamer, Darrell", "id": 96, "links": { "canonical_url": "https://arxiv.org/abs/1411.4038", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1411.4038.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Fully%20Convolutional%20Networks%20for%20Semantic%20Segmentation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Fully%20Convolutional%20Networks%20for%20Semantic%20Segmentation%20Long%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Fully%20Convolutional%20Networks%20for%20Semantic%20Segmentation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1411.4038.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "FCN for segmentation", "title": "Fully Convolutional Networks for Semantic Segmentation", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Chen et al.", "id": 97, "links": { "canonical_url": "https://arxiv.org/abs/1412.7062", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1412.7062.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeepLab%3A%20Semantic%20Image%20Segmentation%20with%20Deep%20CNNs%20and%20CRFs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeepLab%3A%20Semantic%20Image%20Segmentation%20with%20Deep%20CNNs%20and%20CRFs%20Chen%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeepLab%3A%20Semantic%20Image%20Segmentation%20with%20Deep%20CNNs%20and%20CRFs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1412.7062.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Atrous convolution, CRFs", "title": "DeepLab: Semantic Image Segmentation with Deep CNNs and CRFs", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Dosovitskiy et al.", "id": 98, "links": { "canonical_url": "https://arxiv.org/abs/2010.11929", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2010.11929.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=An%20Image%20is%20Worth%2016x16%20Words%20%28ViT%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=An%20Image%20is%20Worth%2016x16%20Words%20%28ViT%29%20Dosovitskiy%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=An%20Image%20is%20Worth%2016x16%20Words%20%28ViT%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2010.11929.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Vision Transformer", "title": "An Image is Worth 16x16 Words (ViT)", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Liu et al.", "id": 99, "links": { "canonical_url": "https://arxiv.org/abs/2103.14030", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2103.14030.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Swin%20Transformer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Swin%20Transformer%20Liu%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Swin%20Transformer&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2103.14030.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Shifted window transformer for vision", "title": "Swin Transformer", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Liu et al.", "id": 100, "links": { "canonical_url": "https://arxiv.org/abs/2201.03545", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2201.03545.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ConvNeXt%3A%20A%20ConvNet%20for%20the%202020s&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ConvNeXt%3A%20A%20ConvNet%20for%20the%202020s%20Liu%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=ConvNeXt%3A%20A%20ConvNet%20for%20the%202020s&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2201.03545.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 5, "section_title": "Convolutional Neural Networks & Computer Vision", "source_note": "Modernized CNN rivaling ViTs", "title": "ConvNeXt: A ConvNet for the 2020s", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Elman", "id": 101, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Finding%20Structure%20in%20Time&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Finding%20Structure%20in%20Time%20Elman%201990", "semantic_scholar": "https://www.semanticscholar.org/search?q=Finding%20Structure%20in%20Time&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Elman RNN — simple recurrent network", "title": "Finding Structure in Time", "work_type": "Research-paper candidate", "year": 1990, "year_display": "1990" }, { "audit_flags": [], "authors": "Hochreiter & Schmidhuber", "id": 102, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": "https://www.bioinf.jku.at/publications/older/2604.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Long%20Short-Term%20Memory%20%28LSTM%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Long%20Short-Term%20Memory%20%28LSTM%29%20Hochreiter%201997", "semantic_scholar": "https://www.semanticscholar.org/search?q=Long%20Short-Term%20Memory%20%28LSTM%29&sort=relevance" }, "supplied_direct_url": "https://www.bioinf.jku.at/publications/older/2604.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "LSTM — solving vanishing gradients", "title": "Long Short-Term Memory (LSTM)", "work_type": "Research-paper candidate", "year": 1997, "year_display": "1997" }, { "audit_flags": [], "authors": "Gers, Schmidhuber, Cummins", "id": 103, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Learning%20to%20Forget%3A%20Continual%20Prediction%20with%20LSTM&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Learning%20to%20Forget%3A%20Continual%20Prediction%20with%20LSTM%20Gers%202000", "semantic_scholar": "https://www.semanticscholar.org/search?q=Learning%20to%20Forget%3A%20Continual%20Prediction%20with%20LSTM&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Forget gate in LSTM", "title": "Learning to Forget: Continual Prediction with LSTM", "work_type": "Research-paper candidate", "year": 2000, "year_display": "2000" }, { "audit_flags": [], "authors": "Cho et al.", "id": 104, "links": { "canonical_url": "https://arxiv.org/abs/1406.1078", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1406.1078.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Learning%20Phrase%20Representations%20using%20RNN%20Encoder-Decoder%20%28GRU%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Learning%20Phrase%20Representations%20using%20RNN%20Encoder-Decoder%20%28GRU%29%20Cho%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Learning%20Phrase%20Representations%20using%20RNN%20Encoder-Decoder%20%28GRU%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1406.1078.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "GRU — simplified gated RNN", "title": "Learning Phrase Representations using RNN Encoder-Decoder (GRU)", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Sutskever, Vinyals, Le", "id": 105, "links": { "canonical_url": "https://arxiv.org/abs/1409.3215", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1409.3215.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Sequence%20to%20Sequence%20Learning%20with%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Sequence%20to%20Sequence%20Learning%20with%20Neural%20Networks%20Sutskever%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Sequence%20to%20Sequence%20Learning%20with%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1409.3215.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Seq2seq — encoder-decoder for translation", "title": "Sequence to Sequence Learning with Neural Networks", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Bahdanau, Cho, Bengio", "id": 106, "links": { "canonical_url": "https://arxiv.org/abs/1409.0473", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1409.0473.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Neural%20Machine%20Translation%20by%20Jointly%20Learning%20to%20Align%20and%20Translate&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Neural%20Machine%20Translation%20by%20Jointly%20Learning%20to%20Align%20and%20Translate%20Bahdanau%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Neural%20Machine%20Translation%20by%20Jointly%20Learning%20to%20Align%20and%20Translate&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1409.0473.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Attention mechanism for NMT", "title": "Neural Machine Translation by Jointly Learning to Align and Translate", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Luong, Pham, Manning", "id": 107, "links": { "canonical_url": "https://arxiv.org/abs/1508.04025", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1508.04025.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Effective%20Approaches%20to%20Attention-based%20Neural%20Machine%20Translation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Effective%20Approaches%20to%20Attention-based%20Neural%20Machine%20Translation%20Luong%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Effective%20Approaches%20to%20Attention-based%20Neural%20Machine%20Translation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1508.04025.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Global vs local attention", "title": "Effective Approaches to Attention-based Neural Machine Translation", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Graves et al.", "id": 108, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": "https://www.cs.toronto.edu/~graves/icml_2006.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Connectionist%20Temporal%20Classification%20%28CTC%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Connectionist%20Temporal%20Classification%20%28CTC%29%20Graves%202006", "semantic_scholar": "https://www.semanticscholar.org/search?q=Connectionist%20Temporal%20Classification%20%28CTC%29&sort=relevance" }, "supplied_direct_url": "https://www.cs.toronto.edu/~graves/icml_2006.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "CTC loss for sequence labeling", "title": "Connectionist Temporal Classification (CTC)", "work_type": "Research-paper candidate", "year": 2006, "year_display": "2006" }, { "audit_flags": [], "authors": "Graves, Mohamed, Hinton", "id": 109, "links": { "canonical_url": "https://arxiv.org/abs/1303.5778", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1303.5778.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Speech%20Recognition%20with%20Deep%20Recurrent%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Speech%20Recognition%20with%20Deep%20Recurrent%20Neural%20Networks%20Graves%202013", "semantic_scholar": "https://www.semanticscholar.org/search?q=Speech%20Recognition%20with%20Deep%20Recurrent%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1303.5778.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Deep bidirectional LSTM for ASR", "title": "Speech Recognition with Deep Recurrent Neural Networks", "work_type": "Research-paper candidate", "year": 2013, "year_display": "2013" }, { "audit_flags": [], "authors": "Vinyals, Fortunato, Jaitly", "id": 110, "links": { "canonical_url": "https://arxiv.org/abs/1506.03134", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1506.03134.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Pointer%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Pointer%20Networks%20Vinyals%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Pointer%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1506.03134.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Attention as pointer to input", "title": "Pointer Networks", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Graves", "id": 111, "links": { "canonical_url": "https://arxiv.org/abs/1308.0850", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1308.0850.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Generating%20Sequences%20with%20Recurrent%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Generating%20Sequences%20with%20Recurrent%20Neural%20Networks%20Graves%202013", "semantic_scholar": "https://www.semanticscholar.org/search?q=Generating%20Sequences%20with%20Recurrent%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1308.0850.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Handwriting/text generation with RNNs", "title": "Generating Sequences with Recurrent Neural Networks", "work_type": "Research-paper candidate", "year": 2013, "year_display": "2013" }, { "audit_flags": [], "authors": "Schuster & Paliwal", "id": 112, "links": { "canonical_url": "https://ieeexplore.ieee.org/document/650093", "corrected_by_audit": false, "direct_url": "https://ieeexplore.ieee.org/document/650093", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Bidirectional%20Recurrent%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Bidirectional%20Recurrent%20Neural%20Networks%20Schuster%201997", "semantic_scholar": "https://www.semanticscholar.org/search?q=Bidirectional%20Recurrent%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": "https://ieeexplore.ieee.org/document/650093" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Bidirectional RNNs", "title": "Bidirectional Recurrent Neural Networks", "work_type": "Research-paper candidate", "year": 1997, "year_display": "1997" }, { "audit_flags": [], "authors": "Vinyals et al.", "id": 113, "links": { "canonical_url": "https://arxiv.org/abs/1411.4555", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1411.4555.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Show%20and%20Tell%3A%20A%20Neural%20Image%20Caption%20Generator&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Show%20and%20Tell%3A%20A%20Neural%20Image%20Caption%20Generator%20Vinyals%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Show%20and%20Tell%3A%20A%20Neural%20Image%20Caption%20Generator&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1411.4555.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "CNN-LSTM image captioning", "title": "Show and Tell: A Neural Image Caption Generator", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Graves, Wayne, Danihelka", "id": 114, "links": { "canonical_url": "https://arxiv.org/abs/1410.5401", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1410.5401.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Neural%20Turing%20Machines&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Neural%20Turing%20Machines%20Graves%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Neural%20Turing%20Machines&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1410.5401.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "External memory with neural nets", "title": "Neural Turing Machines", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Weston, Chopra, Bordes", "id": 115, "links": { "canonical_url": "https://arxiv.org/abs/1410.3916", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1410.3916.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Memory%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Memory%20Networks%20Weston%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Memory%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1410.3916.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "End-to-end memory networks", "title": "Memory Networks", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 966 ], "severity": "warning" } ], "authors": "Bai, Kolter, Koltun", "id": 116, "links": { "canonical_url": "https://arxiv.org/abs/1803.01271", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1803.01271.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Temporal%20Convolutional%20Networks%20%28TCN%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Temporal%20Convolutional%20Networks%20%28TCN%29%20Bai%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Temporal%20Convolutional%20Networks%20%28TCN%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1803.01271.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Causal convolutions vs RNNs", "title": "Temporal Convolutional Networks (TCN)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Bradbury et al.", "id": 117, "links": { "canonical_url": "https://arxiv.org/abs/1611.01576", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1611.01576.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Quasi-Recurrent%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Quasi-Recurrent%20Neural%20Networks%20Bradbury%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Quasi-Recurrent%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1611.01576.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Parallelizable recurrence", "title": "Quasi-Recurrent Neural Networks", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Li et al.", "id": 118, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Independently%20Recurrent%20Neural%20Network%20%28IndRNN%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Independently%20Recurrent%20Neural%20Network%20%28IndRNN%29%20Li%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Independently%20Recurrent%20Neural%20Network%20%28IndRNN%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Longer memory, gradient stability", "title": "Independently Recurrent Neural Network (IndRNN)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Santoro et al.", "id": 119, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Relational%20Recurrent%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Relational%20Recurrent%20Neural%20Networks%20Santoro%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Relational%20Recurrent%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Relational reasoning in RNNs", "title": "Relational Recurrent Neural Networks", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "van den Oord et al.", "id": 120, "links": { "canonical_url": "https://arxiv.org/abs/1609.03499", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1609.03499.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=WaveNet%3A%20A%20Generative%20Model%20for%20Raw%20Audio&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=WaveNet%3A%20A%20Generative%20Model%20for%20Raw%20Audio%20van%20den%20Oord%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=WaveNet%3A%20A%20Generative%20Model%20for%20Raw%20Audio&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1609.03499.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 6, "section_title": "Recurrent Neural Networks & Sequence Modeling", "source_note": "Autoregressive audio generation", "title": "WaveNet: A Generative Model for Raw Audio", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Kingma & Welling", "id": 121, "links": { "canonical_url": "https://arxiv.org/abs/1312.6114", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1312.6114.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Auto-Encoding%20Variational%20Bayes%20%28VAE%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Auto-Encoding%20Variational%20Bayes%20%28VAE%29%20Kingma%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Auto-Encoding%20Variational%20Bayes%20%28VAE%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1312.6114.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "Variational Autoencoders", "title": "Auto-Encoding Variational Bayes (VAE)", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Goodfellow et al.", "id": 122, "links": { "canonical_url": "https://arxiv.org/abs/1406.2661", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1406.2661.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Generative%20Adversarial%20Networks%20%28GAN%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Generative%20Adversarial%20Networks%20%28GAN%29%20Goodfellow%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Generative%20Adversarial%20Networks%20%28GAN%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1406.2661.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "GANs — adversarial training", "title": "Generative Adversarial Networks (GAN)", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Mirza & Osindero", "id": 123, "links": { "canonical_url": "https://arxiv.org/abs/1411.1784", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1411.1784.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Conditional%20Generative%20Adversarial%20Nets&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Conditional%20Generative%20Adversarial%20Nets%20Mirza%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Conditional%20Generative%20Adversarial%20Nets&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1411.1784.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "Class-conditional GANs", "title": "Conditional Generative Adversarial Nets", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Radford, Metz, Chintala", "id": 124, "links": { "canonical_url": "https://arxiv.org/abs/1511.06434", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1511.06434.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Unsupervised%20Representation%20Learning%20with%20DCGANs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Unsupervised%20Representation%20Learning%20with%20DCGANs%20Radford%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Unsupervised%20Representation%20Learning%20with%20DCGANs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1511.06434.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "Deep convolutional GANs", "title": "Unsupervised Representation Learning with DCGANs", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Salimans et al.", "id": 125, "links": { "canonical_url": "https://arxiv.org/abs/1606.03498", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1606.03498.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Improved%20Techniques%20for%20Training%20GANs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Improved%20Techniques%20for%20Training%20GANs%20Salimans%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Improved%20Techniques%20for%20Training%20GANs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1606.03498.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "GAN training stabilization", "title": "Improved Techniques for Training GANs", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Arjovsky, Chintala, Bottou", "id": 126, "links": { "canonical_url": "https://arxiv.org/abs/1701.07875", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1701.07875.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Wasserstein%20GAN&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Wasserstein%20GAN%20Arjovsky%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Wasserstein%20GAN&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1701.07875.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "WGAN — Earth mover's distance", "title": "Wasserstein GAN", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Karras, Aila, Laine, Lehtinen", "id": 127, "links": { "canonical_url": "https://arxiv.org/abs/1710.10196", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1710.10196.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Progressive%20Growing%20of%20GANs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Progressive%20Growing%20of%20GANs%20Karras%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Progressive%20Growing%20of%20GANs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1710.10196.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "High-res image generation", "title": "Progressive Growing of GANs", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Karras, Laine, Aila", "id": 128, "links": { "canonical_url": "https://arxiv.org/abs/1812.04948", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1812.04948.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Style-Based%20Generator%20Architecture%20%28StyleGAN%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Style-Based%20Generator%20Architecture%20%28StyleGAN%29%20Karras%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Style-Based%20Generator%20Architecture%20%28StyleGAN%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1812.04948.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "StyleGAN", "title": "A Style-Based Generator Architecture (StyleGAN)", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Karras et al.", "id": 129, "links": { "canonical_url": "https://arxiv.org/abs/1912.04958", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1912.04958.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Analyzing%20and%20Improving%20StyleGAN%20%28StyleGAN2%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Analyzing%20and%20Improving%20StyleGAN%20%28StyleGAN2%29%20Karras%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Analyzing%20and%20Improving%20StyleGAN%20%28StyleGAN2%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1912.04958.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "StyleGAN improvements", "title": "Analyzing and Improving StyleGAN (StyleGAN2)", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Isola et al.", "id": 130, "links": { "canonical_url": "https://arxiv.org/abs/1611.07004", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1611.07004.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Image-to-Image%20Translation%20with%20Conditional%20GANs%20%28Pix2Pix%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Image-to-Image%20Translation%20with%20Conditional%20GANs%20%28Pix2Pix%29%20Isola%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Image-to-Image%20Translation%20with%20Conditional%20GANs%20%28Pix2Pix%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1611.07004.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "Paired image translation", "title": "Image-to-Image Translation with Conditional GANs (Pix2Pix)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Zhu et al.", "id": 131, "links": { "canonical_url": "https://arxiv.org/abs/1703.10593", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1703.10593.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Unpaired%20Image-to-Image%20Translation%20%28CycleGAN%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Unpaired%20Image-to-Image%20Translation%20%28CycleGAN%29%20Zhu%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Unpaired%20Image-to-Image%20Translation%20%28CycleGAN%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1703.10593.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "Unpaired domain transfer", "title": "Unpaired Image-to-Image Translation (CycleGAN)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Park et al.", "id": 132, "links": { "canonical_url": "https://arxiv.org/abs/1903.07291", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1903.07291.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Semantic%20Image%20Synthesis%20with%20Spatially-Adaptive%20Normalization%20%28SPADE%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Semantic%20Image%20Synthesis%20with%20Spatially-Adaptive%20Normalization%20%28SPADE%29%20Park%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Semantic%20Image%20Synthesis%20with%20Spatially-Adaptive%20Normalization%20%28SPADE%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1903.07291.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "Semantic layout to image", "title": "Semantic Image Synthesis with Spatially-Adaptive Normalization (SPADE)", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "van den Oord, Vinyals, Kavukcuoglu", "id": 133, "links": { "canonical_url": "https://arxiv.org/abs/1711.00937", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1711.00937.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Neural%20Discrete%20Representation%20Learning%20%28VQ-VAE%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Neural%20Discrete%20Representation%20Learning%20%28VQ-VAE%29%20van%20den%20Oord%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Neural%20Discrete%20Representation%20Learning%20%28VQ-VAE%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1711.00937.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "Vector quantized VAE", "title": "Neural Discrete Representation Learning (VQ-VAE)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Razavi, van den Oord, Vinyals", "id": 134, "links": { "canonical_url": "https://arxiv.org/abs/1906.00446", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1906.00446.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Generating%20Diverse%20High-Fidelity%20Images%20with%20VQ-VAE-2&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Generating%20Diverse%20High-Fidelity%20Images%20with%20VQ-VAE-2%20Razavi%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Generating%20Diverse%20High-Fidelity%20Images%20with%20VQ-VAE-2&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1906.00446.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "Hierarchical VQ-VAE", "title": "Generating Diverse High-Fidelity Images with VQ-VAE-2", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Ramesh et al.", "id": 135, "links": { "canonical_url": "https://arxiv.org/abs/2102.12092", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2102.12092.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DALL%C2%B7E%3A%20Zero-Shot%20Text-to-Image%20Generation%20%28dVAE%20component%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DALL%C2%B7E%3A%20Zero-Shot%20Text-to-Image%20Generation%20%28dVAE%20component%29%20Ramesh%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=DALL%C2%B7E%3A%20Zero-Shot%20Text-to-Image%20Generation%20%28dVAE%20component%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2102.12092.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "Text-to-image with discrete VAE", "title": "DALL·E: Zero-Shot Text-to-Image Generation (dVAE component)", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Kingma & Dhariwal", "id": 136, "links": { "canonical_url": "https://arxiv.org/abs/1807.03039", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1807.03039.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Glow%3A%20Generative%20Flow%20with%20Invertible%201x1%20Convolutions&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Glow%3A%20Generative%20Flow%20with%20Invertible%201x1%20Convolutions%20Kingma%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Glow%3A%20Generative%20Flow%20with%20Invertible%201x1%20Convolutions&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1807.03039.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "Normalizing flows", "title": "Glow: Generative Flow with Invertible 1x1 Convolutions", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Dinh, Krueger, Bengio", "id": 137, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=NICE%3A%20Non-linear%20Independent%20Components%20Estimation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=NICE%3A%20Non-linear%20Independent%20Components%20Estimation%20Dinh%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=NICE%3A%20Non-linear%20Independent%20Components%20Estimation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "Coupling layers for flows", "title": "NICE: Non-linear Independent Components Estimation", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Dinh, Sohl-Dickstein, Bengio", "id": 138, "links": { "canonical_url": "https://arxiv.org/abs/1605.08803", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1605.08803.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Density%20Estimation%20Using%20Real-NVP&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Density%20Estimation%20Using%20Real-NVP%20Dinh%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Density%20Estimation%20Using%20Real-NVP&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1605.08803.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "Real-valued Non-Volume Preserving flows", "title": "Density Estimation Using Real-NVP", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "van den Oord et al.", "id": 139, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=PixelCNN&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=PixelCNN%20van%20den%20Oord%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=PixelCNN&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 7, "section_title": "Generative Models", "source_note": "Autoregressive image generation", "title": "PixelCNN", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "various", "id": 140, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Energy-Based%20Models%20for%20Atomic-Scale%20Modeling&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Energy-Based%20Models%20for%20Atomic-Scale%20Modeling%20various%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Energy-Based%20Models%20for%20Atomic-Scale%20Modeling&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 7, "section_title": "Generative Models", "source_note": "Energy-based generative modeling", "title": "Energy-Based Models for Atomic-Scale Modeling", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Vaswani et al.", "id": 141, "links": { "canonical_url": "https://arxiv.org/abs/1706.03762", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1706.03762.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Attention%20Is%20All%20You%20Need&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Attention%20Is%20All%20You%20Need%20Vaswani%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Attention%20Is%20All%20You%20Need&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1706.03762.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "**The Transformer architecture**", "title": "Attention Is All You Need", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Shaw, Uszkoreit, Vaswani", "id": 142, "links": { "canonical_url": "https://arxiv.org/abs/1803.02155", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1803.02155.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Self-Attention%20with%20Relative%20Position%20Representations&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Self-Attention%20with%20Relative%20Position%20Representations%20Shaw%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Self-Attention%20with%20Relative%20Position%20Representations&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1803.02155.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Relative positional encoding", "title": "Self-Attention with Relative Position Representations", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Dai et al.", "id": 143, "links": { "canonical_url": "https://arxiv.org/abs/1901.02860", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1901.02860.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Transformer-XL%3A%20Attentive%20Language%20Models%20Beyond%20a%20Fixed-Length%20Context&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Transformer-XL%3A%20Attentive%20Language%20Models%20Beyond%20a%20Fixed-Length%20Context%20Dai%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Transformer-XL%3A%20Attentive%20Language%20Models%20Beyond%20a%20Fixed-Length%20Context&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1901.02860.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Segment-level recurrence, longer context", "title": "Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Child et al.", "id": 144, "links": { "canonical_url": "https://arxiv.org/abs/1904.10509", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1904.10509.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Generating%20Long%20Sequences%20with%20Sparse%20Transformers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Generating%20Long%20Sequences%20with%20Sparse%20Transformers%20Child%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Generating%20Long%20Sequences%20with%20Sparse%20Transformers&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1904.10509.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Sparse attention patterns", "title": "Generating Long Sequences with Sparse Transformers", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 184 ], "severity": "warning" } ], "authors": "Beltagy, Peters, Cohan", "id": 145, "links": { "canonical_url": "https://arxiv.org/abs/2004.05150", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2004.05150.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Longformer%3A%20The%20Long-Document%20Transformer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Longformer%3A%20The%20Long-Document%20Transformer%20Beltagy%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Longformer%3A%20The%20Long-Document%20Transformer&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2004.05150.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Local + global attention", "title": "Longformer: The Long-Document Transformer", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Zaheer et al.", "id": 146, "links": { "canonical_url": "https://arxiv.org/abs/2007.14062", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2007.14062.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Big%20Bird%3A%20Transformers%20for%20Longer%20Sequences&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Big%20Bird%3A%20Transformers%20for%20Longer%20Sequences%20Zaheer%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Big%20Bird%3A%20Transformers%20for%20Longer%20Sequences&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2007.14062.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Random + window + global attention", "title": "Big Bird: Transformers for Longer Sequences", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Wang et al.", "id": 147, "links": { "canonical_url": "https://arxiv.org/abs/2006.04768", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2006.04768.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Linformer%3A%20Self-Attention%20with%20Linear%20Complexity&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Linformer%3A%20Self-Attention%20with%20Linear%20Complexity%20Wang%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Linformer%3A%20Self-Attention%20with%20Linear%20Complexity&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2006.04768.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Low-rank attention approximation", "title": "Linformer: Self-Attention with Linear Complexity", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Choromanski et al.", "id": 148, "links": { "canonical_url": "https://arxiv.org/abs/2009.14794", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2009.14794.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Performers%3A%20Rethinking%20Attention%20%28FAVOR%2B%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Performers%3A%20Rethinking%20Attention%20%28FAVOR%2B%29%20Choromanski%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Performers%3A%20Rethinking%20Attention%20%28FAVOR%2B%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2009.14794.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Random features for linear attention", "title": "Performers: Rethinking Attention (FAVOR+)", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Dao et al.", "id": 149, "links": { "canonical_url": "https://arxiv.org/abs/2205.14135", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2205.14135.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=FlashAttention%3A%20Fast%20and%20Memory-Efficient%20Exact%20Attention&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=FlashAttention%3A%20Fast%20and%20Memory-Efficient%20Exact%20Attention%20Dao%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=FlashAttention%3A%20Fast%20and%20Memory-Efficient%20Exact%20Attention&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2205.14135.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "IO-aware exact attention", "title": "FlashAttention: Fast and Memory-Efficient Exact Attention", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Dao", "id": 150, "links": { "canonical_url": "https://arxiv.org/abs/2307.08691", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2307.08691.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=FlashAttention-2%3A%20Faster%20Attention%20with%20Better%20Parallelism&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=FlashAttention-2%3A%20Faster%20Attention%20with%20Better%20Parallelism%20Dao%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=FlashAttention-2%3A%20Faster%20Attention%20with%20Better%20Parallelism&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2307.08691.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Improved FlashAttention", "title": "FlashAttention-2: Faster Attention with Better Parallelism", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Shazeer", "id": 151, "links": { "canonical_url": "https://arxiv.org/abs/1911.02150", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1911.02150.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Multi-Query%20Attention&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Multi-Query%20Attention%20Shazeer%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Multi-Query%20Attention&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1911.02150.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Shared KV heads for efficiency", "title": "Multi-Query Attention", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Ainslie et al.", "id": 152, "links": { "canonical_url": "https://arxiv.org/abs/2305.13245", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.13245.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GQA%3A%20Training%20Generalized%20Multi-Query%20Transformer%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GQA%3A%20Training%20Generalized%20Multi-Query%20Transformer%20Models%20Ainslie%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=GQA%3A%20Training%20Generalized%20Multi-Query%20Transformer%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.13245.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Grouped-query attention", "title": "GQA: Training Generalized Multi-Query Transformer Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Su et al.", "id": 153, "links": { "canonical_url": "https://arxiv.org/abs/2104.09864", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2104.09864.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RoFormer%3A%20Enhanced%20Transformer%20with%20Rotary%20Position%20Embedding%20%28RoPE%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RoFormer%3A%20Enhanced%20Transformer%20with%20Rotary%20Position%20Embedding%20%28RoPE%29%20Su%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=RoFormer%3A%20Enhanced%20Transformer%20with%20Rotary%20Position%20Embedding%20%28RoPE%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2104.09864.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Rotary positional embeddings", "title": "RoFormer: Enhanced Transformer with Rotary Position Embedding (RoPE)", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Press et al.", "id": 154, "links": { "canonical_url": "https://arxiv.org/abs/2108.12409", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2108.12409.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ALiBi%3A%20Train%20Short%2C%20Test%20Long%20%28Attention%20with%20Linear%20Biases%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ALiBi%3A%20Train%20Short%2C%20Test%20Long%20%28Attention%20with%20Linear%20Biases%29%20Press%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=ALiBi%3A%20Train%20Short%2C%20Test%20Long%20%28Attention%20with%20Linear%20Biases%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2108.12409.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Position via attention biases", "title": "ALiBi: Train Short, Test Long (Attention with Linear Biases)", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Kitaev, Kaiser, Levskaya", "id": 155, "links": { "canonical_url": "https://arxiv.org/abs/2001.04451", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2001.04451.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Reformer%3A%20The%20Efficient%20Transformer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Reformer%3A%20The%20Efficient%20Transformer%20Kitaev%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Reformer%3A%20The%20Efficient%20Transformer&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2001.04451.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "LSH attention, reversible layers", "title": "Reformer: The Efficient Transformer", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Lee et al.", "id": 156, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Set%20Transformer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Set%20Transformer%20Lee%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Set%20Transformer&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Transformers for set-structured data", "title": "Set Transformer", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Dehghani et al.", "id": 157, "links": { "canonical_url": "https://arxiv.org/abs/1807.03819", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1807.03819.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Universal%20Transformers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Universal%20Transformers%20Dehghani%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Universal%20Transformers&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1807.03819.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Depth-wise recurrent Transformer", "title": "Universal Transformers", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Liu et al.", "id": 158, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scaling%20Transformers%20to%201M%20tokens%20%28Ring%20Attention%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scaling%20Transformers%20to%201M%20tokens%20%28Ring%20Attention%29%20Liu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scaling%20Transformers%20to%201M%20tokens%20%28Ring%20Attention%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Blockwise attention for long context", "title": "Scaling Transformers to 1M tokens (Ring Attention)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Chen et al.", "id": 159, "links": { "canonical_url": "https://arxiv.org/abs/2306.15595", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2306.15595.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Extending%20Context%20Window%20of%20LLMs%20via%20Positional%20Interpolation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Extending%20Context%20Window%20of%20LLMs%20via%20Positional%20Interpolation%20Chen%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Extending%20Context%20Window%20of%20LLMs%20via%20Positional%20Interpolation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2306.15595.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "Context extension via interpolation", "title": "Extending Context Window of LLMs via Positional Interpolation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Peng et al.", "id": 160, "links": { "canonical_url": "https://arxiv.org/abs/2309.00071", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2309.00071.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=YaRN%3A%20Efficient%20Context%20Window%20Extension&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=YaRN%3A%20Efficient%20Context%20Window%20Extension%20Peng%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=YaRN%3A%20Efficient%20Context%20Window%20Extension&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2309.00071.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 8, "section_title": "Attention Mechanisms & Transformers", "source_note": "NTK-aware interpolation for RoPE", "title": "YaRN: Efficient Context Window Extension", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 162 ], "severity": "warning" } ], "authors": "Mikolov et al.", "id": 161, "links": { "canonical_url": "https://arxiv.org/abs/1301.3781", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1301.3781.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Distributed%20Representations%20of%20Words%20%28Word2Vec%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Distributed%20Representations%20of%20Words%20%28Word2Vec%29%20Mikolov%202013", "semantic_scholar": "https://www.semanticscholar.org/search?q=Distributed%20Representations%20of%20Words%20%28Word2Vec%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1301.3781.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Word embeddings", "title": "Distributed Representations of Words (Word2Vec)", "work_type": "Research-paper candidate", "year": 2013, "year_display": "2013" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 161 ], "severity": "warning" } ], "authors": "Mikolov et al.", "id": 162, "links": { "canonical_url": "https://arxiv.org/abs/1301.3781", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1301.3781.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Efficient%20Estimation%20of%20Word%20Representations%20in%20Vector%20Space&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Efficient%20Estimation%20of%20Word%20Representations%20in%20Vector%20Space%20Mikolov%202013", "semantic_scholar": "https://www.semanticscholar.org/search?q=Efficient%20Estimation%20of%20Word%20Representations%20in%20Vector%20Space&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1301.3781.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Skip-gram, CBOW", "title": "Efficient Estimation of Word Representations in Vector Space", "work_type": "Research-paper candidate", "year": 2013, "year_display": "2013" }, { "audit_flags": [], "authors": "Pennington, Socher, Manning", "id": 163, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": "https://nlp.stanford.edu/pubs/glove.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GloVe%3A%20Global%20Vectors%20for%20Word%20Representation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GloVe%3A%20Global%20Vectors%20for%20Word%20Representation%20Pennington%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=GloVe%3A%20Global%20Vectors%20for%20Word%20Representation&sort=relevance" }, "supplied_direct_url": "https://nlp.stanford.edu/pubs/glove.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Global co-occurrence embeddings", "title": "GloVe: Global Vectors for Word Representation", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Bojanowski et al.", "id": 164, "links": { "canonical_url": "https://arxiv.org/abs/1607.04606", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1607.04606.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Enriching%20Word%20Vectors%20with%20Subword%20Information%20%28FastText%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Enriching%20Word%20Vectors%20with%20Subword%20Information%20%28FastText%29%20Bojanowski%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Enriching%20Word%20Vectors%20with%20Subword%20Information%20%28FastText%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1607.04606.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Subword embeddings", "title": "Enriching Word Vectors with Subword Information (FastText)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Peters et al.", "id": 165, "links": { "canonical_url": "https://arxiv.org/abs/1802.05365", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1802.05365.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Deep%20Contextualized%20Word%20Representations%20%28ELMo%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Deep%20Contextualized%20Word%20Representations%20%28ELMo%29%20Peters%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Deep%20Contextualized%20Word%20Representations%20%28ELMo%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1802.05365.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Contextualized embeddings via biLSTM", "title": "Deep Contextualized Word Representations (ELMo)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Dai & Le", "id": 166, "links": { "canonical_url": "https://arxiv.org/abs/1511.01432", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1511.01432.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Semi-supervised%20Sequence%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Semi-supervised%20Sequence%20Learning%20Dai%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Semi-supervised%20Sequence%20Learning&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1511.01432.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "LM pretraining for NLP", "title": "Semi-supervised Sequence Learning", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Howard & Ruder", "id": 167, "links": { "canonical_url": "https://arxiv.org/abs/1801.06146", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1801.06146.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Universal%20Language%20Model%20Fine-tuning%20%28ULMFiT%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Universal%20Language%20Model%20Fine-tuning%20%28ULMFiT%29%20Howard%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Universal%20Language%20Model%20Fine-tuning%20%28ULMFiT%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1801.06146.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Transfer learning for NLP", "title": "Universal Language Model Fine-tuning (ULMFiT)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Devlin et al.", "id": 168, "links": { "canonical_url": "https://arxiv.org/abs/1810.04805", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1810.04805.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BERT%3A%20Pre-training%20of%20Deep%20Bidirectional%20Transformers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BERT%3A%20Pre-training%20of%20Deep%20Bidirectional%20Transformers%20Devlin%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=BERT%3A%20Pre-training%20of%20Deep%20Bidirectional%20Transformers&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1810.04805.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "**Masked LM pretraining**", "title": "BERT: Pre-training of Deep Bidirectional Transformers", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Radford et al.", "id": 169, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": "https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Improving%20Language%20Understanding%20by%20Generative%20Pre-Training%20%28GPT-1%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Improving%20Language%20Understanding%20by%20Generative%20Pre-Training%20%28GPT-1%29%20Radford%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Improving%20Language%20Understanding%20by%20Generative%20Pre-Training%20%28GPT-1%29&sort=relevance" }, "supplied_direct_url": "https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Generative pretraining", "title": "Improving Language Understanding by Generative Pre-Training (GPT-1)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Radford et al.", "id": 170, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": "https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Language%20Models%20are%20Unsupervised%20Multitask%20Learners%20%28GPT-2%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Language%20Models%20are%20Unsupervised%20Multitask%20Learners%20%28GPT-2%29%20Radford%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Language%20Models%20are%20Unsupervised%20Multitask%20Learners%20%28GPT-2%29&sort=relevance" }, "supplied_direct_url": "https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Larger GPT, zero-shot abilities", "title": "Language Models are Unsupervised Multitask Learners (GPT-2)", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Liu et al.", "id": 171, "links": { "canonical_url": "https://arxiv.org/abs/1907.11692", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1907.11692.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RoBERTa%3A%20A%20Robustly%20Optimized%20BERT%20Pretraining%20Approach&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RoBERTa%3A%20A%20Robustly%20Optimized%20BERT%20Pretraining%20Approach%20Liu%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=RoBERTa%3A%20A%20Robustly%20Optimized%20BERT%20Pretraining%20Approach&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1907.11692.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Better BERT training recipe", "title": "RoBERTa: A Robustly Optimized BERT Pretraining Approach", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Lan et al.", "id": 172, "links": { "canonical_url": "https://arxiv.org/abs/1909.11942", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1909.11942.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ALBERT%3A%20A%20Lite%20BERT&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ALBERT%3A%20A%20Lite%20BERT%20Lan%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=ALBERT%3A%20A%20Lite%20BERT&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1909.11942.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Parameter-efficient BERT", "title": "ALBERT: A Lite BERT", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Sanh et al.", "id": 173, "links": { "canonical_url": "https://arxiv.org/abs/1910.01108", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1910.01108.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DistilBERT&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DistilBERT%20Sanh%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=DistilBERT&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1910.01108.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Distilled BERT — smaller, faster", "title": "DistilBERT", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Yang et al.", "id": 174, "links": { "canonical_url": "https://arxiv.org/abs/1906.08237", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1906.08237.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=XLNet%3A%20Generalized%20Autoregressive%20Pretraining&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=XLNet%3A%20Generalized%20Autoregressive%20Pretraining%20Yang%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=XLNet%3A%20Generalized%20Autoregressive%20Pretraining&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1906.08237.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Permutation language modeling", "title": "XLNet: Generalized Autoregressive Pretraining", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Clark et al.", "id": 175, "links": { "canonical_url": "https://arxiv.org/abs/2003.10555", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2003.10555.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ELECTRA%3A%20Pre-training%20Text%20Encoders%20as%20Discriminators&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ELECTRA%3A%20Pre-training%20Text%20Encoders%20as%20Discriminators%20Clark%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=ELECTRA%3A%20Pre-training%20Text%20Encoders%20as%20Discriminators&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2003.10555.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Replaced token detection", "title": "ELECTRA: Pre-training Text Encoders as Discriminators", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "He et al.", "id": 176, "links": { "canonical_url": "https://arxiv.org/abs/2006.03654", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2006.03654.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeBERTa%3A%20Decoding-enhanced%20BERT%20with%20Disentangled%20Attention&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeBERTa%3A%20Decoding-enhanced%20BERT%20with%20Disentangled%20Attention%20He%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeBERTa%3A%20Decoding-enhanced%20BERT%20with%20Disentangled%20Attention&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2006.03654.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Disentangled attention mechanism", "title": "DeBERTa: Decoding-enhanced BERT with Disentangled Attention", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Raffel et al.", "id": 177, "links": { "canonical_url": "https://arxiv.org/abs/1910.10683", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1910.10683.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Exploring%20the%20Limits%20of%20Transfer%20Learning%20with%20a%20Unified%20T5&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Exploring%20the%20Limits%20of%20Transfer%20Learning%20with%20a%20Unified%20T5%20Raffel%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Exploring%20the%20Limits%20of%20Transfer%20Learning%20with%20a%20Unified%20T5&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1910.10683.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Text-to-text framework", "title": "Exploring the Limits of Transfer Learning with a Unified T5", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Lewis et al.", "id": 178, "links": { "canonical_url": "https://arxiv.org/abs/1910.13461", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1910.13461.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BART%3A%20Denoising%20Sequence-to-Sequence%20Pre-training&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BART%3A%20Denoising%20Sequence-to-Sequence%20Pre-training%20Lewis%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=BART%3A%20Denoising%20Sequence-to-Sequence%20Pre-training&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1910.13461.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Denoising autoencoder pretraining", "title": "BART: Denoising Sequence-to-Sequence Pre-training", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Conneau & Lample", "id": 179, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=mBERT%20/%20XLM%3A%20Cross-lingual%20Language%20Model%20Pretraining&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=mBERT%20/%20XLM%3A%20Cross-lingual%20Language%20Model%20Pretraining%20Conneau%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=mBERT%20/%20XLM%3A%20Cross-lingual%20Language%20Model%20Pretraining&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Multilingual pretraining", "title": "mBERT / XLM: Cross-lingual Language Model Pretraining", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Conneau et al.", "id": 180, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=XLM-RoBERTa&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=XLM-RoBERTa%20Conneau%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=XLM-RoBERTa&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Cross-lingual at scale", "title": "XLM-RoBERTa", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Reimers & Gurevych", "id": 181, "links": { "canonical_url": "https://arxiv.org/abs/1908.10084", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1908.10084.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Sentence-BERT%3A%20Sentence%20Embeddings%20using%20Siamese%20BERT&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Sentence-BERT%3A%20Sentence%20Embeddings%20using%20Siamese%20BERT%20Reimers%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Sentence-BERT%3A%20Sentence%20Embeddings%20using%20Siamese%20BERT&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1908.10084.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Sentence embeddings", "title": "Sentence-BERT: Sentence Embeddings using Siamese BERT", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 182, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ERNIE%3A%20Enhanced%20Language%20RepresentatioN%20with%20Informative%20Entities&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ERNIE%3A%20Enhanced%20Language%20RepresentatioN%20with%20Informative%20Entities%20Zhang%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=ERNIE%3A%20Enhanced%20Language%20RepresentatioN%20with%20Informative%20Entities&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Knowledge-enhanced pretraining", "title": "ERNIE: Enhanced Language RepresentatioN with Informative Entities", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Joshi et al.", "id": 183, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SpanBERT%3A%20Improving%20Pre-training%20by%20Representing%20and%20Predicting%20Spans&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SpanBERT%3A%20Improving%20Pre-training%20by%20Representing%20and%20Predicting%20Spans%20Joshi%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=SpanBERT%3A%20Improving%20Pre-training%20by%20Representing%20and%20Predicting%20Spans&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Span-level pretraining", "title": "SpanBERT: Improving Pre-training by Representing and Predicting Spans", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 145 ], "severity": "warning" } ], "authors": "Beltagy et al.", "id": 184, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Longformer%20for%20Long%20Document%20Understanding&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Longformer%20for%20Long%20Document%20Understanding%20Beltagy%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Longformer%20for%20Long%20Document%20Understanding&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Efficient attention for long docs", "title": "Longformer for Long Document Understanding", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Guo et al.", "id": 185, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Unified%20Pre-training%20for%20Program%20Understanding%20and%20Generation%20%28UniXcoder%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Unified%20Pre-training%20for%20Program%20Understanding%20and%20Generation%20%28UniXcoder%29%20Guo%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Unified%20Pre-training%20for%20Program%20Understanding%20and%20Generation%20%28UniXcoder%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 9, "section_title": "Pre-trained Language Models", "source_note": "Pretraining for code", "title": "Unified Pre-training for Program Understanding and Generation (UniXcoder)", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Brown et al.", "id": 186, "links": { "canonical_url": "https://arxiv.org/abs/2005.14165", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2005.14165.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Language%20Models%20are%20Few-Shot%20Learners%20%28GPT-3%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Language%20Models%20are%20Few-Shot%20Learners%20%28GPT-3%29%20Brown%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Language%20Models%20are%20Few-Shot%20Learners%20%28GPT-3%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2005.14165.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "**175B params, in-context learning**", "title": "Language Models are Few-Shot Learners (GPT-3)", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as technical or industry report, not as a research paper.", "severity": "warning" } ], "authors": "OpenAI", "id": 187, "links": { "canonical_url": "https://arxiv.org/abs/2303.08774", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2303.08774.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GPT-4%20Technical%20Report&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GPT-4%20Technical%20Report%20OpenAI%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=GPT-4%20Technical%20Report&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2303.08774.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "**Multimodal LLM, SOTA benchmarks**", "title": "GPT-4 Technical Report", "work_type": "Technical or industry report", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Chowdhery et al.", "id": 188, "links": { "canonical_url": "https://arxiv.org/abs/2204.02311", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2204.02311.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=PaLM%3A%20Scaling%20Language%20Modeling%20with%20Pathways&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=PaLM%3A%20Scaling%20Language%20Modeling%20with%20Pathways%20Chowdhery%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=PaLM%3A%20Scaling%20Language%20Modeling%20with%20Pathways&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2204.02311.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "540B model, Pathways architecture", "title": "PaLM: Scaling Language Modeling with Pathways", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as technical or industry report, not as a research paper.", "severity": "warning" } ], "authors": "Google", "id": 189, "links": { "canonical_url": "https://arxiv.org/abs/2305.10403", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.10403.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=PaLM%202%20Technical%20Report&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=PaLM%202%20Technical%20Report%20Google%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=PaLM%202%20Technical%20Report&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.10403.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Improved multilingual, reasoning", "title": "PaLM 2 Technical Report", "work_type": "Technical or industry report", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Google DeepMind", "id": 190, "links": { "canonical_url": "https://arxiv.org/abs/2312.11805", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2312.11805.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Gemini%3A%20A%20Family%20of%20Highly%20Capable%20Multimodal%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Gemini%3A%20A%20Family%20of%20Highly%20Capable%20Multimodal%20Models%20Google%20DeepMind%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Gemini%3A%20A%20Family%20of%20Highly%20Capable%20Multimodal%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2312.11805.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Natively multimodal LLM", "title": "Gemini: A Family of Highly Capable Multimodal Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Touvron et al.", "id": 191, "links": { "canonical_url": "https://arxiv.org/abs/2302.13971", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2302.13971.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLaMA%3A%20Open%20and%20Efficient%20Foundation%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLaMA%3A%20Open%20and%20Efficient%20Foundation%20Language%20Models%20Touvron%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLaMA%3A%20Open%20and%20Efficient%20Foundation%20Language%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2302.13971.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Open-weight efficient LLMs", "title": "LLaMA: Open and Efficient Foundation Language Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Touvron et al.", "id": 192, "links": { "canonical_url": "https://arxiv.org/abs/2307.09288", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2307.09288.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Llama%202%3A%20Open%20Foundation%20and%20Fine-Tuned%20Chat%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Llama%202%3A%20Open%20Foundation%20and%20Fine-Tuned%20Chat%20Models%20Touvron%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Llama%202%3A%20Open%20Foundation%20and%20Fine-Tuned%20Chat%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2307.09288.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Open chat models with RLHF", "title": "Llama 2: Open Foundation and Fine-Tuned Chat Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Meta", "id": 193, "links": { "canonical_url": "https://arxiv.org/abs/2407.21783", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2407.21783.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Llama%203&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Llama%203%20Meta%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Llama%203&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2407.21783.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Llama 3 family, 8B–405B", "title": "Llama 3", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as product documentation or standard, not as a research paper.", "severity": "warning" } ], "authors": "Anthropic", "id": 194, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Claude%20Model%20Card%20and%20Evaluations&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Claude%20Model%20Card%20and%20Evaluations%20Anthropic%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Claude%20Model%20Card%20and%20Evaluations&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Claude model documentation", "title": "The Claude Model Card and Evaluations", "work_type": "Product documentation or standard", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Jiang et al.", "id": 195, "links": { "canonical_url": "https://arxiv.org/abs/2310.06825", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2310.06825.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mistral%207B&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mistral%207B%20Jiang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mistral%207B&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2310.06825.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Efficient 7B model, sliding window", "title": "Mistral 7B", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 556 ], "severity": "warning" } ], "authors": "Jiang et al.", "id": 196, "links": { "canonical_url": "https://arxiv.org/abs/2401.04088", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2401.04088.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mixtral%20of%20Experts&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mixtral%20of%20Experts%20Jiang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mixtral%20of%20Experts&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2401.04088.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "MoE with Mistral", "title": "Mixtral of Experts", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 731, 782 ], "severity": "warning" } ], "authors": "Gunasekar et al.", "id": 197, "links": { "canonical_url": "https://arxiv.org/abs/2306.11644", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2306.11644.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Phi-1%3A%20Textbooks%20Are%20All%20You%20Need&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Phi-1%3A%20Textbooks%20Are%20All%20You%20Need%20Gunasekar%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Phi-1%3A%20Textbooks%20Are%20All%20You%20Need&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2306.11644.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Small model, high-quality data", "title": "Phi-1: Textbooks Are All You Need", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Microsoft", "id": 198, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Phi-2&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Phi-2%20Microsoft%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Phi-2&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Scaling small models with data quality", "title": "Phi-2", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as technical or industry report, not as a research paper.", "severity": "warning" } ], "authors": "Abdin et al.", "id": 199, "links": { "canonical_url": "https://arxiv.org/abs/2404.14219", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2404.14219.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Phi-3%20Technical%20Report&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Phi-3%20Technical%20Report%20Abdin%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Phi-3%20Technical%20Report&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2404.14219.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Small powerful models", "title": "Phi-3 Technical Report", "work_type": "Technical or industry report", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 722 ], "severity": "warning" } ], "authors": "Hoffmann et al.", "id": 200, "links": { "canonical_url": "https://arxiv.org/abs/2203.15556", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2203.15556.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Chinchilla%3A%20Training%20Compute-Optimal%20Large%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Chinchilla%3A%20Training%20Compute-Optimal%20Large%20Language%20Models%20Hoffmann%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Chinchilla%3A%20Training%20Compute-Optimal%20Large%20Language%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2203.15556.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Optimal data/parameter ratio", "title": "Chinchilla: Training Compute-Optimal Large Language Models", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Rae et al.", "id": 201, "links": { "canonical_url": "https://arxiv.org/abs/2112.11446", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2112.11446.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Gopher&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Gopher%20Rae%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Gopher&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2112.11446.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "280B model, analysis of scaling", "title": "Gopher", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 202, "links": { "canonical_url": "https://arxiv.org/abs/2205.01068", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2205.01068.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=OPT%3A%20Open%20Pre-trained%20Transformer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=OPT%3A%20Open%20Pre-trained%20Transformer%20Zhang%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=OPT%3A%20Open%20Pre-trained%20Transformer&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2205.01068.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Open 175B model from Meta", "title": "OPT: Open Pre-trained Transformer", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "BigScience", "id": 203, "links": { "canonical_url": "https://arxiv.org/abs/2211.05100", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2211.05100.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BLOOM%3A%20A%20176B-Parameter%20Open-Access%20Multilingual%20LM&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BLOOM%3A%20A%20176B-Parameter%20Open-Access%20Multilingual%20LM%20BigScience%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=BLOOM%3A%20A%20176B-Parameter%20Open-Access%20Multilingual%20LM&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2211.05100.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Open multilingual LLM", "title": "BLOOM: A 176B-Parameter Open-Access Multilingual LM", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zeng et al.", "id": 204, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GLM-130B%3A%20An%20Open%20Bilingual%20Pre-Trained%20Model&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GLM-130B%3A%20An%20Open%20Bilingual%20Pre-Trained%20Model%20Zeng%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=GLM-130B%3A%20An%20Open%20Bilingual%20Pre-Trained%20Model&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Bilingual large model", "title": "GLM-130B: An Open Bilingual Pre-Trained Model", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "TII", "id": 205, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Falcon%20LLM&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Falcon%20LLM%20TII%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Falcon%20LLM&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "High-quality open LLM", "title": "Falcon LLM", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "01.AI", "id": 206, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Yi%3A%20Open%20Foundation%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Yi%3A%20Open%20Foundation%20Models%2001.AI%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Yi%3A%20Open%20Foundation%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Yi model family", "title": "Yi: Open Foundation Models", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as technical or industry report, not as a research paper.", "severity": "warning" } ], "authors": "Alibaba", "id": 207, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Qwen%20Technical%20Report&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Qwen%20Technical%20Report%20Alibaba%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Qwen%20Technical%20Report&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Qwen model family", "title": "Qwen Technical Report", "work_type": "Technical or industry report", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as technical or industry report, not as a research paper.", "severity": "warning" } ], "authors": "Alibaba", "id": 208, "links": { "canonical_url": "https://arxiv.org/abs/2407.10671", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2407.10671.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Qwen2%20Technical%20Report&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Qwen2%20Technical%20Report%20Alibaba%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Qwen2%20Technical%20Report&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2407.10671.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Improved Qwen family", "title": "Qwen2 Technical Report", "work_type": "Technical or industry report", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "DeepSeek", "id": 209, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeepSeek%20LLM&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeepSeek%20LLM%20DeepSeek%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeepSeek%20LLM&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Efficient large model training", "title": "DeepSeek LLM", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "DeepSeek", "id": 210, "links": { "canonical_url": "https://arxiv.org/abs/2405.04434", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2405.04434.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeepSeek-V2%3A%20A%20Strong%2C%20Economical%2C%20and%20Efficient%20MoE%20LLM&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeepSeek-V2%3A%20A%20Strong%2C%20Economical%2C%20and%20Efficient%20MoE%20LLM%20DeepSeek%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeepSeek-V2%3A%20A%20Strong%2C%20Economical%2C%20and%20Efficient%20MoE%20LLM&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2405.04434.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Multi-head latent attention + MoE", "title": "DeepSeek-V2: A Strong, Economical, and Efficient MoE LLM", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as technical or industry report, not as a research paper.", "severity": "warning" } ], "authors": "DeepSeek", "id": 211, "links": { "canonical_url": "https://arxiv.org/abs/2412.19437", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2412.19437.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeepSeek-V3%20Technical%20Report&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeepSeek-V3%20Technical%20Report%20DeepSeek%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeepSeek-V3%20Technical%20Report&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2412.19437.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "MoE at frontier performance", "title": "DeepSeek-V3 Technical Report", "work_type": "Technical or industry report", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Google DeepMind", "id": 212, "links": { "canonical_url": "https://arxiv.org/abs/2403.08295", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2403.08295.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Gemma%3A%20Open%20Models%20Based%20on%20Gemini&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Gemma%3A%20Open%20Models%20Based%20on%20Gemini%20Google%20DeepMind%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Gemma%3A%20Open%20Models%20Based%20on%20Gemini&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2403.08295.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Open Gemini-derived models", "title": "Gemma: Open Models Based on Gemini", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Cohere", "id": 213, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Command%20R%2B&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Command%20R%2B%20Cohere%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Command%20R%2B&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "RAG-optimized LLM", "title": "Command R+", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 744 ], "severity": "warning" } ], "authors": "AI21 Labs", "id": 214, "links": { "canonical_url": "https://arxiv.org/abs/2403.19887", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2403.19887.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Jamba%3A%20A%20Hybrid%20Transformer-Mamba%20Model&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Jamba%3A%20A%20Hybrid%20Transformer-Mamba%20Model%20AI21%20Labs%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Jamba%3A%20A%20Hybrid%20Transformer-Mamba%20Model&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2403.19887.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "SSM + Transformer hybrid", "title": "Jamba: A Hybrid Transformer-Mamba Model", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Groeneveld et al.", "id": 215, "links": { "canonical_url": "https://arxiv.org/abs/2402.00838", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2402.00838.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=OLMo%3A%20Accelerating%20the%20Science%20of%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=OLMo%3A%20Accelerating%20the%20Science%20of%20Language%20Models%20Groeneveld%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=OLMo%3A%20Accelerating%20the%20Science%20of%20Language%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2402.00838.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 10, "section_title": "Large Language Models (LLMs)", "source_note": "Fully open LLM pipeline", "title": "OLMo: Accelerating the Science of Language Models", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Ouyang et al.", "id": 216, "links": { "canonical_url": "https://arxiv.org/abs/2203.02155", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2203.02155.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Training%20Language%20Models%20to%20Follow%20Instructions%20%28InstructGPT%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Training%20Language%20Models%20to%20Follow%20Instructions%20%28InstructGPT%29%20Ouyang%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Training%20Language%20Models%20to%20Follow%20Instructions%20%28InstructGPT%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2203.02155.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "**RLHF for instruction following**", "title": "Training Language Models to Follow Instructions (InstructGPT)", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Stiennon et al.", "id": 217, "links": { "canonical_url": "https://arxiv.org/abs/2009.01325", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2009.01325.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Learning%20to%20Summarize%20from%20Human%20Feedback&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Learning%20to%20Summarize%20from%20Human%20Feedback%20Stiennon%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Learning%20to%20Summarize%20from%20Human%20Feedback&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2009.01325.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "RLHF applied to summarization", "title": "Learning to Summarize from Human Feedback", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Bai et al.", "id": 218, "links": { "canonical_url": "https://arxiv.org/abs/2212.08073", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2212.08073.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Constitutional%20AI%3A%20Harmlessness%20from%20AI%20Feedback%20%28CAI%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Constitutional%20AI%3A%20Harmlessness%20from%20AI%20Feedback%20%28CAI%29%20Bai%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Constitutional%20AI%3A%20Harmlessness%20from%20AI%20Feedback%20%28CAI%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2212.08073.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "**RLAIF — AI self-improvement**", "title": "Constitutional AI: Harmlessness from AI Feedback (CAI)", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Rafailov et al.", "id": 219, "links": { "canonical_url": "https://arxiv.org/abs/2305.18290", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.18290.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Direct%20Preference%20Optimization%20%28DPO%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Direct%20Preference%20Optimization%20%28DPO%29%20Rafailov%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Direct%20Preference%20Optimization%20%28DPO%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.18290.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "RLHF without RL", "title": "Direct Preference Optimization (DPO)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Casper et al.", "id": 220, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RLHF%3A%20A%20Survey&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RLHF%3A%20A%20Survey%20Casper%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=RLHF%3A%20A%20Survey&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Comprehensive RLHF survey", "title": "RLHF: A Survey", "work_type": "Survey or review", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Schulman et al.", "id": 221, "links": { "canonical_url": "https://arxiv.org/abs/1707.06347", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1707.06347.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=PPO%3A%20Proximal%20Policy%20Optimization%20Algorithms&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=PPO%3A%20Proximal%20Policy%20Optimization%20Algorithms%20Schulman%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=PPO%3A%20Proximal%20Policy%20Optimization%20Algorithms&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1707.06347.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "PPO — backbone of RLHF", "title": "PPO: Proximal Policy Optimization Algorithms", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 781 ], "severity": "warning" } ], "authors": "Wang et al.", "id": 222, "links": { "canonical_url": "https://arxiv.org/abs/2212.10560", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2212.10560.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Self-Instruct%3A%20Aligning%20LMs%20with%20Self-Generated%20Instructions&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Self-Instruct%3A%20Aligning%20LMs%20with%20Self-Generated%20Instructions%20Wang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Self-Instruct%3A%20Aligning%20LMs%20with%20Self-Generated%20Instructions&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2212.10560.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Synthetic instruction generation", "title": "Self-Instruct: Aligning LMs with Self-Generated Instructions", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zhou et al.", "id": 223, "links": { "canonical_url": "https://arxiv.org/abs/2305.11206", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.11206.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LIMA%3A%20Less%20Is%20More%20for%20Alignment&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LIMA%3A%20Less%20Is%20More%20for%20Alignment%20Zhou%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=LIMA%3A%20Less%20Is%20More%20for%20Alignment&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.11206.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "1000 examples for alignment", "title": "LIMA: Less Is More for Alignment", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Chung et al.", "id": 224, "links": { "canonical_url": "https://arxiv.org/abs/2210.11416", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2210.11416.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scaling%20Instruction-Finetuned%20Language%20Models%20%28Flan-T5/PaLM%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scaling%20Instruction-Finetuned%20Language%20Models%20%28Flan-T5/PaLM%29%20Chung%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scaling%20Instruction-Finetuned%20Language%20Models%20%28Flan-T5/PaLM%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2210.11416.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Instruction tuning at scale", "title": "Scaling Instruction-Finetuned Language Models (Flan-T5/PaLM)", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Wei et al.", "id": 225, "links": { "canonical_url": "https://arxiv.org/abs/2109.01652", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2109.01652.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=FLAN%3A%20Finetuned%20Language%20Net&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=FLAN%3A%20Finetuned%20Language%20Net%20Wei%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=FLAN%3A%20Finetuned%20Language%20Net&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2109.01652.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Task-diverse instruction tuning", "title": "FLAN: Finetuned Language Net", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Longpre et al.", "id": 226, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Flan%20Collection&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Flan%20Collection%20Longpre%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Flan%20Collection&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Design decisions for instruction tuning", "title": "The Flan Collection", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Taori et al.", "id": 227, "links": { "canonical_url": "https://crfm.stanford.edu/2023/03/13/alpaca.html", "corrected_by_audit": false, "direct_url": "https://crfm.stanford.edu/2023/03/13/alpaca.html", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Alpaca%3A%20A%20Strong%2C%20Replicable%20Instruction-Following%20Model&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Alpaca%3A%20A%20Strong%2C%20Replicable%20Instruction-Following%20Model%20Taori%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Alpaca%3A%20A%20Strong%2C%20Replicable%20Instruction-Following%20Model&sort=relevance" }, "supplied_direct_url": "https://crfm.stanford.edu/2023/03/13/alpaca.html" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Fine-tuning with GPT-generated data", "title": "Alpaca: A Strong, Replicable Instruction-Following Model", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Chiang et al.", "id": 228, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Vicuna%3A%20An%20Open-Source%20Chatbot&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Vicuna%3A%20An%20Open-Source%20Chatbot%20Chiang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Vicuna%3A%20An%20Open-Source%20Chatbot&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "ShareGPT-trained chat model", "title": "Vicuna: An Open-Source Chatbot", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 786 ], "severity": "warning" } ], "authors": "Xu et al.", "id": 229, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=WizardLM%3A%20Empowering%20Large%20Language%20Models%20to%20Follow%20Complex%20Instructions&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=WizardLM%3A%20Empowering%20Large%20Language%20Models%20to%20Follow%20Complex%20Instructions%20Xu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=WizardLM%3A%20Empowering%20Large%20Language%20Models%20to%20Follow%20Complex%20Instructions&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Evol-Instruct complexity scaling", "title": "WizardLM: Empowering Large Language Models to Follow Complex Instructions", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Mukherjee et al.", "id": 230, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Orca%3A%20Progressive%20Learning%20from%20Complex%20Explanation%20Traces&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Orca%3A%20Progressive%20Learning%20from%20Complex%20Explanation%20Traces%20Mukherjee%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Orca%3A%20Progressive%20Learning%20from%20Complex%20Explanation%20Traces&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Learning from GPT-4 explanations", "title": "Orca: Progressive Learning from Complex Explanation Traces", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Tunstall et al.", "id": 231, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Zephyr%3A%20Direct%20Distillation%20of%20LM%20Alignment&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Zephyr%3A%20Direct%20Distillation%20of%20LM%20Alignment%20Tunstall%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Zephyr%3A%20Direct%20Distillation%20of%20LM%20Alignment&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "DPO for open models", "title": "Zephyr: Direct Distillation of LM Alignment", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Cui et al.", "id": 232, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=UltraFeedback&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=UltraFeedback%20Cui%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=UltraFeedback&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Large-scale preference dataset", "title": "UltraFeedback", "work_type": "Benchmark or dataset paper", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Lee et al.", "id": 233, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Reinforcement%20Learning%20from%20AI%20Feedback%20%28RLAIF%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Reinforcement%20Learning%20from%20AI%20Feedback%20%28RLAIF%29%20Lee%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Reinforcement%20Learning%20from%20AI%20Feedback%20%28RLAIF%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "AI-generated preferences", "title": "Reinforcement Learning from AI Feedback (RLAIF)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Ethayarajh et al.", "id": 234, "links": { "canonical_url": "https://arxiv.org/abs/2402.01306", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2402.01306.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=KTO%3A%20Model%20Alignment%20as%20Prospect%20Theoretic%20Optimization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=KTO%3A%20Model%20Alignment%20as%20Prospect%20Theoretic%20Optimization%20Ethayarajh%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=KTO%3A%20Model%20Alignment%20as%20Prospect%20Theoretic%20Optimization&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2402.01306.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Kahneman-Tversky optimization", "title": "KTO: Model Alignment as Prospect Theoretic Optimization", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Hong et al.", "id": 235, "links": { "canonical_url": "https://arxiv.org/abs/2403.07691", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2403.07691.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ORPO%3A%20Monolithic%20Preference%20Optimization%20without%20Reference%20Model&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ORPO%3A%20Monolithic%20Preference%20Optimization%20without%20Reference%20Model%20Hong%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=ORPO%3A%20Monolithic%20Preference%20Optimization%20without%20Reference%20Model&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2403.07691.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Odds ratio preference optimization", "title": "ORPO: Monolithic Preference Optimization without Reference Model", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Meng et al.", "id": 236, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SimPO%3A%20Simple%20Preference%20Optimization%20with%20a%20Reference-Free%20Reward&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SimPO%3A%20Simple%20Preference%20Optimization%20with%20a%20Reference-Free%20Reward%20Meng%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=SimPO%3A%20Simple%20Preference%20Optimization%20with%20a%20Reference-Free%20Reward&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Simplified DPO variant", "title": "SimPO: Simple Preference Optimization with a Reference-Free Reward", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Hu et al.", "id": 237, "links": { "canonical_url": "https://arxiv.org/abs/2106.09685", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2106.09685.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LoRA%3A%20Low-Rank%20Adaptation%20of%20Large%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LoRA%3A%20Low-Rank%20Adaptation%20of%20Large%20Language%20Models%20Hu%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=LoRA%3A%20Low-Rank%20Adaptation%20of%20Large%20Language%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2106.09685.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Parameter-efficient fine-tuning", "title": "LoRA: Low-Rank Adaptation of Large Language Models", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Dettmers et al.", "id": 238, "links": { "canonical_url": "https://arxiv.org/abs/2305.14314", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.14314.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=QLoRA%3A%20Efficient%20Finetuning%20of%20Quantized%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=QLoRA%3A%20Efficient%20Finetuning%20of%20Quantized%20LLMs%20Dettmers%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=QLoRA%3A%20Efficient%20Finetuning%20of%20Quantized%20LLMs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.14314.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "4-bit quantized LoRA", "title": "QLoRA: Efficient Finetuning of Quantized LLMs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Li & Liang", "id": 239, "links": { "canonical_url": "https://arxiv.org/abs/2101.00190", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2101.00190.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Prefix-Tuning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Prefix-Tuning%20Li%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Prefix-Tuning&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2101.00190.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Learnable prefixes for generation", "title": "Prefix-Tuning", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Liu et al.", "id": 240, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=P-Tuning%20v2&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=P-Tuning%20v2%20Liu%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=P-Tuning%20v2&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Deep prompt tuning", "title": "P-Tuning v2", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Lester, Al-Rfou, Constant", "id": 241, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Power%20of%20Scale%20for%20Parameter-Efficient%20Prompt%20Tuning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Power%20of%20Scale%20for%20Parameter-Efficient%20Prompt%20Tuning%20Lester%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Power%20of%20Scale%20for%20Parameter-Efficient%20Prompt%20Tuning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Soft prompt tuning", "title": "The Power of Scale for Parameter-Efficient Prompt Tuning", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Liu et al.", "id": 242, "links": { "canonical_url": "https://arxiv.org/abs/2402.09353", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2402.09353.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DoRA%3A%20Weight-Decomposed%20Low-Rank%20Adaptation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DoRA%3A%20Weight-Decomposed%20Low-Rank%20Adaptation%20Liu%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=DoRA%3A%20Weight-Decomposed%20Low-Rank%20Adaptation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2402.09353.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Improved LoRA via magnitude/direction", "title": "DoRA: Weight-Decomposed Low-Rank Adaptation", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Houlsby et al.", "id": 243, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Adapters%3A%20Parameter-Efficient%20Transfer%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Adapters%3A%20Parameter-Efficient%20Transfer%20Learning%20Houlsby%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Adapters%3A%20Parameter-Efficient%20Transfer%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Adapter modules", "title": "Adapters: Parameter-Efficient Transfer Learning", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Jain et al.", "id": 244, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=NEFTune%3A%20Noisy%20Embeddings%20Improve%20Instruction%20Finetuning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=NEFTune%3A%20Noisy%20Embeddings%20Improve%20Instruction%20Finetuning%20Jain%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=NEFTune%3A%20Noisy%20Embeddings%20Improve%20Instruction%20Finetuning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Noise in embeddings during finetuning", "title": "NEFTune: Noisy Embeddings Improve Instruction Finetuning", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 788 ], "severity": "warning" } ], "authors": "Chen et al.", "id": 245, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Self-Play%20Fine-Tuning%20%28SPIN%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Self-Play%20Fine-Tuning%20%28SPIN%29%20Chen%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Self-Play%20Fine-Tuning%20%28SPIN%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 11, "section_title": "LLM Training & Alignment", "source_note": "Self-play for alignment", "title": "Self-Play Fine-Tuning (SPIN)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Dong et al.", "id": 246, "links": { "canonical_url": "https://arxiv.org/abs/2301.00234", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2301.00234.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Survey%20on%20In-Context%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Survey%20on%20In-Context%20Learning%20Dong%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Survey%20on%20In-Context%20Learning&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2301.00234.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "Comprehensive ICL survey", "title": "A Survey on In-Context Learning", "work_type": "Survey or review", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Min et al.", "id": 247, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=What%20Makes%20In-Context%20Learning%20Work%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=What%20Makes%20In-Context%20Learning%20Work%3F%20Min%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=What%20Makes%20In-Context%20Learning%20Work%3F&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "Analyzing ICL mechanisms", "title": "What Makes In-Context Learning Work?", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Min et al.", "id": 248, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Rethinking%20the%20Role%20of%20Demonstrations&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Rethinking%20the%20Role%20of%20Demonstrations%20Min%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Rethinking%20the%20Role%20of%20Demonstrations&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "Ground truth labels not always needed", "title": "Rethinking the Role of Demonstrations", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Lu et al.", "id": 249, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Fantastically%20Ordered%20Prompts%20and%20Where%20to%20Find%20Them&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Fantastically%20Ordered%20Prompts%20and%20Where%20to%20Find%20Them%20Lu%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Fantastically%20Ordered%20Prompts%20and%20Where%20to%20Find%20Them&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "Example ordering matters", "title": "Fantastically Ordered Prompts and Where to Find Them", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Zhao et al.", "id": 250, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Calibrate%20Before%20Use%3A%20Improving%20Few-Shot%20Performance%20of%20LMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Calibrate%20Before%20Use%3A%20Improving%20Few-Shot%20Performance%20of%20LMs%20Zhao%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Calibrate%20Before%20Use%3A%20Improving%20Few-Shot%20Performance%20of%20LMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "Bias calibration in prompting", "title": "Calibrate Before Use: Improving Few-Shot Performance of LMs", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Kojima et al.", "id": 251, "links": { "canonical_url": "https://arxiv.org/abs/2205.11916", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2205.11916.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Large%20Language%20Models%20are%20Zero-Shot%20Reasoners&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Large%20Language%20Models%20are%20Zero-Shot%20Reasoners%20Kojima%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Large%20Language%20Models%20are%20Zero-Shot%20Reasoners&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2205.11916.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "\"Let's think step by step\"", "title": "Large Language Models are Zero-Shot Reasoners", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Reynolds & McDonough", "id": 252, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Prompt%20Programming%20for%20Large%20Language%20Models%3A%20Beyond%20the%20Few-Shot%20Paradigm&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Prompt%20Programming%20for%20Large%20Language%20Models%3A%20Beyond%20the%20Few-Shot%20Paradigm%20Reynolds%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Prompt%20Programming%20for%20Large%20Language%20Models%3A%20Beyond%20the%20Few-Shot%20Paradigm&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "Prompt design strategies", "title": "Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Hao et al.", "id": 253, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Structured%20Prompting%3A%20Scaling%20In-Context%20Learning%20to%201000%20Examples&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Structured%20Prompting%3A%20Scaling%20In-Context%20Learning%20to%201000%20Examples%20Hao%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Structured%20Prompting%3A%20Scaling%20In-Context%20Learning%20to%201000%20Examples&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "Many-shot ICL", "title": "Structured Prompting: Scaling In-Context Learning to 1000 Examples", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Agarwal et al.", "id": 254, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Many-Shot%20In-Context%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Many-Shot%20In-Context%20Learning%20Agarwal%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Many-Shot%20In-Context%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "Scaling ICL with long context", "title": "Many-Shot In-Context Learning", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Liu et al.", "id": 255, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Pre-train%2C%20Prompt%2C%20and%20Predict%3A%20A%20Systematic%20Survey&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Pre-train%2C%20Prompt%2C%20and%20Predict%3A%20A%20Systematic%20Survey%20Liu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Pre-train%2C%20Prompt%2C%20and%20Predict%3A%20A%20Systematic%20Survey&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "Prompt-based learning survey", "title": "Pre-train, Prompt, and Predict: A Systematic Survey", "work_type": "Survey or review", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Microsoft", "id": 256, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Power%20of%20Prompting&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Power%20of%20Prompting%20Microsoft%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Power%20of%20Prompting&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "Medical domain prompting", "title": "The Power of Prompting", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Suzgun & Kalai", "id": 257, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Meta-Prompting%3A%20Enhancing%20LLMs%20with%20the%20Expert%20Interviewing%20Technique&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Meta-Prompting%3A%20Enhancing%20LLMs%20with%20the%20Expert%20Interviewing%20Technique%20Suzgun%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Meta-Prompting%3A%20Enhancing%20LLMs%20with%20the%20Expert%20Interviewing%20Technique&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "Meta-prompting framework", "title": "Meta-Prompting: Enhancing LLMs with the Expert Interviewing Technique", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Weston & Sukhbaatar", "id": 258, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=System%202%20Attention&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=System%202%20Attention%20Weston%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=System%202%20Attention&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "Regenerating attention for reasoning", "title": "System 2 Attention", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as product documentation or standard, not as a research paper.", "severity": "warning" } ], "authors": "Anthropic", "id": 259, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Anthropic%27s%20Prompt%20Engineering%20Guide&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Anthropic%27s%20Prompt%20Engineering%20Guide%20Anthropic%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Anthropic%27s%20Prompt%20Engineering%20Guide&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "Best practices for Claude prompting", "title": "Anthropic's Prompt Engineering Guide", "work_type": "Product documentation or standard", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as product documentation or standard, not as a research paper.", "severity": "warning" } ], "authors": "OpenAI", "id": 260, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=OpenAI%27s%20Prompt%20Engineering%20Guide&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=OpenAI%27s%20Prompt%20Engineering%20Guide%20OpenAI%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=OpenAI%27s%20Prompt%20Engineering%20Guide&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 12, "section_title": "Prompt Engineering & In-Context Learning", "source_note": "GPT prompting best practices", "title": "OpenAI's Prompt Engineering Guide", "work_type": "Product documentation or standard", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Wei et al.", "id": 261, "links": { "canonical_url": "https://arxiv.org/abs/2201.11903", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2201.11903.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Chain-of-Thought%20Prompting%20Elicits%20Reasoning%20in%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Chain-of-Thought%20Prompting%20Elicits%20Reasoning%20in%20LLMs%20Wei%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Chain-of-Thought%20Prompting%20Elicits%20Reasoning%20in%20LLMs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2201.11903.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "**CoT prompting**", "title": "Chain-of-Thought Prompting Elicits Reasoning in LLMs", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Wang et al.", "id": 262, "links": { "canonical_url": "https://arxiv.org/abs/2203.11171", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2203.11171.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Self-Consistency%20Improves%20Chain%20of%20Thought%20Reasoning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Self-Consistency%20Improves%20Chain%20of%20Thought%20Reasoning%20Wang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Self-Consistency%20Improves%20Chain%20of%20Thought%20Reasoning&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2203.11171.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Sample-and-vote for CoT", "title": "Self-Consistency Improves Chain of Thought Reasoning", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Yao et al.", "id": 263, "links": { "canonical_url": "https://arxiv.org/abs/2305.10601", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.10601.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Tree%20of%20Thoughts%3A%20Deliberate%20Problem%20Solving%20with%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Tree%20of%20Thoughts%3A%20Deliberate%20Problem%20Solving%20with%20LLMs%20Yao%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Tree%20of%20Thoughts%3A%20Deliberate%20Problem%20Solving%20with%20LLMs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.10601.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Tree-based reasoning", "title": "Tree of Thoughts: Deliberate Problem Solving with LLMs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Besta et al.", "id": 264, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Graph%20of%20Thoughts&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Graph%20of%20Thoughts%20Besta%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Graph%20of%20Thoughts&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Graph-structured reasoning", "title": "Graph of Thoughts", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zhou et al.", "id": 265, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Least-to-Most%20Prompting%20Enables%20Complex%20Reasoning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Least-to-Most%20Prompting%20Enables%20Complex%20Reasoning%20Zhou%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Least-to-Most%20Prompting%20Enables%20Complex%20Reasoning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Decompose then solve", "title": "Least-to-Most Prompting Enables Complex Reasoning", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 266, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Automatic%20Chain%20of%20Thought%20Prompting%20%28Auto-CoT%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Automatic%20Chain%20of%20Thought%20Prompting%20%28Auto-CoT%29%20Zhang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Automatic%20Chain%20of%20Thought%20Prompting%20%28Auto-CoT%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Automatic CoT generation", "title": "Automatic Chain of Thought Prompting (Auto-CoT)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Fu et al.", "id": 267, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Complexity-Based%20Prompting%20for%20Multi-Step%20Reasoning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Complexity-Based%20Prompting%20for%20Multi-Step%20Reasoning%20Fu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Complexity-Based%20Prompting%20for%20Multi-Step%20Reasoning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Complexity-guided CoT", "title": "Complexity-Based Prompting for Multi-Step Reasoning", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Chen et al.", "id": 268, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Program%20of%20Thoughts%20Prompting%20%28PoT%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Program%20of%20Thoughts%20Prompting%20%28PoT%29%20Chen%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Program%20of%20Thoughts%20Prompting%20%28PoT%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Code-aided reasoning", "title": "Program of Thoughts Prompting (PoT)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Gao et al.", "id": 269, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=PAL%3A%20Program-Aided%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=PAL%3A%20Program-Aided%20Language%20Models%20Gao%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=PAL%3A%20Program-Aided%20Language%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Programs for reasoning", "title": "PAL: Program-Aided Language Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Lyu et al.", "id": 270, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Faithful%20Chain-of-Thought%20Reasoning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Faithful%20Chain-of-Thought%20Reasoning%20Lyu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Faithful%20Chain-of-Thought%20Reasoning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Faithful, verifiable CoT", "title": "Faithful Chain-of-Thought Reasoning", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Hendrycks et al.", "id": 271, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Measuring%20Mathematical%20Problem%20Solving%20With%20the%20MATH%20Dataset&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Measuring%20Mathematical%20Problem%20Solving%20With%20the%20MATH%20Dataset%20Hendrycks%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Measuring%20Mathematical%20Problem%20Solving%20With%20the%20MATH%20Dataset&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Math reasoning benchmark", "title": "Measuring Mathematical Problem Solving With the MATH Dataset", "work_type": "Benchmark or dataset paper", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Cobbe et al.", "id": 272, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GSM8K%3A%20Training%20Verifiers%20to%20Solve%20Math%20Word%20Problems&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GSM8K%3A%20Training%20Verifiers%20to%20Solve%20Math%20Word%20Problems%20Cobbe%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=GSM8K%3A%20Training%20Verifiers%20to%20Solve%20Math%20Word%20Problems&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Math word problem dataset", "title": "GSM8K: Training Verifiers to Solve Math Word Problems", "work_type": "Benchmark or dataset paper", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Lightman et al.", "id": 273, "links": { "canonical_url": "https://arxiv.org/abs/2305.20050", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.20050.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Let%27s%20Verify%20Step%20by%20Step&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Let%27s%20Verify%20Step%20by%20Step%20Lightman%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Let%27s%20Verify%20Step%20by%20Step&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.20050.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Process reward models for math", "title": "Let's Verify Step by Step", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zelikman et al.", "id": 274, "links": { "canonical_url": "https://arxiv.org/abs/2203.14465", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2203.14465.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=STaR%3A%20Self-Taught%20Reasoner&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=STaR%3A%20Self-Taught%20Reasoner%20Zelikman%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=STaR%3A%20Self-Taught%20Reasoner&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2203.14465.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Bootstrap reasoning ability", "title": "STaR: Self-Taught Reasoner", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Zelikman et al.", "id": 275, "links": { "canonical_url": "https://arxiv.org/abs/2403.09629", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2403.09629.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Quiet-STaR%3A%20LMs%20Can%20Teach%20Themselves%20to%20Think%20Before%20Speaking&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Quiet-STaR%3A%20LMs%20Can%20Teach%20Themselves%20to%20Think%20Before%20Speaking%20Zelikman%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Quiet-STaR%3A%20LMs%20Can%20Teach%20Themselves%20to%20Think%20Before%20Speaking&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2403.09629.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Implicit reasoning training", "title": "Quiet-STaR: LMs Can Teach Themselves to Think Before Speaking", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Mitra et al.", "id": 276, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Orca%202%3A%20Teaching%20Small%20LMs%20How%20to%20Reason&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Orca%202%3A%20Teaching%20Small%20LMs%20How%20to%20Reason%20Mitra%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Orca%202%3A%20Teaching%20Small%20LMs%20How%20to%20Reason&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Strategy selection for reasoning", "title": "Orca 2: Teaching Small LMs How to Reason", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Shinn et al.", "id": 277, "links": { "canonical_url": "https://arxiv.org/abs/2303.11366", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2303.11366.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Reflexion%3A%20Language%20Agents%20with%20Verbal%20Reinforcement&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Reflexion%3A%20Language%20Agents%20with%20Verbal%20Reinforcement%20Shinn%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Reflexion%3A%20Language%20Agents%20with%20Verbal%20Reinforcement&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2303.11366.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Self-reflection for improvement", "title": "Reflexion: Language Agents with Verbal Reinforcement", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "OpenAI", "id": 278, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=o1%20/%20Large%20Reasoning%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=o1%20/%20Large%20Reasoning%20Models%20OpenAI%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=o1%20/%20Large%20Reasoning%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Test-time compute for reasoning", "title": "o1 / Large Reasoning Models", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 915 ], "severity": "warning" } ], "authors": "DeepSeek", "id": 279, "links": { "canonical_url": "https://arxiv.org/abs/2501.12948", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2501.12948.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeepSeek-R1%3A%20Incentivizing%20Reasoning%20Capability%20in%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeepSeek-R1%3A%20Incentivizing%20Reasoning%20Capability%20in%20LLMs%20DeepSeek%202025", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeepSeek-R1%3A%20Incentivizing%20Reasoning%20Capability%20in%20LLMs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2501.12948.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Reasoning via RL", "title": "DeepSeek-R1: Incentivizing Reasoning Capability in LLMs", "work_type": "Research-paper candidate", "year": 2025, "year_display": "2025" }, { "audit_flags": [], "authors": "Snell et al.", "id": 280, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scaling%20LLM%20Test-Time%20Compute%20Optimally&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scaling%20LLM%20Test-Time%20Compute%20Optimally%20Snell%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scaling%20LLM%20Test-Time%20Compute%20Optimally&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Optimal test-time compute allocation", "title": "Scaling LLM Test-Time Compute Optimally", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Goyal et al.", "id": 281, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Think%20before%20you%20speak%3A%20Training%20LMs%20with%20Pause%20Tokens&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Think%20before%20you%20speak%3A%20Training%20LMs%20with%20Pause%20Tokens%20Goyal%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Think%20before%20you%20speak%3A%20Training%20LMs%20with%20Pause%20Tokens&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Pause tokens for thinking", "title": "Think before you speak: Training LMs with Pause Tokens", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Wang et al.", "id": 282, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Journey%20Learning%3A%20From%20Superficial%20to%20Reasoning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Journey%20Learning%3A%20From%20Superficial%20to%20Reasoning%20Wang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Journey%20Learning%3A%20From%20Superficial%20to%20Reasoning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Staged reasoning curriculum", "title": "Journey Learning: From Superficial to Reasoning", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Qi et al.", "id": 283, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mutual%20Reasoning%20Makes%20Smaller%20LLMs%20Stronger%20Problem-Solvers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mutual%20Reasoning%20Makes%20Smaller%20LLMs%20Stronger%20Problem-Solvers%20Qi%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mutual%20Reasoning%20Makes%20Smaller%20LLMs%20Stronger%20Problem-Solvers&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Cross-model reasoning", "title": "Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 284, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Beyond%20Chain-of-Thought%3A%20A%20Survey%20of%20Chain-of-X%20Paradigms&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Beyond%20Chain-of-Thought%3A%20A%20Survey%20of%20Chain-of-X%20Paradigms%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Beyond%20Chain-of-Thought%3A%20A%20Survey%20of%20Chain-of-X%20Paradigms&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Survey of CoT variants", "title": "Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 285, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Rethinking%20LLM%20Reasoning%3A%20Are%20LLMs%20Truly%20Reasoning%20or%20Reciting%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Rethinking%20LLM%20Reasoning%3A%20Are%20LLMs%20Truly%20Reasoning%20or%20Reciting%3F%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Rethinking%20LLM%20Reasoning%3A%20Are%20LLMs%20Truly%20Reasoning%20or%20Reciting%3F&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 13, "section_title": "Reasoning & Chain-of-Thought", "source_note": "Analyzing reasoning vs memorization", "title": "Rethinking LLM Reasoning: Are LLMs Truly Reasoning or Reciting?", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Lewis et al.", "id": 286, "links": { "canonical_url": "https://arxiv.org/abs/2005.11401", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2005.11401.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Retrieval-Augmented%20Generation%20for%20Knowledge-Intensive%20NLP%20Tasks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Retrieval-Augmented%20Generation%20for%20Knowledge-Intensive%20NLP%20Tasks%20Lewis%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Retrieval-Augmented%20Generation%20for%20Knowledge-Intensive%20NLP%20Tasks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2005.11401.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "**Original RAG paper**", "title": "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Guu et al.", "id": 287, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=REALM%3A%20Retrieval-Augmented%20Language%20Model%20Pre-Training&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=REALM%3A%20Retrieval-Augmented%20Language%20Model%20Pre-Training%20Guu%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=REALM%3A%20Retrieval-Augmented%20Language%20Model%20Pre-Training&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Pretraining with retrieval", "title": "REALM: Retrieval-Augmented Language Model Pre-Training", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Karpukhin et al.", "id": 288, "links": { "canonical_url": "https://arxiv.org/abs/2004.04906", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2004.04906.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Dense%20Passage%20Retrieval%20%28DPR%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Dense%20Passage%20Retrieval%20%28DPR%29%20Karpukhin%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Dense%20Passage%20Retrieval%20%28DPR%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2004.04906.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Dense retrieval for QA", "title": "Dense Passage Retrieval (DPR)", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Khattab & Zaharia", "id": 289, "links": { "canonical_url": "https://arxiv.org/abs/2004.12832", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2004.12832.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ColBERT%3A%20Efficient%20and%20Effective%20Passage%20Search&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ColBERT%3A%20Efficient%20and%20Effective%20Passage%20Search%20Khattab%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=ColBERT%3A%20Efficient%20and%20Effective%20Passage%20Search&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2004.12832.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Late interaction retrieval", "title": "ColBERT: Efficient and Effective Passage Search", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Santhanam et al.", "id": 290, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ColBERTv2%3A%20Effective%20and%20Efficient%20Retrieval%20via%20Lightweight%20Late%20Interaction&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ColBERTv2%3A%20Effective%20and%20Efficient%20Retrieval%20via%20Lightweight%20Late%20Interaction%20Santhanam%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=ColBERTv2%3A%20Effective%20and%20Efficient%20Retrieval%20via%20Lightweight%20Late%20Interaction&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Improved ColBERT", "title": "ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Borgeaud et al.", "id": 291, "links": { "canonical_url": "https://arxiv.org/abs/2112.04426", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2112.04426.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RETRO%3A%20Improving%20Language%20Models%20by%20Retrieving%20from%20Trillions%20of%20Tokens&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RETRO%3A%20Improving%20Language%20Models%20by%20Retrieving%20from%20Trillions%20of%20Tokens%20Borgeaud%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=RETRO%3A%20Improving%20Language%20Models%20by%20Retrieving%20from%20Trillions%20of%20Tokens&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2112.04426.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Retrieval-enhanced LM", "title": "RETRO: Improving Language Models by Retrieving from Trillions of Tokens", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Izacard et al.", "id": 292, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Atlas%3A%20Few-shot%20Learning%20with%20Retrieval%20Augmented%20LMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Atlas%3A%20Few-shot%20Learning%20with%20Retrieval%20Augmented%20LMs%20Izacard%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Atlas%3A%20Few-shot%20Learning%20with%20Retrieval%20Augmented%20LMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "RAG for few-shot", "title": "Atlas: Few-shot Learning with Retrieval Augmented LMs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Asai et al.", "id": 293, "links": { "canonical_url": "https://arxiv.org/abs/2310.11511", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2310.11511.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Self-RAG%3A%20Learning%20to%20Retrieve%2C%20Generate%2C%20and%20Critique&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Self-RAG%3A%20Learning%20to%20Retrieve%2C%20Generate%2C%20and%20Critique%20Asai%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Self-RAG%3A%20Learning%20to%20Retrieve%2C%20Generate%2C%20and%20Critique&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2310.11511.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Self-reflective RAG", "title": "Self-RAG: Learning to Retrieve, Generate, and Critique", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Yan et al.", "id": 294, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Corrective%20RAG%20%28CRAG%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Corrective%20RAG%20%28CRAG%29%20Yan%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Corrective%20RAG%20%28CRAG%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Self-correcting retrieval", "title": "Corrective RAG (CRAG)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Jeong et al.", "id": 295, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Adaptive%20RAG&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Adaptive%20RAG%20Jeong%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Adaptive%20RAG&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Query-adaptive retrieval", "title": "Adaptive RAG", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Sarthi et al.", "id": 296, "links": { "canonical_url": "https://arxiv.org/abs/2401.18059", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2401.18059.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RAPTOR%3A%20Recursive%20Abstractive%20Processing%20for%20Tree-Organized%20Retrieval&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RAPTOR%3A%20Recursive%20Abstractive%20Processing%20for%20Tree-Organized%20Retrieval%20Sarthi%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=RAPTOR%3A%20Recursive%20Abstractive%20Processing%20for%20Tree-Organized%20Retrieval&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2401.18059.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Hierarchical document chunking", "title": "RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Gao et al.", "id": 297, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=HyDE%3A%20Precise%20Zero-Shot%20Dense%20Retrieval%20without%20Relevance%20Labels&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=HyDE%3A%20Precise%20Zero-Shot%20Dense%20Retrieval%20without%20Relevance%20Labels%20Gao%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=HyDE%3A%20Precise%20Zero-Shot%20Dense%20Retrieval%20without%20Relevance%20Labels&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Hypothetical document embeddings", "title": "HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Liu et al.", "id": 298, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Lost%20in%20the%20Middle%3A%20How%20LMs%20Use%20Long%20Contexts&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Lost%20in%20the%20Middle%3A%20How%20LMs%20Use%20Long%20Contexts%20Liu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Lost%20in%20the%20Middle%3A%20How%20LMs%20Use%20Long%20Contexts&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Position bias in long contexts", "title": "Lost in the Middle: How LMs Use Long Contexts", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Gao et al.", "id": 299, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Retrieval-Augmented%20Generation%3A%20A%20Survey&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Retrieval-Augmented%20Generation%3A%20A%20Survey%20Gao%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Retrieval-Augmented%20Generation%3A%20A%20Survey&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Comprehensive RAG survey", "title": "Retrieval-Augmented Generation: A Survey", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 300, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=From%20RAG%20to%20Agentic%20RAG&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=From%20RAG%20to%20Agentic%20RAG%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=From%20RAG%20to%20Agentic%20RAG&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Agentic retrieval patterns", "title": "From RAG to Agentic RAG", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Edge et al.", "id": 301, "links": { "canonical_url": "https://arxiv.org/abs/2404.16130", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2404.16130.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Graph%20RAG%3A%20Unlocking%20LLM%20Discovery%20on%20Narrative%20Private%20Data&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Graph%20RAG%3A%20Unlocking%20LLM%20Discovery%20on%20Narrative%20Private%20Data%20Edge%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Graph%20RAG%3A%20Unlocking%20LLM%20Discovery%20on%20Narrative%20Private%20Data&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2404.16130.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Graph-based RAG", "title": "Graph RAG: Unlocking LLM Discovery on Narrative Private Data", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Anthropic", "id": 302, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Contextual%20Retrieval&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Contextual%20Retrieval%20Anthropic%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Contextual%20Retrieval&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Contextual chunk headers", "title": "Contextual Retrieval", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "non_paper_or_multi_work", "message": "A multi-model topic container, not one citable work; the importer requires a four-digit year.", "required_action": "Replace with separate canonical E5, BGE and GTE publications.", "severity": "blocking" } ], "authors": "Various", "id": 303, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Embedding%20Models%20%28E5%2C%20BGE%2C%20GTE%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Embedding%20Models%20%28E5%2C%20BGE%2C%20GTE%29%20Various%202023-2024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Embedding%20Models%20%28E5%2C%20BGE%2C%20GTE%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Modern embedding models", "title": "Embedding Models (E5, BGE, GTE)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023-2024" }, { "audit_flags": [], "authors": "Muennighoff et al.", "id": 304, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MTEB%3A%20Massive%20Text%20Embedding%20Benchmark&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MTEB%3A%20Massive%20Text%20Embedding%20Benchmark%20Muennighoff%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=MTEB%3A%20Massive%20Text%20Embedding%20Benchmark&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Embedding evaluation", "title": "MTEB: Massive Text Embedding Benchmark", "work_type": "Benchmark or dataset paper", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Kusupati et al.", "id": 305, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Matryoshka%20Representation%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Matryoshka%20Representation%20Learning%20Kusupati%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Matryoshka%20Representation%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 14, "section_title": "Retrieval-Augmented Generation (RAG)", "source_note": "Multi-granularity embeddings", "title": "Matryoshka Representation Learning", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Schick et al.", "id": 306, "links": { "canonical_url": "https://arxiv.org/abs/2302.04761", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2302.04761.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Toolformer%3A%20Language%20Models%20Can%20Teach%20Themselves%20to%20Use%20Tools&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Toolformer%3A%20Language%20Models%20Can%20Teach%20Themselves%20to%20Use%20Tools%20Schick%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Toolformer%3A%20Language%20Models%20Can%20Teach%20Themselves%20to%20Use%20Tools&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2302.04761.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "**Self-supervised tool learning**", "title": "Toolformer: Language Models Can Teach Themselves to Use Tools", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Nakano et al.", "id": 307, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=WebGPT%3A%20Browser-Assisted%20Question-Answering&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=WebGPT%3A%20Browser-Assisted%20Question-Answering%20Nakano%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=WebGPT%3A%20Browser-Assisted%20Question-Answering&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "LLM with web browsing", "title": "WebGPT: Browser-Assisted Question-Answering", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Paranjape et al.", "id": 308, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ART%3A%20Automatic%20Multi-step%20Reasoning%20and%20Tool-use&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ART%3A%20Automatic%20Multi-step%20Reasoning%20and%20Tool-use%20Paranjape%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=ART%3A%20Automatic%20Multi-step%20Reasoning%20and%20Tool-use&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "Automated tool selection", "title": "ART: Automatic Multi-step Reasoning and Tool-use", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Patil et al.", "id": 309, "links": { "canonical_url": "https://arxiv.org/abs/2305.15334", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.15334.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Gorilla%3A%20Large%20Language%20Model%20Connected%20with%20Massive%20APIs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Gorilla%3A%20Large%20Language%20Model%20Connected%20with%20Massive%20APIs%20Patil%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Gorilla%3A%20Large%20Language%20Model%20Connected%20with%20Massive%20APIs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.15334.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "API-calling LLM", "title": "Gorilla: Large Language Model Connected with Massive APIs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Qin et al.", "id": 310, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ToolLLM%3A%20Facilitating%20LLMs%20to%20Master%2016000%2B%20APIs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ToolLLM%3A%20Facilitating%20LLMs%20to%20Master%2016000%2B%20APIs%20Qin%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=ToolLLM%3A%20Facilitating%20LLMs%20to%20Master%2016000%2B%20APIs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "Large-scale API learning", "title": "ToolLLM: Facilitating LLMs to Master 16000+ APIs", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Li et al.", "id": 311, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=API-Bank%3A%20A%20Comprehensive%20Benchmark%20for%20Tool-Augmented%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=API-Bank%3A%20A%20Comprehensive%20Benchmark%20for%20Tool-Augmented%20LLMs%20Li%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=API-Bank%3A%20A%20Comprehensive%20Benchmark%20for%20Tool-Augmented%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "Tool use benchmark", "title": "API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs", "work_type": "Benchmark or dataset paper", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Liang et al.", "id": 312, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=TaskMatrix.AI%3A%20Completing%20Tasks%20by%20Connecting%20Foundation%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=TaskMatrix.AI%3A%20Completing%20Tasks%20by%20Connecting%20Foundation%20Models%20Liang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=TaskMatrix.AI%3A%20Completing%20Tasks%20by%20Connecting%20Foundation%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "Foundation model orchestration", "title": "TaskMatrix.AI: Completing Tasks by Connecting Foundation Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Shen et al.", "id": 313, "links": { "canonical_url": "https://arxiv.org/abs/2303.17580", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2303.17580.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=HuggingGPT%3A%20Solving%20AI%20Tasks%20with%20ChatGPT%20and%20HuggingFace&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=HuggingGPT%3A%20Solving%20AI%20Tasks%20with%20ChatGPT%20and%20HuggingFace%20Shen%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=HuggingGPT%3A%20Solving%20AI%20Tasks%20with%20ChatGPT%20and%20HuggingFace&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2303.17580.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "LLM as controller of AI models", "title": "HuggingGPT: Solving AI Tasks with ChatGPT and HuggingFace", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Lu et al.", "id": 314, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Chameleon%3A%20Plug-and-Play%20Compositional%20Reasoning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Chameleon%3A%20Plug-and-Play%20Compositional%20Reasoning%20Lu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Chameleon%3A%20Plug-and-Play%20Compositional%20Reasoning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "Compositional tool use", "title": "Chameleon: Plug-and-Play Compositional Reasoning", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Nexusflow", "id": 315, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=NexusRaven%3A%20Function%20Calling%20LLM&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=NexusRaven%3A%20Function%20Calling%20LLM%20Nexusflow%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=NexusRaven%3A%20Function%20Calling%20LLM&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "Specialized function-calling model", "title": "NexusRaven: Function Calling LLM", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as product documentation or standard, not as a research paper.", "severity": "warning" } ], "authors": "Anthropic", "id": 316, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Anthropic%27s%20Tool%20Use%20Documentation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Anthropic%27s%20Tool%20Use%20Documentation%20Anthropic%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Anthropic%27s%20Tool%20Use%20Documentation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "Tool use patterns for Claude", "title": "Anthropic's Tool Use Documentation", "work_type": "Product documentation or standard", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as product documentation or standard, not as a research paper.", "severity": "warning" } ], "authors": "Anthropic", "id": 317, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Model%20Context%20Protocol%20%28MCP%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Model%20Context%20Protocol%20%28MCP%29%20Anthropic%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Model%20Context%20Protocol%20%28MCP%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "Standard protocol for tool integration", "title": "Model Context Protocol (MCP)", "work_type": "Product documentation or standard", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Song et al.", "id": 318, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RestGPT%3A%20Connecting%20LLMs%20with%20Real-World%20RESTful%20APIs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RestGPT%3A%20Connecting%20LLMs%20with%20Real-World%20RESTful%20APIs%20Song%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=RestGPT%3A%20Connecting%20LLMs%20with%20Real-World%20RESTful%20APIs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "REST API integration", "title": "RestGPT: Connecting LLMs with Real-World RESTful APIs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Karpas et al.", "id": 319, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MRKL%20Systems&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MRKL%20Systems%20Karpas%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=MRKL%20Systems&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "Modular Reasoning, Knowledge, Language", "title": "MRKL Systems", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Creswell & Shanahan", "id": 320, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Faithful%20Reasoning%20Using%20Large%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Faithful%20Reasoning%20Using%20Large%20Language%20Models%20Creswell%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Faithful%20Reasoning%20Using%20Large%20Language%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 15, "section_title": "Tool Use & Function Calling", "source_note": "Tool-augmented faithful reasoning", "title": "Faithful Reasoning Using Large Language Models", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Wang et al.", "id": 321, "links": { "canonical_url": "https://arxiv.org/abs/2308.11432", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2308.11432.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Survey%20on%20Large%20Language%20Model%20based%20Autonomous%20Agents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Survey%20on%20Large%20Language%20Model%20based%20Autonomous%20Agents%20Wang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Survey%20on%20Large%20Language%20Model%20based%20Autonomous%20Agents&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2308.11432.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "**Comprehensive agent survey**", "title": "A Survey on Large Language Model based Autonomous Agents", "work_type": "Survey or review", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Yao et al.", "id": 322, "links": { "canonical_url": "https://arxiv.org/abs/2210.03629", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2210.03629.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ReAct%3A%20Synergizing%20Reasoning%20and%20Acting%20in%20LMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ReAct%3A%20Synergizing%20Reasoning%20and%20Acting%20in%20LMs%20Yao%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=ReAct%3A%20Synergizing%20Reasoning%20and%20Acting%20in%20LMs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2210.03629.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "**Reason-Act paradigm**", "title": "ReAct: Synergizing Reasoning and Acting in LMs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Wang et al.", "id": 323, "links": { "canonical_url": "https://arxiv.org/abs/2305.16291", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.16291.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Voyager%3A%20An%20Open-Ended%20Embodied%20Agent%20with%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Voyager%3A%20An%20Open-Ended%20Embodied%20Agent%20with%20LLMs%20Wang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Voyager%3A%20An%20Open-Ended%20Embodied%20Agent%20with%20LLMs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.16291.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Lifelong learning agent in Minecraft", "title": "Voyager: An Open-Ended Embodied Agent with LLMs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Park et al.", "id": 324, "links": { "canonical_url": "https://arxiv.org/abs/2304.03442", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2304.03442.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Generative%20Agents%3A%20Interactive%20Simulacra%20of%20Human%20Behavior&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Generative%20Agents%3A%20Interactive%20Simulacra%20of%20Human%20Behavior%20Park%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Generative%20Agents%3A%20Interactive%20Simulacra%20of%20Human%20Behavior&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2304.03442.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Believable agent society", "title": "Generative Agents: Interactive Simulacra of Human Behavior", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Richards", "id": 325, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AutoGPT%20%28technical%20overview%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AutoGPT%20%28technical%20overview%29%20Richards%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=AutoGPT%20%28technical%20overview%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Autonomous GPT-4 agent", "title": "AutoGPT (technical overview)", "work_type": "Survey or review", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Nakajima", "id": 326, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BabyAGI&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BabyAGI%20Nakajima%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=BabyAGI&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Task-driven autonomous agent", "title": "BabyAGI", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Chase", "id": 327, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LangChain%20Agents%20%28technical%20paper%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LangChain%20Agents%20%28technical%20paper%29%20Chase%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=LangChain%20Agents%20%28technical%20paper%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Agent framework and chains", "title": "LangChain Agents (technical paper)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Liu et al.", "id": 328, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AgentBench%3A%20Evaluating%20LLMs%20as%20Agents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AgentBench%3A%20Evaluating%20LLMs%20as%20Agents%20Liu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=AgentBench%3A%20Evaluating%20LLMs%20as%20Agents&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Agent evaluation benchmark", "title": "AgentBench: Evaluating LLMs as Agents", "work_type": "Benchmark or dataset paper", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Liu et al.", "id": 329, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BOLAA%3A%20Benchmarking%20and%20Orchestrating%20LLM-augmented%20Autonomous%20Agents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BOLAA%3A%20Benchmarking%20and%20Orchestrating%20LLM-augmented%20Autonomous%20Agents%20Liu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=BOLAA%3A%20Benchmarking%20and%20Orchestrating%20LLM-augmented%20Autonomous%20Agents&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Agent orchestration benchmark", "title": "BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents", "work_type": "Benchmark or dataset paper", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Xi et al.", "id": 330, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Rise%20and%20Potential%20of%20LLM%20Based%20Agents%3A%20A%20Survey&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Rise%20and%20Potential%20of%20LLM%20Based%20Agents%3A%20A%20Survey%20Xi%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Rise%20and%20Potential%20of%20LLM%20Based%20Agents%3A%20A%20Survey&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Agent capabilities survey", "title": "The Rise and Potential of LLM Based Agents: A Survey", "work_type": "Survey or review", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 331, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Agent%20Foundation%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Agent%20Foundation%20Models%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Agent%20Foundation%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Training agents end-to-end", "title": "Agent Foundation Models", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Xie et al.", "id": 332, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=OpenAgents%3A%20An%20Open%20Platform%20for%20Language%20Agents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=OpenAgents%3A%20An%20Open%20Platform%20for%20Language%20Agents%20Xie%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=OpenAgents%3A%20An%20Open%20Platform%20for%20Language%20Agents&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Open agent platform", "title": "OpenAgents: An Open Platform for Language Agents", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zeng et al.", "id": 333, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AgentTuning%3A%20Enabling%20Generalized%20Agent%20Abilities%20For%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AgentTuning%3A%20Enabling%20Generalized%20Agent%20Abilities%20For%20LLMs%20Zeng%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=AgentTuning%3A%20Enabling%20Generalized%20Agent%20Abilities%20For%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Fine-tuning for agent behavior", "title": "AgentTuning: Enabling Generalized Agent Abilities For LLMs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Sumers et al.", "id": 334, "links": { "canonical_url": "https://arxiv.org/abs/2309.02427", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2309.02427.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Cognitive%20Architectures%20for%20Language%20Agents%20%28CoALA%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Cognitive%20Architectures%20for%20Language%20Agents%20%28CoALA%29%20Sumers%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Cognitive%20Architectures%20for%20Language%20Agents%20%28CoALA%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2309.02427.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Cognitive architecture for agents", "title": "Cognitive Architectures for Language Agents (CoALA)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 335, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Language%20Agents%3A%20From%20Next-Token%20Prediction%20to%20Digital%20Automation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Language%20Agents%3A%20From%20Next-Token%20Prediction%20to%20Digital%20Automation%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Language%20Agents%3A%20From%20Next-Token%20Prediction%20to%20Digital%20Automation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Vision for language agents", "title": "Language Agents: From Next-Token Prediction to Digital Automation", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zhuge et al.", "id": 336, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Agent-as-a-Judge&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Agent-as-a-Judge%20Zhuge%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Agent-as-a-Judge&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Agents evaluating agents", "title": "Agent-as-a-Judge", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Liu et al.", "id": 337, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AgentLite%3A%20A%20Lightweight%20Library%20for%20Building%20and%20Advancing%20Task-Oriented%20LLM%20Agents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AgentLite%3A%20A%20Lightweight%20Library%20for%20Building%20and%20Advancing%20Task-Oriented%20LLM%20Agents%20Liu%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=AgentLite%3A%20A%20Lightweight%20Library%20for%20Building%20and%20Advancing%20Task-Oriented%20LLM%20Agents&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Lightweight agent library", "title": "AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agents", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Li et al.", "id": 338, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Personal%20LLM%20Agents%3A%20Insights%20and%20Survey%20about%20the%20Capability%2C%20Efficiency%20and%20Security&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Personal%20LLM%20Agents%3A%20Insights%20and%20Survey%20about%20the%20Capability%2C%20Efficiency%20and%20Security%20Li%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Personal%20LLM%20Agents%3A%20Insights%20and%20Survey%20about%20the%20Capability%2C%20Efficiency%20and%20Security&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Personal agent survey", "title": "Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 339, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Agent%20Smith%3A%20Scaling%20LLM%20Agents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Agent%20Smith%3A%20Scaling%20LLM%20Agents%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Agent%20Smith%3A%20Scaling%20LLM%20Agents&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Scaling agent systems", "title": "Agent Smith: Scaling LLM Agents", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Chen et al.", "id": 340, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Internet%20of%20Agents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Internet%20of%20Agents%20Chen%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Internet%20of%20Agents&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 16, "section_title": "AI Agents — Foundations", "source_note": "Networked agent systems", "title": "Internet of Agents", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 341, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Planning%20with%20Large%20Language%20Models%20for%20Code%20Generation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Planning%20with%20Large%20Language%20Models%20for%20Code%20Generation%20Zhang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Planning%20with%20Large%20Language%20Models%20for%20Code%20Generation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "LLM-based planning", "title": "Planning with Large Language Models for Code Generation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Liu et al.", "id": 342, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLM%2BP%3A%20Empowering%20LLMs%20with%20Optimal%20Planning%20Proficiency&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLM%2BP%3A%20Empowering%20LLMs%20with%20Optimal%20Planning%20Proficiency%20Liu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLM%2BP%3A%20Empowering%20LLMs%20with%20Optimal%20Planning%20Proficiency&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "Classical planning with LLMs", "title": "LLM+P: Empowering LLMs with Optimal Planning Proficiency", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Wang et al.", "id": 343, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Describe%2C%20Explain%2C%20Plan%20and%20Select%20%28DEPS%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Describe%2C%20Explain%2C%20Plan%20and%20Select%20%28DEPS%29%20Wang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Describe%2C%20Explain%2C%20Plan%20and%20Select%20%28DEPS%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "Multi-step planning", "title": "Describe, Explain, Plan and Select (DEPS)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Wang et al.", "id": 344, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Plan-and-Solve%20Prompting&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Plan-and-Solve%20Prompting%20Wang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Plan-and-Solve%20Prompting&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "Plan before solving", "title": "Plan-and-Solve Prompting", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Sun et al.", "id": 345, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AdaPlanner%3A%20Adaptive%20Planning%20from%20Feedback&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AdaPlanner%3A%20Adaptive%20Planning%20from%20Feedback%20Sun%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=AdaPlanner%3A%20Adaptive%20Planning%20from%20Feedback&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "Feedback-driven planning", "title": "AdaPlanner: Adaptive Planning from Feedback", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 758 ], "severity": "warning" } ], "authors": "Zhou et al.", "id": 346, "links": { "canonical_url": "https://arxiv.org/abs/2310.04406", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2310.04406.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LATS%3A%20Language%20Agent%20Tree%20Search&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LATS%3A%20Language%20Agent%20Tree%20Search%20Zhou%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=LATS%3A%20Language%20Agent%20Tree%20Search&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2310.04406.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "MCTS-style agent search", "title": "LATS: Language Agent Tree Search", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Huang et al.", "id": 347, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Inner%20Monologue%3A%20Embodied%20Reasoning%20through%20Planning%20with%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Inner%20Monologue%3A%20Embodied%20Reasoning%20through%20Planning%20with%20Language%20Models%20Huang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Inner%20Monologue%3A%20Embodied%20Reasoning%20through%20Planning%20with%20Language%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "Inner monologue for robots", "title": "Inner Monologue: Embodied Reasoning through Planning with Language Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Rana et al.", "id": 348, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SayPlan%3A%20Grounding%20Large%20Language%20Models%20using%203D%20Scene%20Graphs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SayPlan%3A%20Grounding%20Large%20Language%20Models%20using%203D%20Scene%20Graphs%20Rana%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=SayPlan%3A%20Grounding%20Large%20Language%20Models%20using%203D%20Scene%20Graphs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "LLM planning with scene graphs", "title": "SayPlan: Grounding Large Language Models using 3D Scene Graphs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Weng", "id": 349, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLM%20Powered%20Autonomous%20Agents%20%28Lilian%20Weng%20blog-paper%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLM%20Powered%20Autonomous%20Agents%20%28Lilian%20Weng%20blog-paper%29%20Weng%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLM%20Powered%20Autonomous%20Agents%20%28Lilian%20Weng%20blog-paper%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "Influential agent design overview", "title": "LLM Powered Autonomous Agents (Lilian Weng blog-paper)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Hao et al.", "id": 350, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Reasoning%20with%20Language%20Model%20is%20Planning%20with%20World%20Model&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Reasoning%20with%20Language%20Model%20is%20Planning%20with%20World%20Model%20Hao%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Reasoning%20with%20Language%20Model%20is%20Planning%20with%20World%20Model&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "RAP — reasoning as planning", "title": "Reasoning with Language Model is Planning with World Model", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Ding et al.", "id": 351, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Everything%20of%20Thoughts%3A%20Defying%20the%20Law%20of%20Penrose%20Triangle&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Everything%20of%20Thoughts%3A%20Defying%20the%20Law%20of%20Penrose%20Triangle%20Ding%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Everything%20of%20Thoughts%3A%20Defying%20the%20Law%20of%20Penrose%20Triangle&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "External solver + LLM", "title": "Everything of Thoughts: Defying the Law of Penrose Triangle", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Yang et al.", "id": 352, "links": { "canonical_url": "https://arxiv.org/abs/2405.15793", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2405.15793.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SWE-Agent%3A%20Agent-Computer%20Interfaces%20Enable%20Automated%20Software%20Engineering&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SWE-Agent%3A%20Agent-Computer%20Interfaces%20Enable%20Automated%20Software%20Engineering%20Yang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=SWE-Agent%3A%20Agent-Computer%20Interfaces%20Enable%20Automated%20Software%20Engineering&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2405.15793.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "Agent-computer interface design", "title": "SWE-Agent: Agent-Computer Interfaces Enable Automated Software Engineering", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Wang et al.", "id": 353, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Trial%20and%20Error%3A%20Exploration-Based%20Trajectory%20Optimization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Trial%20and%20Error%3A%20Exploration-Based%20Trajectory%20Optimization%20Wang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Trial%20and%20Error%3A%20Exploration-Based%20Trajectory%20Optimization&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "Exploration-based agents", "title": "Trial and Error: Exploration-Based Trajectory Optimization", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Huang et al.", "id": 354, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AgentCoder%3A%20Multi-Agent-based%20Code%20Generation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AgentCoder%3A%20Multi-Agent-based%20Code%20Generation%20Huang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=AgentCoder%3A%20Multi-Agent-based%20Code%20Generation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "Agents for coding", "title": "AgentCoder: Multi-Agent-based Code Generation", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Yin et al.", "id": 355, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Lumos%3A%20Learning%20Agents%20with%20Unified%20Data%2C%20Modular%20Design%2C%20and%20Open-Source%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Lumos%3A%20Learning%20Agents%20with%20Unified%20Data%2C%20Modular%20Design%2C%20and%20Open-Source%20LLMs%20Yin%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Lumos%3A%20Learning%20Agents%20with%20Unified%20Data%2C%20Modular%20Design%2C%20and%20Open-Source%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 17, "section_title": "AI Agents — Planning & Reasoning", "source_note": "Modular open-source agents", "title": "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Li et al.", "id": 356, "links": { "canonical_url": "https://arxiv.org/abs/2303.17760", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2303.17760.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=CAMEL%3A%20Communicative%20Agents%20for%20%22Mind%22%20Exploration%20of%20LLM%20Society&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=CAMEL%3A%20Communicative%20Agents%20for%20%22Mind%22%20Exploration%20of%20LLM%20Society%20Li%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=CAMEL%3A%20Communicative%20Agents%20for%20%22Mind%22%20Exploration%20of%20LLM%20Society&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2303.17760.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "**Role-playing multi-agent**", "title": "CAMEL: Communicative Agents for \"Mind\" Exploration of LLM Society", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Wu et al.", "id": 357, "links": { "canonical_url": "https://arxiv.org/abs/2308.08155", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2308.08155.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AutoGen%3A%20Enabling%20Next-Gen%20LLM%20Applications%20via%20Multi-Agent%20Conversation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AutoGen%3A%20Enabling%20Next-Gen%20LLM%20Applications%20via%20Multi-Agent%20Conversation%20Wu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=AutoGen%3A%20Enabling%20Next-Gen%20LLM%20Applications%20via%20Multi-Agent%20Conversation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2308.08155.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "**Microsoft multi-agent framework**", "title": "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Hong et al.", "id": 358, "links": { "canonical_url": "https://arxiv.org/abs/2308.00352", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2308.00352.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MetaGPT%3A%20Meta%20Programming%20for%20Multi-Agent%20Collaborative%20Framework&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MetaGPT%3A%20Meta%20Programming%20for%20Multi-Agent%20Collaborative%20Framework%20Hong%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=MetaGPT%3A%20Meta%20Programming%20for%20Multi-Agent%20Collaborative%20Framework&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2308.00352.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "Software dev multi-agent", "title": "MetaGPT: Meta Programming for Multi-Agent Collaborative Framework", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Qian et al.", "id": 359, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ChatDev%3A%20Communicative%20Agents%20for%20Software%20Development&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ChatDev%3A%20Communicative%20Agents%20for%20Software%20Development%20Qian%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=ChatDev%3A%20Communicative%20Agents%20for%20Software%20Development&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "Chat-driven software dev agents", "title": "ChatDev: Communicative Agents for Software Development", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Chen et al.", "id": 360, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AgentVerse%3A%20Facilitating%20Multi-Agent%20Collaboration&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AgentVerse%3A%20Facilitating%20Multi-Agent%20Collaboration%20Chen%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=AgentVerse%3A%20Facilitating%20Multi-Agent%20Collaboration&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "Multi-agent collaboration", "title": "AgentVerse: Facilitating Multi-Agent Collaboration", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Du et al.", "id": 361, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Multi-Agent%20Debate&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Multi-Agent%20Debate%20Du%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Multi-Agent%20Debate&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "Debate improves factuality", "title": "Multi-Agent Debate", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Liang et al.", "id": 362, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Improving%20Factuality%20and%20Reasoning%20via%20Multi-Agent%20Debate&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Improving%20Factuality%20and%20Reasoning%20via%20Multi-Agent%20Debate%20Liang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Improving%20Factuality%20and%20Reasoning%20via%20Multi-Agent%20Debate&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "Debate for accuracy", "title": "Improving Factuality and Reasoning via Multi-Agent Debate", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Wang et al.", "id": 363, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Dynamic%20LLM-Agent%20Network%3A%20Mixture%20of%20Agents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Dynamic%20LLM-Agent%20Network%3A%20Mixture%20of%20Agents%20Wang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Dynamic%20LLM-Agent%20Network%3A%20Mixture%20of%20Agents&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "Dynamic agent composition", "title": "Dynamic LLM-Agent Network: Mixture of Agents", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 906 ], "severity": "warning" } ], "authors": "Together AI", "id": 364, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mixture%20of%20Agents%20%28MoA%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mixture%20of%20Agents%20%28MoA%29%20Together%20AI%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mixture%20of%20Agents%20%28MoA%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "Layered multi-agent inference", "title": "Mixture of Agents (MoA)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Moura", "id": 365, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=CrewAI%20%28technical%20overview%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=CrewAI%20%28technical%20overview%29%20Moura%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=CrewAI%20%28technical%20overview%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "Role-based agent orchestration", "title": "CrewAI (technical overview)", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zhuge et al.", "id": 366, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Society%20of%20Mind%20%28SoM%29%20for%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Society%20of%20Mind%20%28SoM%29%20for%20LLMs%20Zhuge%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Society%20of%20Mind%20%28SoM%29%20for%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "Modular cognitive agents", "title": "Society of Mind (SoM) for LLMs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Sun et al.", "id": 367, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Corex%3A%20Pushing%20the%20Boundaries%20of%20Complex%20Reasoning%20through%20Multi-Agent%20Collaboration&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Corex%3A%20Pushing%20the%20Boundaries%20of%20Complex%20Reasoning%20through%20Multi-Agent%20Collaboration%20Sun%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Corex%3A%20Pushing%20the%20Boundaries%20of%20Complex%20Reasoning%20through%20Multi-Agent%20Collaboration&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "Complex reasoning agents", "title": "Corex: Pushing the Boundaries of Complex Reasoning through Multi-Agent Collaboration", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Liang et al.", "id": 368, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MAD%3A%20Multi-Agent%20Debate%20with%20Large%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MAD%3A%20Multi-Agent%20Debate%20with%20Large%20Language%20Models%20Liang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=MAD%3A%20Multi-Agent%20Debate%20with%20Large%20Language%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "Structured multi-agent debate", "title": "MAD: Multi-Agent Debate with Large Language Models", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Gao et al.", "id": 369, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AgentScope%3A%20A%20Flexible%20yet%20Robust%20Multi-Agent%20Platform&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AgentScope%3A%20A%20Flexible%20yet%20Robust%20Multi-Agent%20Platform%20Gao%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=AgentScope%3A%20A%20Flexible%20yet%20Robust%20Multi-Agent%20Platform&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "Scalable agent platform", "title": "AgentScope: A Flexible yet Robust Multi-Agent Platform", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Jiang et al.", "id": 370, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLM-Blender%3A%20Ensembling%20LLMs%20with%20Pairwise%20Ranking&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLM-Blender%3A%20Ensembling%20LLMs%20with%20Pairwise%20Ranking%20Jiang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLM-Blender%3A%20Ensembling%20LLMs%20with%20Pairwise%20Ranking&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 18, "section_title": "Multi-Agent Systems", "source_note": "Ensemble multiple LLMs", "title": "LLM-Blender: Ensembling LLMs with Pairwise Ranking", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Chen et al.", "id": 371, "links": { "canonical_url": "https://arxiv.org/abs/2107.03374", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2107.03374.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Evaluating%20Large%20Language%20Models%20Trained%20on%20Code%20%28Codex%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Evaluating%20Large%20Language%20Models%20Trained%20on%20Code%20%28Codex%29%20Chen%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Evaluating%20Large%20Language%20Models%20Trained%20on%20Code%20%28Codex%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2107.03374.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Codex / GitHub Copilot", "title": "Evaluating Large Language Models Trained on Code (Codex)", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Chen et al.", "id": 372, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=HumanEval&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=HumanEval%20Chen%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=HumanEval&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Code generation benchmark", "title": "HumanEval", "work_type": "Benchmark or dataset paper", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Nijkamp et al.", "id": 373, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=CodeGen%3A%20An%20Open%20Large%20Language%20Model%20for%20Code&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=CodeGen%3A%20An%20Open%20Large%20Language%20Model%20for%20Code%20Nijkamp%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=CodeGen%3A%20An%20Open%20Large%20Language%20Model%20for%20Code&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Open code generation", "title": "CodeGen: An Open Large Language Model for Code", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Li et al.", "id": 374, "links": { "canonical_url": "https://arxiv.org/abs/2305.06161", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.06161.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=StarCoder%3A%20May%20the%20Source%20Be%20with%20You%21&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=StarCoder%3A%20May%20the%20Source%20Be%20with%20You%21%20Li%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=StarCoder%3A%20May%20the%20Source%20Be%20with%20You%21&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.06161.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Open source code model", "title": "StarCoder: May the Source Be with You!", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Lozhkov et al.", "id": 375, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=StarCoder%202&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=StarCoder%202%20Lozhkov%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=StarCoder%202&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Improved StarCoder", "title": "StarCoder 2", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Rozière et al.", "id": 376, "links": { "canonical_url": "https://arxiv.org/abs/2308.12950", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2308.12950.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Code%20Llama%3A%20Open%20Foundation%20Models%20for%20Code&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Code%20Llama%3A%20Open%20Foundation%20Models%20for%20Code%20Rozi%C3%A8re%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Code%20Llama%3A%20Open%20Foundation%20Models%20for%20Code&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2308.12950.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Meta's code LLM", "title": "Code Llama: Open Foundation Models for Code", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Guo et al.", "id": 377, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeepSeek-Coder&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeepSeek-Coder%20Guo%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeepSeek-Coder&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Competitive code model", "title": "DeepSeek-Coder", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Luo et al.", "id": 378, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=WizardCoder%3A%20Empowering%20Code%20LLMs%20with%20Evol-Instruct&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=WizardCoder%3A%20Empowering%20Code%20LLMs%20with%20Evol-Instruct%20Luo%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=WizardCoder%3A%20Empowering%20Code%20LLMs%20with%20Evol-Instruct&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Evolved instructions for code", "title": "WizardCoder: Empowering Code LLMs with Evol-Instruct", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Jimenez et al.", "id": 379, "links": { "canonical_url": "https://arxiv.org/abs/2310.06770", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2310.06770.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SWE-bench%3A%20Can%20Language%20Models%20Resolve%20Real-World%20GitHub%20Issues%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SWE-bench%3A%20Can%20Language%20Models%20Resolve%20Real-World%20GitHub%20Issues%3F%20Jimenez%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=SWE-bench%3A%20Can%20Language%20Models%20Resolve%20Real-World%20GitHub%20Issues%3F&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2310.06770.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Real-world SWE benchmark", "title": "SWE-bench: Can Language Models Resolve Real-World GitHub Issues?", "work_type": "Benchmark or dataset paper", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Yang et al.", "id": 380, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SWE-Agent&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SWE-Agent%20Yang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=SWE-Agent&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Agent for SWE-bench", "title": "SWE-Agent", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Cognition", "id": 381, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Devin%3A%20AI%20Software%20Engineer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Devin%3A%20AI%20Software%20Engineer%20Cognition%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Devin%3A%20AI%20Software%20Engineer&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Autonomous coding agent", "title": "Devin: AI Software Engineer", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Wang et al.", "id": 382, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=OpenDevin%20/%20OpenHands&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=OpenDevin%20/%20OpenHands%20Wang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=OpenDevin%20/%20OpenHands&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Open-source Devin alternative", "title": "OpenDevin / OpenHands", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Gauthier", "id": 383, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Aider%3A%20AI%20Pair%20Programming%20in%20Terminal&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Aider%3A%20AI%20Pair%20Programming%20in%20Terminal%20Gauthier%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Aider%3A%20AI%20Pair%20Programming%20in%20Terminal&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Terminal-based AI coding", "title": "Aider: AI Pair Programming in Terminal", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Anthropic", "id": 384, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Claude%20Code%20%28Anthropic%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Claude%20Code%20%28Anthropic%29%20Anthropic%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Claude%20Code%20%28Anthropic%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "CLI agentic coding tool", "title": "Claude Code (Anthropic)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Li et al.", "id": 385, "links": { "canonical_url": "https://arxiv.org/abs/2203.07814", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2203.07814.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AlphaCode%3A%20Competition-Level%20Code%20Generation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AlphaCode%3A%20Competition-Level%20Code%20Generation%20Li%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=AlphaCode%3A%20Competition-Level%20Code%20Generation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2203.07814.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Competitive programming", "title": "AlphaCode: Competition-Level Code Generation", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Google DeepMind", "id": 386, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AlphaCode%202&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AlphaCode%202%20Google%20DeepMind%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=AlphaCode%202&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Improved competitive coding", "title": "AlphaCode 2", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Chen et al.", "id": 387, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=CodeT%3A%20Code%20Generation%20with%20Generated%20Tests&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=CodeT%3A%20Code%20Generation%20with%20Generated%20Tests%20Chen%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=CodeT%3A%20Code%20Generation%20with%20Generated%20Tests&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Test-driven code generation", "title": "CodeT: Code Generation with Generated Tests", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Chen et al.", "id": 388, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Self-Debugging%3A%20Teaching%20LLMs%20to%20Self-Debug&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Self-Debugging%3A%20Teaching%20LLMs%20to%20Self-Debug%20Chen%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Self-Debugging%3A%20Teaching%20LLMs%20to%20Self-Debug&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Self-debugging code", "title": "Self-Debugging: Teaching LLMs to Self-Debug", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Austin et al.", "id": 389, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MBPP%3A%20Mostly%20Basic%20Python%20Programming&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MBPP%3A%20Mostly%20Basic%20Python%20Programming%20Austin%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=MBPP%3A%20Mostly%20Basic%20Python%20Programming&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Python code benchmark", "title": "MBPP: Mostly Basic Python Programming", "work_type": "Benchmark or dataset paper", "year": 2021, "year_display": "2021" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 390, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Repository-Level%20Code%20Completion&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Repository-Level%20Code%20Completion%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Repository-Level%20Code%20Completion&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 19, "section_title": "Code Generation & Software Engineering Agents", "source_note": "Repo-level context for code", "title": "Repository-Level Code Completion", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "non_paper_or_multi_work", "message": "Two book editions are combined; the importer requires a single four-digit year.", "required_action": "Select and cite one edition or create two typed book records.", "severity": "blocking" } ], "authors": "Sutton & Barto", "id": 391, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Reinforcement%20Learning%3A%20An%20Introduction&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Reinforcement%20Learning%3A%20An%20Introduction%20Sutton%201998/2018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Reinforcement%20Learning%3A%20An%20Introduction&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 20, "section_title": "Reinforcement Learning Foundations", "source_note": "RL textbook", "title": "Reinforcement Learning: An Introduction", "work_type": "Book or textbook", "year": 1998, "year_display": "1998/2018" }, { "audit_flags": [], "authors": "Watkins & Dayan", "id": 392, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Q-Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Q-Learning%20Watkins%201992", "semantic_scholar": "https://www.semanticscholar.org/search?q=Q-Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 20, "section_title": "Reinforcement Learning Foundations", "source_note": "Q-learning algorithm", "title": "Q-Learning", "work_type": "Research-paper candidate", "year": 1992, "year_display": "1992" }, { "audit_flags": [], "authors": "Sutton et al.", "id": 393, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Policy%20Gradient%20Methods%20for%20RL%20with%20Function%20Approximation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Policy%20Gradient%20Methods%20for%20RL%20with%20Function%20Approximation%20Sutton%202000", "semantic_scholar": "https://www.semanticscholar.org/search?q=Policy%20Gradient%20Methods%20for%20RL%20with%20Function%20Approximation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 20, "section_title": "Reinforcement Learning Foundations", "source_note": "Policy gradient theorem", "title": "Policy Gradient Methods for RL with Function Approximation", "work_type": "Research-paper candidate", "year": 2000, "year_display": "2000" }, { "audit_flags": [], "authors": "Konda & Tsitsiklis", "id": 394, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Actor-Critic%20Algorithms&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Actor-Critic%20Algorithms%20Konda%202000", "semantic_scholar": "https://www.semanticscholar.org/search?q=Actor-Critic%20Algorithms&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 20, "section_title": "Reinforcement Learning Foundations", "source_note": "Actor-critic framework", "title": "Actor-Critic Algorithms", "work_type": "Research-paper candidate", "year": 2000, "year_display": "2000" }, { "audit_flags": [], "authors": "Williams", "id": 395, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Simple%20Statistical%20Gradient-Following%20Algorithms%20%28REINFORCE%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Simple%20Statistical%20Gradient-Following%20Algorithms%20%28REINFORCE%29%20Williams%201992", "semantic_scholar": "https://www.semanticscholar.org/search?q=Simple%20Statistical%20Gradient-Following%20Algorithms%20%28REINFORCE%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 20, "section_title": "Reinforcement Learning Foundations", "source_note": "REINFORCE algorithm", "title": "Simple Statistical Gradient-Following Algorithms (REINFORCE)", "work_type": "Research-paper candidate", "year": 1992, "year_display": "1992" }, { "audit_flags": [], "authors": "Sutton", "id": 396, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Temporal-Difference%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Temporal-Difference%20Learning%20Sutton%201988", "semantic_scholar": "https://www.semanticscholar.org/search?q=Temporal-Difference%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 20, "section_title": "Reinforcement Learning Foundations", "source_note": "TD learning", "title": "Temporal-Difference Learning", "work_type": "Research-paper candidate", "year": 1988, "year_display": "1988" }, { "audit_flags": [], "authors": "Sutton, Precup, Singh", "id": 397, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Between%20MDPs%20and%20semi-MDPs%3A%20A%20Framework%20for%20Temporal%20Abstraction%20%28Options%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Between%20MDPs%20and%20semi-MDPs%3A%20A%20Framework%20for%20Temporal%20Abstraction%20%28Options%29%20Sutton%201999", "semantic_scholar": "https://www.semanticscholar.org/search?q=Between%20MDPs%20and%20semi-MDPs%3A%20A%20Framework%20for%20Temporal%20Abstraction%20%28Options%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 20, "section_title": "Reinforcement Learning Foundations", "source_note": "Hierarchical RL — options", "title": "Between MDPs and semi-MDPs: A Framework for Temporal Abstraction (Options)", "work_type": "Research-paper candidate", "year": 1999, "year_display": "1999" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 398, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Multi-Agent%20Reinforcement%20Learning%3A%20A%20Selective%20Overview&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Multi-Agent%20Reinforcement%20Learning%3A%20A%20Selective%20Overview%20Zhang%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Multi-Agent%20Reinforcement%20Learning%3A%20A%20Selective%20Overview&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 20, "section_title": "Reinforcement Learning Foundations", "source_note": "MARL survey", "title": "Multi-Agent Reinforcement Learning: A Selective Overview", "work_type": "Survey or review", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Ng, Harada, Russell", "id": 399, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Reward%20Shaping&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Reward%20Shaping%20Ng%201999", "semantic_scholar": "https://www.semanticscholar.org/search?q=Reward%20Shaping&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 20, "section_title": "Reinforcement Learning Foundations", "source_note": "Potential-based reward shaping", "title": "Reward Shaping", "work_type": "Research-paper candidate", "year": 1999, "year_display": "1999" }, { "audit_flags": [ { "code": "non_paper_or_multi_work", "message": "A topic label rather than a uniquely identifiable publication.", "required_action": "Replace with one or more canonical exploration-exploitation papers.", "severity": "blocking" } ], "authors": "various", "id": 400, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Exploration%20and%20Exploitation%20in%20RL&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Exploration%20and%20Exploitation%20in%20RL%20various%202000s", "semantic_scholar": "https://www.semanticscholar.org/search?q=Exploration%20and%20Exploitation%20in%20RL&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 20, "section_title": "Reinforcement Learning Foundations", "source_note": "Explore-exploit tradeoff", "title": "Exploration and Exploitation in RL", "work_type": "Research-paper candidate", "year": 2000, "year_display": "2000s" }, { "audit_flags": [], "authors": "Mnih et al.", "id": 401, "links": { "canonical_url": "https://arxiv.org/abs/1312.5602", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1312.5602.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Playing%20Atari%20with%20Deep%20Reinforcement%20Learning%20%28DQN%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Playing%20Atari%20with%20Deep%20Reinforcement%20Learning%20%28DQN%29%20Mnih%202013", "semantic_scholar": "https://www.semanticscholar.org/search?q=Playing%20Atari%20with%20Deep%20Reinforcement%20Learning%20%28DQN%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1312.5602.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "**Deep Q-Network**", "title": "Playing Atari with Deep Reinforcement Learning (DQN)", "work_type": "Research-paper candidate", "year": 2013, "year_display": "2013" }, { "audit_flags": [], "authors": "Mnih et al.", "id": 402, "links": { "canonical_url": "https://www.nature.com/articles/nature14236", "corrected_by_audit": false, "direct_url": "https://www.nature.com/articles/nature14236", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Human-Level%20Control%20through%20Deep%20RL%20%28DQN%20Nature%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Human-Level%20Control%20through%20Deep%20RL%20%28DQN%20Nature%29%20Mnih%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Human-Level%20Control%20through%20Deep%20RL%20%28DQN%20Nature%29&sort=relevance" }, "supplied_direct_url": "https://www.nature.com/articles/nature14236" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "DQN in Nature", "title": "Human-Level Control through Deep RL (DQN Nature)", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "van Hasselt et al.", "id": 403, "links": { "canonical_url": "https://arxiv.org/abs/1509.06461", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1509.06461.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Deep%20Reinforcement%20Learning%20with%20Double%20Q-Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Deep%20Reinforcement%20Learning%20with%20Double%20Q-Learning%20van%20Hasselt%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Deep%20Reinforcement%20Learning%20with%20Double%20Q-Learning&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1509.06461.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "Double DQN", "title": "Deep Reinforcement Learning with Double Q-Learning", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Schaul et al.", "id": 404, "links": { "canonical_url": "https://arxiv.org/abs/1511.05952", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1511.05952.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Prioritized%20Experience%20Replay&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Prioritized%20Experience%20Replay%20Schaul%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Prioritized%20Experience%20Replay&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1511.05952.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "Priority-based replay buffer", "title": "Prioritized Experience Replay", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Wang et al.", "id": 405, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Dueling%20Network%20Architectures%20for%20Deep%20RL&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Dueling%20Network%20Architectures%20for%20Deep%20RL%20Wang%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Dueling%20Network%20Architectures%20for%20Deep%20RL&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "Dueling DQN", "title": "Dueling Network Architectures for Deep RL", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Mnih et al.", "id": 406, "links": { "canonical_url": "https://arxiv.org/abs/1602.01783", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1602.01783.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Asynchronous%20Methods%20for%20Deep%20RL%20%28A3C%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Asynchronous%20Methods%20for%20Deep%20RL%20%28A3C%29%20Mnih%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Asynchronous%20Methods%20for%20Deep%20RL%20%28A3C%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1602.01783.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "A3C — parallel RL", "title": "Asynchronous Methods for Deep RL (A3C)", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Lillicrap et al.", "id": 407, "links": { "canonical_url": "https://arxiv.org/abs/1509.02971", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1509.02971.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Continuous%20Control%20with%20Deep%20RL%20%28DDPG%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Continuous%20Control%20with%20Deep%20RL%20%28DDPG%29%20Lillicrap%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Continuous%20Control%20with%20Deep%20RL%20%28DDPG%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1509.02971.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "Deep deterministic policy gradient", "title": "Continuous Control with Deep RL (DDPG)", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Schulman et al.", "id": 408, "links": { "canonical_url": "https://arxiv.org/abs/1502.05477", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1502.05477.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Trust%20Region%20Policy%20Optimization%20%28TRPO%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Trust%20Region%20Policy%20Optimization%20%28TRPO%29%20Schulman%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Trust%20Region%20Policy%20Optimization%20%28TRPO%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1502.05477.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "TRPO", "title": "Trust Region Policy Optimization (TRPO)", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Schulman et al.", "id": 409, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=High-Dimensional%20Continuous%20Control%20Using%20Generalized%20Advantage%20Estimation%20%28GAE%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=High-Dimensional%20Continuous%20Control%20Using%20Generalized%20Advantage%20Estimation%20%28GAE%29%20Schulman%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=High-Dimensional%20Continuous%20Control%20Using%20Generalized%20Advantage%20Estimation%20%28GAE%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "GAE for variance reduction", "title": "High-Dimensional Continuous Control Using Generalized Advantage Estimation (GAE)", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Haarnoja et al.", "id": 410, "links": { "canonical_url": "https://arxiv.org/abs/1801.01290", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1801.01290.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Soft%20Actor-Critic%20%28SAC%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Soft%20Actor-Critic%20%28SAC%29%20Haarnoja%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Soft%20Actor-Critic%20%28SAC%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1801.01290.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "Maximum entropy RL", "title": "Soft Actor-Critic (SAC)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Silver et al.", "id": 411, "links": { "canonical_url": "https://www.nature.com/articles/nature16961", "corrected_by_audit": false, "direct_url": "https://www.nature.com/articles/nature16961", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mastering%20the%20Game%20of%20Go%20with%20Deep%20Neural%20Networks%20%28AlphaGo%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mastering%20the%20Game%20of%20Go%20with%20Deep%20Neural%20Networks%20%28AlphaGo%29%20Silver%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mastering%20the%20Game%20of%20Go%20with%20Deep%20Neural%20Networks%20%28AlphaGo%29&sort=relevance" }, "supplied_direct_url": "https://www.nature.com/articles/nature16961" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "**AlphaGo**", "title": "Mastering the Game of Go with Deep Neural Networks (AlphaGo)", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Silver et al.", "id": 412, "links": { "canonical_url": "https://www.nature.com/articles/nature24270", "corrected_by_audit": false, "direct_url": "https://www.nature.com/articles/nature24270", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mastering%20Go%20without%20Human%20Knowledge%20%28AlphaGo%20Zero%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mastering%20Go%20without%20Human%20Knowledge%20%28AlphaGo%20Zero%29%20Silver%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mastering%20Go%20without%20Human%20Knowledge%20%28AlphaGo%20Zero%29&sort=relevance" }, "supplied_direct_url": "https://www.nature.com/articles/nature24270" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "Self-play from scratch", "title": "Mastering Go without Human Knowledge (AlphaGo Zero)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Silver et al.", "id": 413, "links": { "canonical_url": "https://arxiv.org/abs/1712.01815", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1712.01815.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20General%20RL%20Algorithm%20that%20Masters%20Chess%2C%20Shogi%2C%20and%20Go%20%28AlphaZero%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20General%20RL%20Algorithm%20that%20Masters%20Chess%2C%20Shogi%2C%20and%20Go%20%28AlphaZero%29%20Silver%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20General%20RL%20Algorithm%20that%20Masters%20Chess%2C%20Shogi%2C%20and%20Go%20%28AlphaZero%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1712.01815.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "General game-playing", "title": "A General RL Algorithm that Masters Chess, Shogi, and Go (AlphaZero)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Schrittwieser et al.", "id": 414, "links": { "canonical_url": "https://arxiv.org/abs/1911.08265", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1911.08265.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MuZero%3A%20Mastering%20Atari%2C%20Go%2C%20Chess%20and%20Shogi%20by%20Planning%20with%20a%20Learned%20Model&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MuZero%3A%20Mastering%20Atari%2C%20Go%2C%20Chess%20and%20Shogi%20by%20Planning%20with%20a%20Learned%20Model%20Schrittwieser%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=MuZero%3A%20Mastering%20Atari%2C%20Go%2C%20Chess%20and%20Shogi%20by%20Planning%20with%20a%20Learned%20Model&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1911.08265.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "Model-based + model-free", "title": "MuZero: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "OpenAI", "id": 415, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=OpenAI%20Five&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=OpenAI%20Five%20OpenAI%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=OpenAI%20Five&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "Dota 2 team-play", "title": "OpenAI Five", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Vinyals et al.", "id": 416, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AlphaStar%3A%20Mastering%20StarCraft%20II&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AlphaStar%3A%20Mastering%20StarCraft%20II%20Vinyals%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=AlphaStar%3A%20Mastering%20StarCraft%20II&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "StarCraft grand-master level", "title": "AlphaStar: Mastering StarCraft II", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Pathak et al.", "id": 417, "links": { "canonical_url": "https://arxiv.org/abs/1705.05363", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1705.05363.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Curiosity-Driven%20Exploration%20%28ICM%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Curiosity-Driven%20Exploration%20%28ICM%29%20Pathak%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Curiosity-Driven%20Exploration%20%28ICM%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1705.05363.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "Intrinsic motivation", "title": "Curiosity-Driven Exploration (ICM)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 691 ], "severity": "warning" } ], "authors": "Ha & Schmidhuber", "id": 418, "links": { "canonical_url": "https://arxiv.org/abs/1803.10122", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1803.10122.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=World%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=World%20Models%20Ha%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=World%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1803.10122.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "Learn world model, plan in latent space", "title": "World Models", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Hafner et al.", "id": 419, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Dream%20to%20Control%20%28Dreamer%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Dream%20to%20Control%20%28Dreamer%29%20Hafner%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Dream%20to%20Control%20%28Dreamer%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "Model-based latent imagination", "title": "Dream to Control (Dreamer)", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Hafner et al.", "id": 420, "links": { "canonical_url": "https://arxiv.org/abs/2301.04104", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2301.04104.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DreamerV3%3A%20Mastering%20Diverse%20Domains%20through%20World%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DreamerV3%3A%20Mastering%20Diverse%20Domains%20through%20World%20Models%20Hafner%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=DreamerV3%3A%20Mastering%20Diverse%20Domains%20through%20World%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2301.04104.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 21, "section_title": "Deep Reinforcement Learning", "source_note": "General world model RL", "title": "DreamerV3: Mastering Diverse Domains through World Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Srivastava & Salakhutdinov", "id": 421, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Multimodal%20Learning%20with%20Deep%20Boltzmann%20Machines&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Multimodal%20Learning%20with%20Deep%20Boltzmann%20Machines%20Srivastava%202012", "semantic_scholar": "https://www.semanticscholar.org/search?q=Multimodal%20Learning%20with%20Deep%20Boltzmann%20Machines&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "Early multimodal learning", "title": "Multimodal Learning with Deep Boltzmann Machines", "work_type": "Research-paper candidate", "year": 2012, "year_display": "2012" }, { "audit_flags": [], "authors": "Antol et al.", "id": 422, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Visual%20Question%20Answering%20%28VQA%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Visual%20Question%20Answering%20%28VQA%29%20Antol%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Visual%20Question%20Answering%20%28VQA%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "VQA task and dataset", "title": "Visual Question Answering (VQA)", "work_type": "Benchmark or dataset paper", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Lu et al.", "id": 423, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ViLBERT%3A%20Pretraining%20Task-Agnostic%20Visiolinguistic%20Representations&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ViLBERT%3A%20Pretraining%20Task-Agnostic%20Visiolinguistic%20Representations%20Lu%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=ViLBERT%3A%20Pretraining%20Task-Agnostic%20Visiolinguistic%20Representations&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "Two-stream vision-language", "title": "ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Tan & Bansal", "id": 424, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LXMERT%3A%20Learning%20Cross-Modality%20Encoder%20Representations&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LXMERT%3A%20Learning%20Cross-Modality%20Encoder%20Representations%20Tan%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=LXMERT%3A%20Learning%20Cross-Modality%20Encoder%20Representations&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "Cross-modality pretraining", "title": "LXMERT: Learning Cross-Modality Encoder Representations", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Li et al.", "id": 425, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Oscar%3A%20Object-Semantics%20Aligned%20Pre-training&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Oscar%3A%20Object-Semantics%20Aligned%20Pre-training%20Li%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Oscar%3A%20Object-Semantics%20Aligned%20Pre-training&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "Object tags for VL alignment", "title": "Oscar: Object-Semantics Aligned Pre-training", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Chen et al.", "id": 426, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=UNITER%3A%20Universal%20Image-Text%20Representation%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=UNITER%3A%20Universal%20Image-Text%20Representation%20Learning%20Chen%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=UNITER%3A%20Universal%20Image-Text%20Representation%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "Unified VL pretraining", "title": "UNITER: Universal Image-Text Representation Learning", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 427, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=VinVL%3A%20Revisiting%20Visual%20Representations%20in%20VL%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=VinVL%3A%20Revisiting%20Visual%20Representations%20in%20VL%20Models%20Zhang%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=VinVL%3A%20Revisiting%20Visual%20Representations%20in%20VL%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "Better visual features for VL", "title": "VinVL: Revisiting Visual Representations in VL Models", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Jaegle et al.", "id": 428, "links": { "canonical_url": "https://arxiv.org/abs/2103.03206", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2103.03206.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Perceiver%3A%20General%20Perception%20with%20Iterative%20Attention&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Perceiver%3A%20General%20Perception%20with%20Iterative%20Attention%20Jaegle%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Perceiver%3A%20General%20Perception%20with%20Iterative%20Attention&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2103.03206.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "Modality-agnostic architecture", "title": "Perceiver: General Perception with Iterative Attention", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Jaegle et al.", "id": 429, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Perceiver%20IO&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Perceiver%20IO%20Jaegle%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Perceiver%20IO&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "Generalized multimodal IO", "title": "Perceiver IO", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Baevski et al.", "id": 430, "links": { "canonical_url": "https://arxiv.org/abs/2202.03555", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2202.03555.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Data2Vec%3A%20A%20General%20Framework%20for%20Self-Supervised%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Data2Vec%3A%20A%20General%20Framework%20for%20Self-Supervised%20Learning%20Baevski%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Data2Vec%3A%20A%20General%20Framework%20for%20Self-Supervised%20Learning&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2202.03555.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "Unified self-supervised across modalities", "title": "Data2Vec: A General Framework for Self-Supervised Learning", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Girdhar et al.", "id": 431, "links": { "canonical_url": "https://arxiv.org/abs/2305.05665", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.05665.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ImageBind%3A%20One%20Embedding%20Space%20to%20Bind%20Them%20All&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ImageBind%3A%20One%20Embedding%20Space%20to%20Bind%20Them%20All%20Girdhar%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=ImageBind%3A%20One%20Embedding%20Space%20to%20Bind%20Them%20All&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.05665.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "Six-modality binding", "title": "ImageBind: One Embedding Space to Bind Them All", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 432, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Meta-Transformer%3A%20A%20Unified%20Framework%20for%20Multimodal%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Meta-Transformer%3A%20A%20Unified%20Framework%20for%20Multimodal%20Learning%20Zhang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Meta-Transformer%3A%20A%20Unified%20Framework%20for%20Multimodal%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "12-modality transformer", "title": "Meta-Transformer: A Unified Framework for Multimodal Learning", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Tang et al.", "id": 433, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Any-to-Any%20Generation%20via%20Composable%20Diffusion%20%28CoDi%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Any-to-Any%20Generation%20via%20Composable%20Diffusion%20%28CoDi%29%20Tang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Any-to-Any%20Generation%20via%20Composable%20Diffusion%20%28CoDi%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "Cross-modal generation", "title": "Any-to-Any Generation via Composable Diffusion (CoDi)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Wu et al.", "id": 434, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=NExT-GPT%3A%20Any-to-Any%20Multimodal%20LLM&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=NExT-GPT%3A%20Any-to-Any%20Multimodal%20LLM%20Wu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=NExT-GPT%3A%20Any-to-Any%20Multimodal%20LLM&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "End-to-end multimodal generation", "title": "NExT-GPT: Any-to-Any Multimodal LLM", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Bachmann et al.", "id": 435, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=4M%3A%20Massively%20Multimodal%20Masked%20Modeling&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=4M%3A%20Massively%20Multimodal%20Masked%20Modeling%20Bachmann%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=4M%3A%20Massively%20Multimodal%20Masked%20Modeling&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 22, "section_title": "Multimodal AI", "source_note": "Multi-task multimodal pretraining", "title": "4M: Massively Multimodal Masked Modeling", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Radford et al.", "id": 436, "links": { "canonical_url": "https://arxiv.org/abs/2103.00020", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2103.00020.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=CLIP%3A%20Learning%20Transferable%20Visual%20Models%20from%20Natural%20Language%20Supervision&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=CLIP%3A%20Learning%20Transferable%20Visual%20Models%20from%20Natural%20Language%20Supervision%20Radford%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=CLIP%3A%20Learning%20Transferable%20Visual%20Models%20from%20Natural%20Language%20Supervision&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2103.00020.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "**Contrastive language-image pretraining**", "title": "CLIP: Learning Transferable Visual Models from Natural Language Supervision", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Jia et al.", "id": 437, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ALIGN%3A%20Scaling%20Up%20Visual%20and%20Vision-Language%20Representation%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ALIGN%3A%20Scaling%20Up%20Visual%20and%20Vision-Language%20Representation%20Learning%20Jia%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=ALIGN%3A%20Scaling%20Up%20Visual%20and%20Vision-Language%20Representation%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Noisy image-text pairs at scale", "title": "ALIGN: Scaling Up Visual and Vision-Language Representation Learning", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Yuan et al.", "id": 438, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Florence%3A%20A%20New%20Foundation%20Model%20for%20Computer%20Vision&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Florence%3A%20A%20New%20Foundation%20Model%20for%20Computer%20Vision%20Yuan%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Florence%3A%20A%20New%20Foundation%20Model%20for%20Computer%20Vision&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Unified vision foundation", "title": "Florence: A New Foundation Model for Computer Vision", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Alayrac et al.", "id": 439, "links": { "canonical_url": "https://arxiv.org/abs/2204.14198", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2204.14198.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Flamingo%3A%20A%20Visual%20Language%20Model%20for%20Few-Shot%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Flamingo%3A%20A%20Visual%20Language%20Model%20for%20Few-Shot%20Learning%20Alayrac%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Flamingo%3A%20A%20Visual%20Language%20Model%20for%20Few-Shot%20Learning&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2204.14198.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Few-shot VL model", "title": "Flamingo: A Visual Language Model for Few-Shot Learning", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Li et al.", "id": 440, "links": { "canonical_url": "https://arxiv.org/abs/2201.12086", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2201.12086.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BLIP%3A%20Bootstrapping%20Language-Image%20Pre-training&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BLIP%3A%20Bootstrapping%20Language-Image%20Pre-training%20Li%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=BLIP%3A%20Bootstrapping%20Language-Image%20Pre-training&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2201.12086.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Bootstrapped VL pretraining", "title": "BLIP: Bootstrapping Language-Image Pre-training", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Li et al.", "id": 441, "links": { "canonical_url": "https://arxiv.org/abs/2301.12597", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2301.12597.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BLIP-2%3A%20Bootstrapping%20Language-Image%20Pre-training%20with%20Frozen%20Image%20Encoders%20and%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BLIP-2%3A%20Bootstrapping%20Language-Image%20Pre-training%20with%20Frozen%20Image%20Encoders%20and%20LLMs%20Li%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=BLIP-2%3A%20Bootstrapping%20Language-Image%20Pre-training%20with%20Frozen%20Image%20Encoders%20and%20LLMs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2301.12597.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Q-Former for vision-language", "title": "BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and LLMs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Liu et al.", "id": 442, "links": { "canonical_url": "https://arxiv.org/abs/2304.08485", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2304.08485.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLaVA%3A%20Visual%20Instruction%20Tuning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLaVA%3A%20Visual%20Instruction%20Tuning%20Liu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLaVA%3A%20Visual%20Instruction%20Tuning&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2304.08485.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Visual instruction following", "title": "LLaVA: Visual Instruction Tuning", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Liu et al.", "id": 443, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLaVA-1.5&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLaVA-1.5%20Liu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLaVA-1.5&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Improved visual chat", "title": "LLaVA-1.5", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Dai et al.", "id": 444, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=InstructBLIP&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=InstructBLIP%20Dai%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=InstructBLIP&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Instruction-tuned BLIP-2", "title": "InstructBLIP", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zhu et al.", "id": 445, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MiniGPT-4%3A%20Enhancing%20Vision-Language%20Understanding&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MiniGPT-4%3A%20Enhancing%20Vision-Language%20Understanding%20Zhu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=MiniGPT-4%3A%20Enhancing%20Vision-Language%20Understanding&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "GPT-4 vision abilities in small model", "title": "MiniGPT-4: Enhancing Vision-Language Understanding", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Bai et al.", "id": 446, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Qwen-VL%3A%20A%20Versatile%20VLM&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Qwen-VL%3A%20A%20Versatile%20VLM%20Bai%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Qwen-VL%3A%20A%20Versatile%20VLM&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Versatile VLM", "title": "Qwen-VL: A Versatile VLM", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Wang et al.", "id": 447, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=CogVLM%3A%20Visual%20Expert%20for%20Pretrained%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=CogVLM%3A%20Visual%20Expert%20for%20Pretrained%20Language%20Models%20Wang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=CogVLM%3A%20Visual%20Expert%20for%20Pretrained%20Language%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Deep visual-language fusion", "title": "CogVLM: Visual Expert for Pretrained Language Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Chen et al.", "id": 448, "links": { "canonical_url": "https://arxiv.org/abs/2312.14238", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2312.14238.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=InternVL%3A%20Scaling%20Up%20Vision%20Foundation%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=InternVL%3A%20Scaling%20Up%20Vision%20Foundation%20Models%20Chen%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=InternVL%3A%20Scaling%20Up%20Vision%20Foundation%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2312.14238.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Scaling VL models", "title": "InternVL: Scaling Up Vision Foundation Models", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Tong et al.", "id": 449, "links": { "canonical_url": "https://arxiv.org/abs/2406.16860", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2406.16860.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Cambrian-1%3A%20A%20Fully%20Open%20Vision-Centric%20Exploration%20of%20Multimodal%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Cambrian-1%3A%20A%20Fully%20Open%20Vision-Centric%20Exploration%20of%20Multimodal%20LLMs%20Tong%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Cambrian-1%3A%20A%20Fully%20Open%20Vision-Centric%20Exploration%20of%20Multimodal%20LLMs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2406.16860.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Open multimodal exploration", "title": "Cambrian-1: A Fully Open Vision-Centric Exploration of Multimodal LLMs", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zhai et al.", "id": 450, "links": { "canonical_url": "https://arxiv.org/abs/2303.15343", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2303.15343.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SigLIP%3A%20Sigmoid%20Loss%20for%20Language%20Image%20Pre-Training&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SigLIP%3A%20Sigmoid%20Loss%20for%20Language%20Image%20Pre-Training%20Zhai%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=SigLIP%3A%20Sigmoid%20Loss%20for%20Language%20Image%20Pre-Training&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2303.15343.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Simplified contrastive VL", "title": "SigLIP: Sigmoid Loss for Language Image Pre-Training", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Kirillov et al.", "id": 451, "links": { "canonical_url": "https://arxiv.org/abs/2304.02643", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2304.02643.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SAM%3A%20Segment%20Anything&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SAM%3A%20Segment%20Anything%20Kirillov%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=SAM%3A%20Segment%20Anything&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2304.02643.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Foundation model for segmentation", "title": "SAM: Segment Anything", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Ravi et al.", "id": 452, "links": { "canonical_url": "https://arxiv.org/abs/2408.00714", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2408.00714.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SAM%202%3A%20Segment%20Anything%20in%20Images%20and%20Videos&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SAM%202%3A%20Segment%20Anything%20in%20Images%20and%20Videos%20Ravi%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=SAM%202%3A%20Segment%20Anything%20in%20Images%20and%20Videos&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2408.00714.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Video segmentation foundation", "title": "SAM 2: Segment Anything in Images and Videos", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Liu et al.", "id": 453, "links": { "canonical_url": "https://arxiv.org/abs/2303.05499", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2303.05499.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Grounding%20DINO%3A%20Marrying%20DINO%20with%20Grounded%20Pre-Training&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Grounding%20DINO%3A%20Marrying%20DINO%20with%20Grounded%20Pre-Training%20Liu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Grounding%20DINO%3A%20Marrying%20DINO%20with%20Grounded%20Pre-Training&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2303.05499.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Open-set object detection", "title": "Grounding DINO: Marrying DINO with Grounded Pre-Training", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Minderer et al.", "id": 454, "links": { "canonical_url": "https://arxiv.org/abs/2205.06230", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2205.06230.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=OWL-ViT%3A%20Open-World%20Object%20Detection%20with%20Vision%20Transformers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=OWL-ViT%3A%20Open-World%20Object%20Detection%20with%20Vision%20Transformers%20Minderer%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=OWL-ViT%3A%20Open-World%20Object%20Detection%20with%20Vision%20Transformers&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2205.06230.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Open-vocabulary detection", "title": "OWL-ViT: Open-World Object Detection with Vision Transformers", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Chen et al.", "id": 455, "links": { "canonical_url": "https://arxiv.org/abs/2209.06794", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2209.06794.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=PaLI%3A%20A%20Jointly-Scaled%20Multilingual%20Language-Image%20Model&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=PaLI%3A%20A%20Jointly-Scaled%20Multilingual%20Language-Image%20Model%20Chen%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=PaLI%3A%20A%20Jointly-Scaled%20Multilingual%20Language-Image%20Model&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2209.06794.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 23, "section_title": "Vision-Language Models", "source_note": "Multilingual VL model", "title": "PaLI: A Jointly-Scaled Multilingual Language-Image Model", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Hannun et al.", "id": 456, "links": { "canonical_url": "https://arxiv.org/abs/1412.5567", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1412.5567.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Deep%20Speech%3A%20Scaling%20Up%20End-to-End%20Speech%20Recognition&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Deep%20Speech%3A%20Scaling%20Up%20End-to-End%20Speech%20Recognition%20Hannun%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Deep%20Speech%3A%20Scaling%20Up%20End-to-End%20Speech%20Recognition&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1412.5567.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "End-to-end ASR", "title": "Deep Speech: Scaling Up End-to-End Speech Recognition", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Amodei et al.", "id": 457, "links": { "canonical_url": "https://arxiv.org/abs/1512.02595", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1512.02595.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Deep%20Speech%202&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Deep%20Speech%202%20Amodei%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Deep%20Speech%202&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1512.02595.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "English + Mandarin ASR", "title": "Deep Speech 2", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Chan et al.", "id": 458, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Listen%2C%20Attend%20and%20Spell%20%28LAS%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Listen%2C%20Attend%20and%20Spell%20%28LAS%29%20Chan%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Listen%2C%20Attend%20and%20Spell%20%28LAS%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Attention-based ASR", "title": "Listen, Attend and Spell (LAS)", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Schneider et al.", "id": 459, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=wav2vec%3A%20Unsupervised%20Pre-training%20for%20Speech%20Recognition&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=wav2vec%3A%20Unsupervised%20Pre-training%20for%20Speech%20Recognition%20Schneider%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=wav2vec%3A%20Unsupervised%20Pre-training%20for%20Speech%20Recognition&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Self-supervised speech", "title": "wav2vec: Unsupervised Pre-training for Speech Recognition", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Baevski et al.", "id": 460, "links": { "canonical_url": "https://arxiv.org/abs/2006.11477", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2006.11477.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=wav2vec%202.0%3A%20A%20Framework%20for%20Self-Supervised%20Learning%20of%20Speech&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=wav2vec%202.0%3A%20A%20Framework%20for%20Self-Supervised%20Learning%20of%20Speech%20Baevski%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=wav2vec%202.0%3A%20A%20Framework%20for%20Self-Supervised%20Learning%20of%20Speech&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2006.11477.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Contrastive speech pretraining", "title": "wav2vec 2.0: A Framework for Self-Supervised Learning of Speech", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Hsu et al.", "id": 461, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=HuBERT%3A%20Self-Supervised%20Speech%20Representation%20Learning%20by%20Masked%20Prediction&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=HuBERT%3A%20Self-Supervised%20Speech%20Representation%20Learning%20by%20Masked%20Prediction%20Hsu%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=HuBERT%3A%20Self-Supervised%20Speech%20Representation%20Learning%20by%20Masked%20Prediction&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Hidden-unit BERT for speech", "title": "HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Radford et al.", "id": 462, "links": { "canonical_url": "https://arxiv.org/abs/2212.04356", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2212.04356.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Whisper%3A%20Robust%20Speech%20Recognition%20via%20Large-Scale%20Weak%20Supervision&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Whisper%3A%20Robust%20Speech%20Recognition%20via%20Large-Scale%20Weak%20Supervision%20Radford%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Whisper%3A%20Robust%20Speech%20Recognition%20via%20Large-Scale%20Weak%20Supervision&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2212.04356.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "**Universal ASR model**", "title": "Whisper: Robust Speech Recognition via Large-Scale Weak Supervision", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Gulati et al.", "id": 463, "links": { "canonical_url": "https://arxiv.org/abs/2005.08100", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2005.08100.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Conformer%3A%20Convolution-augmented%20Transformer%20for%20Speech&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Conformer%3A%20Convolution-augmented%20Transformer%20for%20Speech%20Gulati%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Conformer%3A%20Convolution-augmented%20Transformer%20for%20Speech&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2005.08100.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Hybrid conv-transformer for speech", "title": "Conformer: Convolution-augmented Transformer for Speech", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Shen et al.", "id": 464, "links": { "canonical_url": "https://arxiv.org/abs/1712.05884", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1712.05884.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Tacotron%202%3A%20Natural%20TTS%20Synthesis&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Tacotron%202%3A%20Natural%20TTS%20Synthesis%20Shen%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Tacotron%202%3A%20Natural%20TTS%20Synthesis&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1712.05884.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Neural text-to-speech", "title": "Tacotron 2: Natural TTS Synthesis", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Ren et al.", "id": 465, "links": { "canonical_url": "https://arxiv.org/abs/2006.04558", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2006.04558.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=FastSpeech%202%3A%20Fast%20and%20High-Quality%20End-to-End%20TTS&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=FastSpeech%202%3A%20Fast%20and%20High-Quality%20End-to-End%20TTS%20Ren%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=FastSpeech%202%3A%20Fast%20and%20High-Quality%20End-to-End%20TTS&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2006.04558.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Non-autoregressive TTS", "title": "FastSpeech 2: Fast and High-Quality End-to-End TTS", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Wang et al.", "id": 466, "links": { "canonical_url": "https://arxiv.org/abs/2301.02111", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2301.02111.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=VALL-E%3A%20Neural%20Codec%20Language%20Models%20are%20Zero-Shot%20TTS&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=VALL-E%3A%20Neural%20Codec%20Language%20Models%20are%20Zero-Shot%20TTS%20Wang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=VALL-E%3A%20Neural%20Codec%20Language%20Models%20are%20Zero-Shot%20TTS&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2301.02111.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Voice cloning with LLM", "title": "VALL-E: Neural Codec Language Models are Zero-Shot TTS", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Casanova et al.", "id": 467, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=XTTS%3A%20Massively%20Multilingual%20TTS&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=XTTS%3A%20Massively%20Multilingual%20TTS%20Casanova%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=XTTS%3A%20Massively%20Multilingual%20TTS&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Multilingual voice synthesis", "title": "XTTS: Massively Multilingual TTS", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Borsos et al.", "id": 468, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AudioLM%3A%20A%20Language%20Modeling%20Approach%20to%20Audio%20Generation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AudioLM%3A%20A%20Language%20Modeling%20Approach%20to%20Audio%20Generation%20Borsos%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=AudioLM%3A%20A%20Language%20Modeling%20Approach%20to%20Audio%20Generation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Audio as language modeling", "title": "AudioLM: A Language Modeling Approach to Audio Generation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Agostinelli et al.", "id": 469, "links": { "canonical_url": "https://arxiv.org/abs/2301.11325", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2301.11325.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MusicLM%3A%20Generating%20Music%20from%20Text&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MusicLM%3A%20Generating%20Music%20from%20Text%20Agostinelli%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=MusicLM%3A%20Generating%20Music%20from%20Text&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2301.11325.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Text-to-music", "title": "MusicLM: Generating Music from Text", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Suno", "id": 470, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Bark%3A%20Text-Prompted%20Generative%20Audio%20Model&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Bark%3A%20Text-Prompted%20Generative%20Audio%20Model%20Suno%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Bark%3A%20Text-Prompted%20Generative%20Audio%20Model&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Versatile audio generation", "title": "Bark: Text-Prompted Generative Audio Model", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Rubenstein et al.", "id": 471, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AudioPaLM%3A%20A%20Large%20Language%20Model%20that%20Can%20Speak%20and%20Listen&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AudioPaLM%3A%20A%20Large%20Language%20Model%20that%20Can%20Speak%20and%20Listen%20Rubenstein%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=AudioPaLM%3A%20A%20Large%20Language%20Model%20that%20Can%20Speak%20and%20Listen&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Multimodal speech LLM", "title": "AudioPaLM: A Large Language Model that Can Speak and Listen", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Meta", "id": 472, "links": { "canonical_url": "https://arxiv.org/abs/2308.11596", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2308.11596.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SeamlessM4T%3A%20Massively%20Multilingual%20%26%20Multimodal%20Machine%20Translation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SeamlessM4T%3A%20Massively%20Multilingual%20%26%20Multimodal%20Machine%20Translation%20Meta%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=SeamlessM4T%3A%20Massively%20Multilingual%20%26%20Multimodal%20Machine%20Translation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2308.11596.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "100+ language speech translation", "title": "SeamlessM4T: Massively Multilingual & Multimodal Machine Translation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Défossez et al.", "id": 473, "links": { "canonical_url": "https://arxiv.org/abs/2210.13438", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2210.13438.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Encodec%3A%20High%20Fidelity%20Neural%20Audio%20Compression&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Encodec%3A%20High%20Fidelity%20Neural%20Audio%20Compression%20D%C3%A9fossez%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Encodec%3A%20High%20Fidelity%20Neural%20Audio%20Compression&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2210.13438.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Neural audio codec", "title": "Encodec: High Fidelity Neural Audio Compression", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Le et al.", "id": 474, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Voicebox%3A%20Text-Guided%20Multilingual%20Universal%20Speech%20Generation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Voicebox%3A%20Text-Guided%20Multilingual%20Universal%20Speech%20Generation%20Le%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Voicebox%3A%20Text-Guided%20Multilingual%20Universal%20Speech%20Generation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Universal speech generation", "title": "Voicebox: Text-Guided Multilingual Universal Speech Generation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Borsos et al.", "id": 475, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SoundStorm%3A%20Efficient%20Parallel%20Audio%20Generation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SoundStorm%3A%20Efficient%20Parallel%20Audio%20Generation%20Borsos%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=SoundStorm%3A%20Efficient%20Parallel%20Audio%20Generation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 24, "section_title": "Speech & Audio Models", "source_note": "Parallel audio decoding", "title": "SoundStorm: Efficient Parallel Audio Generation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Sohl-Dickstein et al.", "id": 476, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Deep%20Unsupervised%20Learning%20using%20Nonequilibrium%20Thermodynamics&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Deep%20Unsupervised%20Learning%20using%20Nonequilibrium%20Thermodynamics%20Sohl-Dickstein%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Deep%20Unsupervised%20Learning%20using%20Nonequilibrium%20Thermodynamics&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Diffusion process for generation", "title": "Deep Unsupervised Learning using Nonequilibrium Thermodynamics", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Ho, Jain, Abbeel", "id": 477, "links": { "canonical_url": "https://arxiv.org/abs/2006.11239", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2006.11239.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Denoising%20Diffusion%20Probabilistic%20Models%20%28DDPM%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Denoising%20Diffusion%20Probabilistic%20Models%20%28DDPM%29%20Ho%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Denoising%20Diffusion%20Probabilistic%20Models%20%28DDPM%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2006.11239.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "**Modern diffusion models**", "title": "Denoising Diffusion Probabilistic Models (DDPM)", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Song et al.", "id": 478, "links": { "canonical_url": "https://arxiv.org/abs/2011.13456", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2011.13456.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Score-Based%20Generative%20Modeling%20through%20SDE&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Score-Based%20Generative%20Modeling%20through%20SDE%20Song%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Score-Based%20Generative%20Modeling%20through%20SDE&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2011.13456.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Score matching + SDEs", "title": "Score-Based Generative Modeling through SDE", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Song, Meng, Ermon", "id": 479, "links": { "canonical_url": "https://arxiv.org/abs/2010.02502", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2010.02502.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Denoising%20Diffusion%20Implicit%20Models%20%28DDIM%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Denoising%20Diffusion%20Implicit%20Models%20%28DDIM%29%20Song%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Denoising%20Diffusion%20Implicit%20Models%20%28DDIM%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2010.02502.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Faster diffusion sampling", "title": "Denoising Diffusion Implicit Models (DDIM)", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Ho & Salimans", "id": 480, "links": { "canonical_url": "https://arxiv.org/abs/2207.12598", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2207.12598.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Classifier-Free%20Diffusion%20Guidance&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Classifier-Free%20Diffusion%20Guidance%20Ho%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Classifier-Free%20Diffusion%20Guidance&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2207.12598.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "CFG — standard guidance method", "title": "Classifier-Free Diffusion Guidance", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Rombach et al.", "id": 481, "links": { "canonical_url": "https://arxiv.org/abs/2112.10752", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2112.10752.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=High-Resolution%20Image%20Synthesis%20with%20Latent%20Diffusion%20Models%20%28LDM%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=High-Resolution%20Image%20Synthesis%20with%20Latent%20Diffusion%20Models%20%28LDM%29%20Rombach%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=High-Resolution%20Image%20Synthesis%20with%20Latent%20Diffusion%20Models%20%28LDM%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2112.10752.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Latent space diffusion", "title": "High-Resolution Image Synthesis with Latent Diffusion Models (LDM)", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Stability AI / Rombach et al.", "id": 482, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Stable%20Diffusion&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Stable%20Diffusion%20Stability%20AI%20/%20Rombach%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Stable%20Diffusion&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "**Open image generation**", "title": "Stable Diffusion", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Ramesh et al.", "id": 483, "links": { "canonical_url": "https://arxiv.org/abs/2204.06125", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2204.06125.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DALL%C2%B7E%202%3A%20Hierarchical%20Text-Conditional%20Image%20Generation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DALL%C2%B7E%202%3A%20Hierarchical%20Text-Conditional%20Image%20Generation%20Ramesh%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=DALL%C2%B7E%202%3A%20Hierarchical%20Text-Conditional%20Image%20Generation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2204.06125.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "CLIP-guided diffusion", "title": "DALL·E 2: Hierarchical Text-Conditional Image Generation", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Saharia et al.", "id": 484, "links": { "canonical_url": "https://arxiv.org/abs/2205.11487", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2205.11487.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Imagen%3A%20Photorealistic%20Text-to-Image%20Diffusion%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Imagen%3A%20Photorealistic%20Text-to-Image%20Diffusion%20Models%20Saharia%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Imagen%3A%20Photorealistic%20Text-to-Image%20Diffusion%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2205.11487.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "T5-guided diffusion", "title": "Imagen: Photorealistic Text-to-Image Diffusion Models", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Balaji et al.", "id": 485, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=eDiff-I%3A%20Text-to-Image%20Diffusion%20Models%20with%20an%20Ensemble%20of%20Expert%20Denoisers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=eDiff-I%3A%20Text-to-Image%20Diffusion%20Models%20with%20an%20Ensemble%20of%20Expert%20Denoisers%20Balaji%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=eDiff-I%3A%20Text-to-Image%20Diffusion%20Models%20with%20an%20Ensemble%20of%20Expert%20Denoisers&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Expert denoisers", "title": "eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Podell et al.", "id": 486, "links": { "canonical_url": "https://arxiv.org/abs/2307.01952", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2307.01952.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SDXL%3A%20Improving%20Latent%20Diffusion%20Models%20for%20High-Resolution%20Image%20Synthesis&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SDXL%3A%20Improving%20Latent%20Diffusion%20Models%20for%20High-Resolution%20Image%20Synthesis%20Podell%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=SDXL%3A%20Improving%20Latent%20Diffusion%20Models%20for%20High-Resolution%20Image%20Synthesis&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2307.01952.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Stable Diffusion XL", "title": "SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Betker et al.", "id": 487, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DALL%C2%B7E%203&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DALL%C2%B7E%203%20Betker%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=DALL%C2%B7E%203&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Improved text following", "title": "DALL·E 3", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "non_paper_or_multi_work", "message": "A product-analysis container rather than a uniquely identifiable research paper.", "required_action": "Move to a typed product-analysis collection or replace with a citable technical source.", "severity": "blocking" } ], "authors": "Midjourney", "id": 488, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Midjourney%20%28V5/V6%20technical%20analysis%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Midjourney%20%28V5/V6%20technical%20analysis%29%20Midjourney%202023-2024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Midjourney%20%28V5/V6%20technical%20analysis%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Aesthetic image generation", "title": "Midjourney (V5/V6 technical analysis)", "work_type": "Product or topic analysis", "year": 2023, "year_display": "2023-2024" }, { "audit_flags": [], "authors": "Song et al.", "id": 489, "links": { "canonical_url": "https://arxiv.org/abs/2303.01469", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2303.01469.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Consistency%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Consistency%20Models%20Song%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Consistency%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2303.01469.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "One-step generation", "title": "Consistency Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Luo et al.", "id": 490, "links": { "canonical_url": "https://arxiv.org/abs/2310.04378", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2310.04378.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Latent%20Consistency%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Latent%20Consistency%20Models%20Luo%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Latent%20Consistency%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2310.04378.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Fast latent diffusion", "title": "Latent Consistency Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Liu et al.", "id": 491, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Rectified%20Flow%20%28InstaFlow%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Rectified%20Flow%20%28InstaFlow%29%20Liu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Rectified%20Flow%20%28InstaFlow%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Straight trajectory sampling", "title": "Rectified Flow (InstaFlow)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Esser et al.", "id": 492, "links": { "canonical_url": "https://arxiv.org/abs/2403.03206", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2403.03206.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Stable%20Diffusion%203%20%28MM-DiT%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Stable%20Diffusion%203%20%28MM-DiT%29%20Esser%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Stable%20Diffusion%203%20%28MM-DiT%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2403.03206.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Multimodal DiT architecture", "title": "Stable Diffusion 3 (MM-DiT)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Black Forest Labs", "id": 493, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=FLUX&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=FLUX%20Black%20Forest%20Labs%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=FLUX&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Next-gen flow-based generation", "title": "FLUX", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zhang & Agrawala", "id": 494, "links": { "canonical_url": "https://arxiv.org/abs/2302.05543", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2302.05543.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ControlNet%3A%20Adding%20Conditional%20Control%20to%20Text-to-Image%20Diffusion&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ControlNet%3A%20Adding%20Conditional%20Control%20to%20Text-to-Image%20Diffusion%20Zhang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=ControlNet%3A%20Adding%20Conditional%20Control%20to%20Text-to-Image%20Diffusion&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2302.05543.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Structural control for diffusion", "title": "ControlNet: Adding Conditional Control to Text-to-Image Diffusion", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Ye et al.", "id": 495, "links": { "canonical_url": "https://arxiv.org/abs/2308.06721", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2308.06721.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=IP-Adapter%3A%20Text%20Compatible%20Image%20Prompt%20Adapter&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=IP-Adapter%3A%20Text%20Compatible%20Image%20Prompt%20Adapter%20Ye%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=IP-Adapter%3A%20Text%20Compatible%20Image%20Prompt%20Adapter&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2308.06721.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Image prompt adapters", "title": "IP-Adapter: Text Compatible Image Prompt Adapter", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Ruiz et al.", "id": 496, "links": { "canonical_url": "https://arxiv.org/abs/2208.12242", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2208.12242.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DreamBooth%3A%20Fine%20Tuning%20Text-to-Image%20Models%20for%20Subject-Driven%20Generation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DreamBooth%3A%20Fine%20Tuning%20Text-to-Image%20Models%20for%20Subject-Driven%20Generation%20Ruiz%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=DreamBooth%3A%20Fine%20Tuning%20Text-to-Image%20Models%20for%20Subject-Driven%20Generation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2208.12242.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Subject customization", "title": "DreamBooth: Fine Tuning Text-to-Image Models for Subject-Driven Generation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Gal et al.", "id": 497, "links": { "canonical_url": "https://arxiv.org/abs/2208.01618", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2208.01618.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Textual%20Inversion%3A%20An%20Image%20is%20Worth%20One%20Word&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Textual%20Inversion%3A%20An%20Image%20is%20Worth%20One%20Word%20Gal%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Textual%20Inversion%3A%20An%20Image%20is%20Worth%20One%20Word&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2208.01618.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Concept learning via tokens", "title": "Textual Inversion: An Image is Worth One Word", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Brooks et al.", "id": 498, "links": { "canonical_url": "https://arxiv.org/abs/2211.09800", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2211.09800.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=InstructPix2Pix%3A%20Learning%20to%20Follow%20Image%20Editing%20Instructions&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=InstructPix2Pix%3A%20Learning%20to%20Follow%20Image%20Editing%20Instructions%20Brooks%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=InstructPix2Pix%3A%20Learning%20to%20Follow%20Image%20Editing%20Instructions&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2211.09800.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Instruction-based image editing", "title": "InstructPix2Pix: Learning to Follow Image Editing Instructions", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Peebles & Xie", "id": 499, "links": { "canonical_url": "https://arxiv.org/abs/2212.09748", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2212.09748.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scalable%20Diffusion%20Models%20with%20Transformers%20%28DiT%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scalable%20Diffusion%20Models%20with%20Transformers%20%28DiT%29%20Peebles%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scalable%20Diffusion%20Models%20with%20Transformers%20%28DiT%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2212.09748.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Transformer-based diffusion", "title": "Scalable Diffusion Models with Transformers (DiT)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Lipman et al.", "id": 500, "links": { "canonical_url": "https://arxiv.org/abs/2210.02747", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2210.02747.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Flow%20Matching%20for%20Generative%20Modeling&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Flow%20Matching%20for%20Generative%20Modeling%20Lipman%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Flow%20Matching%20for%20Generative%20Modeling&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2210.02747.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 25, "section_title": "Diffusion Models & Image Generation", "source_note": "Optimal transport flows", "title": "Flow Matching for Generative Modeling", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Ho et al.", "id": 501, "links": { "canonical_url": "https://arxiv.org/abs/2204.03458", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2204.03458.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Video%20Diffusion%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Video%20Diffusion%20Models%20Ho%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Video%20Diffusion%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2204.03458.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "Diffusion for video", "title": "Video Diffusion Models", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Ho et al.", "id": 502, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Imagen%20Video%3A%20High%20Definition%20Video%20Generation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Imagen%20Video%3A%20High%20Definition%20Video%20Generation%20Ho%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Imagen%20Video%3A%20High%20Definition%20Video%20Generation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "Cascaded video diffusion", "title": "Imagen Video: High Definition Video Generation", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Singer et al.", "id": 503, "links": { "canonical_url": "https://arxiv.org/abs/2209.14792", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2209.14792.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Make-A-Video%3A%20Text-to-Video%20Generation%20without%20Text-Video%20Data&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Make-A-Video%3A%20Text-to-Video%20Generation%20without%20Text-Video%20Data%20Singer%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Make-A-Video%3A%20Text-to-Video%20Generation%20without%20Text-Video%20Data&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2209.14792.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "Text-to-video from image data", "title": "Make-A-Video: Text-to-Video Generation without Text-Video Data", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Kondratyuk et al.", "id": 504, "links": { "canonical_url": "https://arxiv.org/abs/2312.14125", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2312.14125.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=VideoPoet%3A%20A%20Large%20Language%20Model%20for%20Zero-Shot%20Video%20Generation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=VideoPoet%3A%20A%20Large%20Language%20Model%20for%20Zero-Shot%20Video%20Generation%20Kondratyuk%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=VideoPoet%3A%20A%20Large%20Language%20Model%20for%20Zero-Shot%20Video%20Generation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2312.14125.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "LLM-based video generation", "title": "VideoPoet: A Large Language Model for Zero-Shot Video Generation", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "OpenAI", "id": 505, "links": { "canonical_url": "https://openai.com/research/video-generation-models-as-world-simulators", "corrected_by_audit": false, "direct_url": "https://openai.com/research/video-generation-models-as-world-simulators", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Sora%3A%20Video%20Generation%20Models%20as%20World%20Simulators&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Sora%3A%20Video%20Generation%20Models%20as%20World%20Simulators%20OpenAI%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Sora%3A%20Video%20Generation%20Models%20as%20World%20Simulators&sort=relevance" }, "supplied_direct_url": "https://openai.com/research/video-generation-models-as-world-simulators" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "**Frontier video generation**", "title": "Sora: Video Generation Models as World Simulators", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Blattmann et al.", "id": 506, "links": { "canonical_url": "https://arxiv.org/abs/2311.15127", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2311.15127.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Stable%20Video%20Diffusion&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Stable%20Video%20Diffusion%20Blattmann%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Stable%20Video%20Diffusion&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2311.15127.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "Open video generation", "title": "Stable Video Diffusion", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Guo et al.", "id": 507, "links": { "canonical_url": "https://arxiv.org/abs/2307.04725", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2307.04725.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AnimateDiff%3A%20Animate%20Your%20Personalized%20Text-to-Image%20Diffusion%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AnimateDiff%3A%20Animate%20Your%20Personalized%20Text-to-Image%20Diffusion%20Models%20Guo%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=AnimateDiff%3A%20Animate%20Your%20Personalized%20Text-to-Image%20Diffusion%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2307.04725.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "Motion modules for SD", "title": "AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as product or topic analysis, not as a research paper.", "severity": "warning" } ], "authors": "Kuaishou", "id": 508, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Kling%20%28technical%20analysis%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Kling%20%28technical%20analysis%29%20Kuaishou%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Kling%20%28technical%20analysis%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "Chinese video generation", "title": "Kling (technical analysis)", "work_type": "Product or topic analysis", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Runway", "id": 509, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Gen-2%3A%20Generating%20Novel%20Videos%20with%20Text%2C%20Images%2C%20or%20Clips&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Gen-2%3A%20Generating%20Novel%20Videos%20with%20Text%2C%20Images%2C%20or%20Clips%20Runway%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Gen-2%3A%20Generating%20Novel%20Videos%20with%20Text%2C%20Images%2C%20or%20Clips&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "Multimodal video generation", "title": "Gen-2: Generating Novel Videos with Text, Images, or Clips", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Chen et al.", "id": 510, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=VideoCrafter%3A%20A%20Toolkit%20for%20Text-to-Video%20Generation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=VideoCrafter%3A%20A%20Toolkit%20for%20Text-to-Video%20Generation%20Chen%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=VideoCrafter%3A%20A%20Toolkit%20for%20Text-to-Video%20Generation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "Open video toolkit", "title": "VideoCrafter: A Toolkit for Text-to-Video Generation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Tong et al.", "id": 511, "links": { "canonical_url": "https://arxiv.org/abs/2203.12602", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2203.12602.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=VideoMAE%3A%20Masked%20Autoencoders%20are%20Data-Efficient%20Learners%20for%20Self-Supervised%20Video%20Pre-Training&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=VideoMAE%3A%20Masked%20Autoencoders%20are%20Data-Efficient%20Learners%20for%20Self-Supervised%20Video%20Pre-Training%20Tong%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=VideoMAE%3A%20Masked%20Autoencoders%20are%20Data-Efficient%20Learners%20for%20Self-Supervised%20Video%20Pre-Training&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2203.12602.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "Self-supervised video", "title": "VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Bertasius et al.", "id": 512, "links": { "canonical_url": "https://arxiv.org/abs/2102.05095", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2102.05095.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=TimeSformer%3A%20Is%20Space-Time%20Attention%20All%20You%20Need%20for%20Video%20Understanding%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=TimeSformer%3A%20Is%20Space-Time%20Attention%20All%20You%20Need%20for%20Video%20Understanding%3F%20Bertasius%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=TimeSformer%3A%20Is%20Space-Time%20Attention%20All%20You%20Need%20for%20Video%20Understanding%3F&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2102.05095.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "Space-time attention", "title": "TimeSformer: Is Space-Time Attention All You Need for Video Understanding?", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Arnab et al.", "id": 513, "links": { "canonical_url": "https://arxiv.org/abs/2103.15691", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2103.15691.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ViViT%3A%20A%20Video%20Vision%20Transformer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ViViT%3A%20A%20Video%20Vision%20Transformer%20Arnab%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=ViViT%3A%20A%20Video%20Vision%20Transformer&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2103.15691.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "Video transformer", "title": "ViViT: A Video Vision Transformer", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Wang et al.", "id": 514, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=InternVideo%3A%20General%20Video%20Foundation%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=InternVideo%3A%20General%20Video%20Foundation%20Models%20Wang%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=InternVideo%3A%20General%20Video%20Foundation%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "Video foundation model", "title": "InternVideo: General Video Foundation Models", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Lin et al.", "id": 515, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Video-LLaVA&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Video-LLaVA%20Lin%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Video-LLaVA&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 26, "section_title": "Video Generation & Understanding", "source_note": "Video understanding with VLMs", "title": "Video-LLaVA", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Kipf & Welling", "id": 516, "links": { "canonical_url": "https://arxiv.org/abs/1609.02907", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1609.02907.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Semi-Supervised%20Classification%20with%20Graph%20Convolutional%20Networks%20%28GCN%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Semi-Supervised%20Classification%20with%20Graph%20Convolutional%20Networks%20%28GCN%29%20Kipf%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Semi-Supervised%20Classification%20with%20Graph%20Convolutional%20Networks%20%28GCN%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1609.02907.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "Graph convolutions", "title": "Semi-Supervised Classification with Graph Convolutional Networks (GCN)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Veličković et al.", "id": 517, "links": { "canonical_url": "https://arxiv.org/abs/1710.10903", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1710.10903.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Attention-Based%20Graph%20Neural%20Network%20%28GAT%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Attention-Based%20Graph%20Neural%20Network%20%28GAT%29%20Veli%C4%8Dkovi%C4%87%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Attention-Based%20Graph%20Neural%20Network%20%28GAT%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1710.10903.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "Graph attention", "title": "Attention-Based Graph Neural Network (GAT)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Hamilton, Ying, Leskovec", "id": 518, "links": { "canonical_url": "https://arxiv.org/abs/1706.02216", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1706.02216.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Inductive%20Representation%20Learning%20on%20Large%20Graphs%20%28GraphSAGE%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Inductive%20Representation%20Learning%20on%20Large%20Graphs%20%28GraphSAGE%29%20Hamilton%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Inductive%20Representation%20Learning%20on%20Large%20Graphs%20%28GraphSAGE%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1706.02216.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "Scalable graph learning", "title": "Inductive Representation Learning on Large Graphs (GraphSAGE)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Xu et al.", "id": 519, "links": { "canonical_url": "https://arxiv.org/abs/1810.00826", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1810.00826.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=How%20Powerful%20are%20Graph%20Neural%20Networks%3F%20%28GIN%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=How%20Powerful%20are%20Graph%20Neural%20Networks%3F%20%28GIN%29%20Xu%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=How%20Powerful%20are%20Graph%20Neural%20Networks%3F%20%28GIN%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1810.00826.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "GNN expressivity analysis", "title": "How Powerful are Graph Neural Networks? (GIN)", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Gilmer et al.", "id": 520, "links": { "canonical_url": "https://arxiv.org/abs/1704.01212", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1704.01212.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Message%20Passing%20Neural%20Networks%20%28MPNN%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Message%20Passing%20Neural%20Networks%20%28MPNN%29%20Gilmer%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Message%20Passing%20Neural%20Networks%20%28MPNN%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1704.01212.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "Unified message passing framework", "title": "Message Passing Neural Networks (MPNN)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Xu et al.", "id": 521, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Graph%20Isomorphism%20Network%20%28GIN%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Graph%20Isomorphism%20Network%20%28GIN%29%20Xu%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Graph%20Isomorphism%20Network%20%28GIN%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "WL-test equivalent GNN", "title": "Graph Isomorphism Network (GIN)", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Schlichtkrull et al.", "id": 522, "links": { "canonical_url": "https://arxiv.org/abs/1703.06103", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1703.06103.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Relational%20Graph%20Convolutional%20Networks%20%28R-GCN%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Relational%20Graph%20Convolutional%20Networks%20%28R-GCN%29%20Schlichtkrull%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Relational%20Graph%20Convolutional%20Networks%20%28R-GCN%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1703.06103.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "GCNs for knowledge graphs", "title": "Relational Graph Convolutional Networks (R-GCN)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Yun et al.", "id": 523, "links": { "canonical_url": "https://arxiv.org/abs/1911.06455", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1911.06455.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Graph%20Transformer%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Graph%20Transformer%20Networks%20Yun%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Graph%20Transformer%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1911.06455.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "Transformers on graphs", "title": "Graph Transformer Networks", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Perozzi, Al-Rfou, Skiena", "id": 524, "links": { "canonical_url": "https://arxiv.org/abs/1403.6652", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1403.6652.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeepWalk%3A%20Online%20Learning%20of%20Social%20Representations&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeepWalk%3A%20Online%20Learning%20of%20Social%20Representations%20Perozzi%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeepWalk%3A%20Online%20Learning%20of%20Social%20Representations&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1403.6652.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "Graph embeddings via random walks", "title": "DeepWalk: Online Learning of Social Representations", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Grover & Leskovec", "id": 525, "links": { "canonical_url": "https://arxiv.org/abs/1607.00653", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1607.00653.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Node2Vec%3A%20Scalable%20Feature%20Learning%20for%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Node2Vec%3A%20Scalable%20Feature%20Learning%20for%20Networks%20Grover%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Node2Vec%3A%20Scalable%20Feature%20Learning%20for%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1607.00653.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "Biased random walk embeddings", "title": "Node2Vec: Scalable Feature Learning for Networks", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Wu et al.", "id": 526, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Comprehensive%20Survey%20on%20Graph%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Comprehensive%20Survey%20on%20Graph%20Neural%20Networks%20Wu%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Comprehensive%20Survey%20on%20Graph%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "GNN survey", "title": "A Comprehensive Survey on Graph Neural Networks", "work_type": "Survey or review", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Satorras et al.", "id": 527, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Equivariant%20Graph%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Equivariant%20Graph%20Neural%20Networks%20Satorras%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Equivariant%20Graph%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "E(n)-equivariant GNNs", "title": "Equivariant Graph Neural Networks", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Zhou et al.", "id": 528, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Graph%20Neural%20Networks%3A%20A%20Review%20of%20Methods%20and%20Applications&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Graph%20Neural%20Networks%3A%20A%20Review%20of%20Methods%20and%20Applications%20Zhou%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Graph%20Neural%20Networks%3A%20A%20Review%20of%20Methods%20and%20Applications&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "GNN applications review", "title": "Graph Neural Networks: A Review of Methods and Applications", "work_type": "Survey or review", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Bruna et al.", "id": 529, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Spectral%20Graph%20Theory%20and%20Deep%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Spectral%20Graph%20Theory%20and%20Deep%20Learning%20Bruna%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Spectral%20Graph%20Theory%20and%20Deep%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "Spectral graph convolutions", "title": "Spectral Graph Theory and Deep Learning", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Bronstein et al.", "id": 530, "links": { "canonical_url": "https://arxiv.org/abs/2104.13478", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2104.13478.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Geometric%20Deep%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Geometric%20Deep%20Learning%20Bronstein%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Geometric%20Deep%20Learning&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2104.13478.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 27, "section_title": "Graph Neural Networks", "source_note": "Unified geometric DL framework", "title": "Geometric Deep Learning", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Han et al.", "id": 531, "links": { "canonical_url": "https://arxiv.org/abs/1510.00149", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1510.00149.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Deep%20Compression%3A%20Pruning%2C%20Quantization%2C%20Huffman%20Coding&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Deep%20Compression%3A%20Pruning%2C%20Quantization%2C%20Huffman%20Coding%20Han%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Deep%20Compression%3A%20Pruning%2C%20Quantization%2C%20Huffman%20Coding&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1510.00149.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Three-stage compression", "title": "Deep Compression: Pruning, Quantization, Huffman Coding", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Howard et al.", "id": 532, "links": { "canonical_url": "https://arxiv.org/abs/1704.04861", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1704.04861.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MobileNets%3A%20Efficient%20CNNs%20for%20Mobile%20Vision%20Applications&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MobileNets%3A%20Efficient%20CNNs%20for%20Mobile%20Vision%20Applications%20Howard%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=MobileNets%3A%20Efficient%20CNNs%20for%20Mobile%20Vision%20Applications&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1704.04861.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Depthwise separable convolutions", "title": "MobileNets: Efficient CNNs for Mobile Vision Applications", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Sandler et al.", "id": 533, "links": { "canonical_url": "https://arxiv.org/abs/1801.04381", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1801.04381.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MobileNetV2%3A%20Inverted%20Residuals%20and%20Linear%20Bottlenecks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MobileNetV2%3A%20Inverted%20Residuals%20and%20Linear%20Bottlenecks%20Sandler%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=MobileNetV2%3A%20Inverted%20Residuals%20and%20Linear%20Bottlenecks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1801.04381.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Inverted residuals", "title": "MobileNetV2: Inverted Residuals and Linear Bottlenecks", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 534, "links": { "canonical_url": "https://arxiv.org/abs/1707.01083", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1707.01083.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ShuffleNet%3A%20Extremely%20Efficient%20CNN%20for%20Mobile%20Devices&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ShuffleNet%3A%20Extremely%20Efficient%20CNN%20for%20Mobile%20Devices%20Zhang%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=ShuffleNet%3A%20Extremely%20Efficient%20CNN%20for%20Mobile%20Devices&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1707.01083.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Channel shuffle", "title": "ShuffleNet: Extremely Efficient CNN for Mobile Devices", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Iandola et al.", "id": 535, "links": { "canonical_url": "https://arxiv.org/abs/1602.07360", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1602.07360.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SqueezeNet%3A%20AlexNet-level%20Accuracy%20with%2050x%20Fewer%20Parameters&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SqueezeNet%3A%20AlexNet-level%20Accuracy%20with%2050x%20Fewer%20Parameters%20Iandola%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=SqueezeNet%3A%20AlexNet-level%20Accuracy%20with%2050x%20Fewer%20Parameters&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1602.07360.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Compact architectures", "title": "SqueezeNet: AlexNet-level Accuracy with 50x Fewer Parameters", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Dettmers et al.", "id": 536, "links": { "canonical_url": "https://arxiv.org/abs/2208.07339", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2208.07339.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLM.int8%28%29%3A%208-bit%20Matrix%20Multiplication%20for%20Transformers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLM.int8%28%29%3A%208-bit%20Matrix%20Multiplication%20for%20Transformers%20Dettmers%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLM.int8%28%29%3A%208-bit%20Matrix%20Multiplication%20for%20Transformers&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2208.07339.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "8-bit quantization for LLMs", "title": "LLM.int8(): 8-bit Matrix Multiplication for Transformers", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Frantar et al.", "id": 537, "links": { "canonical_url": "https://arxiv.org/abs/2210.17323", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2210.17323.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GPTQ%3A%20Accurate%20Post-Training%20Quantization%20for%20GPT&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GPTQ%3A%20Accurate%20Post-Training%20Quantization%20for%20GPT%20Frantar%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=GPTQ%3A%20Accurate%20Post-Training%20Quantization%20for%20GPT&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2210.17323.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "One-shot weight quantization", "title": "GPTQ: Accurate Post-Training Quantization for GPT", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Lin et al.", "id": 538, "links": { "canonical_url": "https://arxiv.org/abs/2306.00978", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2306.00978.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AWQ%3A%20Activation-aware%20Weight%20Quantization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AWQ%3A%20Activation-aware%20Weight%20Quantization%20Lin%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=AWQ%3A%20Activation-aware%20Weight%20Quantization&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2306.00978.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Activation-aware quantization", "title": "AWQ: Activation-aware Weight Quantization", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Kim et al.", "id": 539, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SqueezeLLM%3A%20Dense-and-Sparse%20Quantization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SqueezeLLM%3A%20Dense-and-Sparse%20Quantization%20Kim%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=SqueezeLLM%3A%20Dense-and-Sparse%20Quantization&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Ultra-low bit quantization", "title": "SqueezeLLM: Dense-and-Sparse Quantization", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Ma et al.", "id": 540, "links": { "canonical_url": "https://arxiv.org/abs/2402.17764", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2402.17764.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Era%20of%201-bit%20LLMs%3A%20Training-time%201.58-bit%20Models%20%28BitNet%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Era%20of%201-bit%20LLMs%3A%20Training-time%201.58-bit%20Models%20%28BitNet%29%20Ma%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Era%20of%201-bit%20LLMs%3A%20Training-time%201.58-bit%20Models%20%28BitNet%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2402.17764.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Ternary weight LLMs", "title": "The Era of 1-bit LLMs: Training-time 1.58-bit Models (BitNet)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Frantar & Alistarh", "id": 541, "links": { "canonical_url": "https://arxiv.org/abs/2301.00774", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2301.00774.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SparseGPT%3A%20Massive%20Language%20Models%20Can%20Be%20Accurately%20Pruned%20in%20One-Shot&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SparseGPT%3A%20Massive%20Language%20Models%20Can%20Be%20Accurately%20Pruned%20in%20One-Shot%20Frantar%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=SparseGPT%3A%20Massive%20Language%20Models%20Can%20Be%20Accurately%20Pruned%20in%20One-Shot&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2301.00774.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "One-shot pruning for LLMs", "title": "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Sun et al.", "id": 542, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Wanda%3A%20A%20Simple%20and%20Effective%20Pruning%20Approach&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Wanda%3A%20A%20Simple%20and%20Effective%20Pruning%20Approach%20Sun%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Wanda%3A%20A%20Simple%20and%20Effective%20Pruning%20Approach&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Pruning by weights and activations", "title": "Wanda: A Simple and Effective Pruning Approach", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Dao et al.", "id": 543, "links": { "canonical_url": "https://crfm.stanford.edu/2023/10/12/flashdecoding.html", "corrected_by_audit": false, "direct_url": "https://crfm.stanford.edu/2023/10/12/flashdecoding.html", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Flash-Decoding%20for%20Long%20Context%20Inference&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Flash-Decoding%20for%20Long%20Context%20Inference%20Dao%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Flash-Decoding%20for%20Long%20Context%20Inference&sort=relevance" }, "supplied_direct_url": "https://crfm.stanford.edu/2023/10/12/flashdecoding.html" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Parallel decoding across KV", "title": "Flash-Decoding for Long Context Inference", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Leviathan, Kalman, Matias", "id": 544, "links": { "canonical_url": "https://arxiv.org/abs/2211.17192", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2211.17192.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Speculative%20Decoding&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Speculative%20Decoding%20Leviathan%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Speculative%20Decoding&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2211.17192.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Draft model for fast decoding", "title": "Speculative Decoding", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Cai et al.", "id": 545, "links": { "canonical_url": "https://arxiv.org/abs/2401.10774", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2401.10774.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Medusa%3A%20Simple%20LLM%20Inference%20Acceleration&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Medusa%3A%20Simple%20LLM%20Inference%20Acceleration%20Cai%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Medusa%3A%20Simple%20LLM%20Inference%20Acceleration&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2401.10774.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Multi-head speculative decoding", "title": "Medusa: Simple LLM Inference Acceleration", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Kwon et al.", "id": 546, "links": { "canonical_url": "https://arxiv.org/abs/2309.06180", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2309.06180.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=vLLM%3A%20Efficient%20Memory%20Management%20for%20LLM%20Serving%20%28PagedAttention%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=vLLM%3A%20Efficient%20Memory%20Management%20for%20LLM%20Serving%20%28PagedAttention%29%20Kwon%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=vLLM%3A%20Efficient%20Memory%20Management%20for%20LLM%20Serving%20%28PagedAttention%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2309.06180.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Paged KV cache management", "title": "vLLM: Efficient Memory Management for LLM Serving (PagedAttention)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "NVIDIA", "id": 547, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=TensorRT-LLM&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=TensorRT-LLM%20NVIDIA%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=TensorRT-LLM&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Optimized LLM inference", "title": "TensorRT-LLM", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Gerganov", "id": 548, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=llama.cpp&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=llama.cpp%20Gerganov%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=llama.cpp&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "CPU inference for LLMs", "title": "llama.cpp", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Ollama", "id": 549, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Ollama%20%28technical%20overview%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Ollama%20%28technical%20overview%29%20Ollama%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Ollama%20%28technical%20overview%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Local LLM deployment", "title": "Ollama (technical overview)", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Gerganov", "id": 550, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GGUF%3A%20GPT-Generated%20Unified%20Format&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GGUF%3A%20GPT-Generated%20Unified%20Format%20Gerganov%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=GGUF%3A%20GPT-Generated%20Unified%20Format&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 28, "section_title": "Efficient AI & Model Compression", "source_note": "Efficient model format", "title": "GGUF: GPT-Generated Unified Format", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Jacobs et al.", "id": 551, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": "https://www.cs.toronto.edu/~hinton/absps/jjnh91.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Adaptive%20Mixtures%20of%20Local%20Experts&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Adaptive%20Mixtures%20of%20Local%20Experts%20Jacobs%201991", "semantic_scholar": "https://www.semanticscholar.org/search?q=Adaptive%20Mixtures%20of%20Local%20Experts&sort=relevance" }, "supplied_direct_url": "https://www.cs.toronto.edu/~hinton/absps/jjnh91.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 29, "section_title": "Mixture of Experts", "source_note": "Original MoE concept", "title": "Adaptive Mixtures of Local Experts", "work_type": "Research-paper candidate", "year": 1991, "year_display": "1991" }, { "audit_flags": [], "authors": "Shazeer et al.", "id": 552, "links": { "canonical_url": "https://arxiv.org/abs/1701.06538", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1701.06538.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Outrageously%20Large%20Neural%20Networks%3A%20The%20Sparsely-Gated%20MoE%20Layer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Outrageously%20Large%20Neural%20Networks%3A%20The%20Sparsely-Gated%20MoE%20Layer%20Shazeer%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Outrageously%20Large%20Neural%20Networks%3A%20The%20Sparsely-Gated%20MoE%20Layer&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1701.06538.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 29, "section_title": "Mixture of Experts", "source_note": "Sparsely-gated MoE at scale", "title": "Outrageously Large Neural Networks: The Sparsely-Gated MoE Layer", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Fedus, Zoph, Shazeer", "id": 553, "links": { "canonical_url": "https://arxiv.org/abs/2101.03961", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2101.03961.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Switch%20Transformers%3A%20Scaling%20to%20Trillion%20Parameter%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Switch%20Transformers%3A%20Scaling%20to%20Trillion%20Parameter%20Models%20Fedus%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Switch%20Transformers%3A%20Scaling%20to%20Trillion%20Parameter%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2101.03961.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 29, "section_title": "Mixture of Experts", "source_note": "Simplified MoE routing", "title": "Switch Transformers: Scaling to Trillion Parameter Models", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Du et al.", "id": 554, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GLaM%3A%20Efficient%20Scaling%20of%20Language%20Models%20with%20MoE&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GLaM%3A%20Efficient%20Scaling%20of%20Language%20Models%20with%20MoE%20Du%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=GLaM%3A%20Efficient%20Scaling%20of%20Language%20Models%20with%20MoE&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 29, "section_title": "Mixture of Experts", "source_note": "1.2T parameter MoE", "title": "GLaM: Efficient Scaling of Language Models with MoE", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Zoph et al.", "id": 555, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ST-MoE%3A%20Designing%20Stable%20and%20Transferable%20Sparse%20Expert%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ST-MoE%3A%20Designing%20Stable%20and%20Transferable%20Sparse%20Expert%20Models%20Zoph%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=ST-MoE%3A%20Designing%20Stable%20and%20Transferable%20Sparse%20Expert%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 29, "section_title": "Mixture of Experts", "source_note": "Stable MoE training", "title": "ST-MoE: Designing Stable and Transferable Sparse Expert Models", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 196 ], "severity": "warning" } ], "authors": "Jiang et al.", "id": 556, "links": { "canonical_url": "https://arxiv.org/abs/2401.04088", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2401.04088.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mixtral%20of%20Experts&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mixtral%20of%20Experts%20Jiang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mixtral%20of%20Experts&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2401.04088.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 29, "section_title": "Mixture of Experts", "source_note": "Open MoE model", "title": "Mixtral of Experts", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Dai et al.", "id": 557, "links": { "canonical_url": "https://arxiv.org/abs/2401.06066", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2401.06066.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeepSeekMoE%3A%20Towards%20Ultimate%20Expert%20Specialization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeepSeekMoE%3A%20Towards%20Ultimate%20Expert%20Specialization%20Dai%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeepSeekMoE%3A%20Towards%20Ultimate%20Expert%20Specialization&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2401.06066.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 29, "section_title": "Mixture of Experts", "source_note": "Fine-grained expert design", "title": "DeepSeekMoE: Towards Ultimate Expert Specialization", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Clark et al.", "id": 558, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Unified%20Scaling%20Laws%20for%20Routed%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Unified%20Scaling%20Laws%20for%20Routed%20Language%20Models%20Clark%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Unified%20Scaling%20Laws%20for%20Routed%20Language%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 29, "section_title": "Mixture of Experts", "source_note": "Scaling laws for MoE", "title": "Unified Scaling Laws for Routed Language Models", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Pioro et al.", "id": 559, "links": { "canonical_url": "https://arxiv.org/abs/2401.04081", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2401.04081.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MoE-Mamba&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MoE-Mamba%20Pioro%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=MoE-Mamba&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2401.04081.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 29, "section_title": "Mixture of Experts", "source_note": "MoE with state-space models", "title": "MoE-Mamba", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Wei et al.", "id": 560, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Skywork-MoE%3A%20A%20Deep%20Dive%20into%20Training%20Techniques%20for%20MoE%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Skywork-MoE%3A%20A%20Deep%20Dive%20into%20Training%20Techniques%20for%20MoE%20LLMs%20Wei%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Skywork-MoE%3A%20A%20Deep%20Dive%20into%20Training%20Techniques%20for%20MoE%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 29, "section_title": "Mixture of Experts", "source_note": "MoE training analysis", "title": "Skywork-MoE: A Deep Dive into Training Techniques for MoE LLMs", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Hinton, Vinyals, Dean", "id": 561, "links": { "canonical_url": "https://arxiv.org/abs/1503.02531", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1503.02531.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Distilling%20the%20Knowledge%20in%20a%20Neural%20Network&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Distilling%20the%20Knowledge%20in%20a%20Neural%20Network%20Hinton%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Distilling%20the%20Knowledge%20in%20a%20Neural%20Network&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1503.02531.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 30, "section_title": "Knowledge Distillation & Transfer Learning", "source_note": "Knowledge distillation", "title": "Distilling the Knowledge in a Neural Network", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Furlanello et al.", "id": 562, "links": { "canonical_url": "https://arxiv.org/abs/1805.04770", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1805.04770.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Born%20Again%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Born%20Again%20Neural%20Networks%20Furlanello%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Born%20Again%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1805.04770.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 30, "section_title": "Knowledge Distillation & Transfer Learning", "source_note": "Self-distillation", "title": "Born Again Neural Networks", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 563, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Be%20Your%20Own%20Teacher%3A%20Improve%20the%20Performance%20of%20CNNs%20via%20Self-Distillation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Be%20Your%20Own%20Teacher%3A%20Improve%20the%20Performance%20of%20CNNs%20via%20Self-Distillation%20Zhang%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Be%20Your%20Own%20Teacher%3A%20Improve%20the%20Performance%20of%20CNNs%20via%20Self-Distillation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 30, "section_title": "Knowledge Distillation & Transfer Learning", "source_note": "Self-distillation in CNNs", "title": "Be Your Own Teacher: Improve the Performance of CNNs via Self-Distillation", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Jiao et al.", "id": 564, "links": { "canonical_url": "https://arxiv.org/abs/1909.10351", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1909.10351.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=TinyBERT%3A%20Distilling%20BERT%20for%20Natural%20Language%20Understanding&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=TinyBERT%3A%20Distilling%20BERT%20for%20Natural%20Language%20Understanding%20Jiao%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=TinyBERT%3A%20Distilling%20BERT%20for%20Natural%20Language%20Understanding&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1909.10351.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 30, "section_title": "Knowledge Distillation & Transfer Learning", "source_note": "Distilling BERT", "title": "TinyBERT: Distilling BERT for Natural Language Understanding", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Wang et al.", "id": 565, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MiniLM%3A%20Deep%20Self-Attention%20Distillation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MiniLM%3A%20Deep%20Self-Attention%20Distillation%20Wang%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=MiniLM%3A%20Deep%20Self-Attention%20Distillation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 30, "section_title": "Knowledge Distillation & Transfer Learning", "source_note": "Attention-based distillation", "title": "MiniLM: Deep Self-Attention Distillation", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Zhuang et al.", "id": 566, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=How%20Good%20Are%20You%20at%20Transferring%3F%20A%20Survey%20on%20Transfer%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=How%20Good%20Are%20You%20at%20Transferring%3F%20A%20Survey%20on%20Transfer%20Learning%20Zhuang%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=How%20Good%20Are%20You%20at%20Transferring%3F%20A%20Survey%20on%20Transfer%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 30, "section_title": "Knowledge Distillation & Transfer Learning", "source_note": "Transfer learning survey", "title": "How Good Are You at Transferring? A Survey on Transfer Learning", "work_type": "Survey or review", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Saenko et al.", "id": 567, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Domain%20Adaptation%20for%20Object%20Recognition&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Domain%20Adaptation%20for%20Object%20Recognition%20Saenko%202010", "semantic_scholar": "https://www.semanticscholar.org/search?q=Domain%20Adaptation%20for%20Object%20Recognition&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 30, "section_title": "Knowledge Distillation & Transfer Learning", "source_note": "Visual domain adaptation", "title": "Domain Adaptation for Object Recognition", "work_type": "Research-paper candidate", "year": 2010, "year_display": "2010" }, { "audit_flags": [], "authors": "Donahue et al.", "id": 568, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeCAF%3A%20A%20Deep%20Convolutional%20Activation%20Feature&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeCAF%3A%20A%20Deep%20Convolutional%20Activation%20Feature%20Donahue%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeCAF%3A%20A%20Deep%20Convolutional%20Activation%20Feature&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 30, "section_title": "Knowledge Distillation & Transfer Learning", "source_note": "CNN feature transfer", "title": "DeCAF: A Deep Convolutional Activation Feature", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Yosinski et al.", "id": 569, "links": { "canonical_url": "https://arxiv.org/abs/1411.1792", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1411.1792.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=How%20Transferable%20are%20Features%20in%20Deep%20Neural%20Networks%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=How%20Transferable%20are%20Features%20in%20Deep%20Neural%20Networks%3F%20Yosinski%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=How%20Transferable%20are%20Features%20in%20Deep%20Neural%20Networks%3F&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1411.1792.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 30, "section_title": "Knowledge Distillation & Transfer Learning", "source_note": "Layer transferability analysis", "title": "How Transferable are Features in Deep Neural Networks?", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Lee et al.", "id": 570, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLM2LLM%3A%20Boosting%20LLMs%20with%20Novel%20Iterative%20Data%20Enhancement&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLM2LLM%3A%20Boosting%20LLMs%20with%20Novel%20Iterative%20Data%20Enhancement%20Lee%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLM2LLM%3A%20Boosting%20LLMs%20with%20Novel%20Iterative%20Data%20Enhancement&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 30, "section_title": "Knowledge Distillation & Transfer Learning", "source_note": "LLM-to-LLM distillation", "title": "LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Kirkpatrick et al.", "id": 571, "links": { "canonical_url": "https://arxiv.org/abs/1612.00796", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1612.00796.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Overcoming%20Catastrophic%20Forgetting%20in%20Neural%20Networks%20%28EWC%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Overcoming%20Catastrophic%20Forgetting%20in%20Neural%20Networks%20%28EWC%29%20Kirkpatrick%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Overcoming%20Catastrophic%20Forgetting%20in%20Neural%20Networks%20%28EWC%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1612.00796.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 31, "section_title": "Continual & Lifelong Learning", "source_note": "Elastic weight consolidation", "title": "Overcoming Catastrophic Forgetting in Neural Networks (EWC)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Rusu et al.", "id": 572, "links": { "canonical_url": "https://arxiv.org/abs/1606.04671", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1606.04671.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Progressive%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Progressive%20Neural%20Networks%20Rusu%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Progressive%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1606.04671.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 31, "section_title": "Continual & Lifelong Learning", "source_note": "Growing network capacity", "title": "Progressive Neural Networks", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Parisi et al.", "id": 573, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Continual%20Lifelong%20Learning%20with%20Neural%20Networks%3A%20A%20Review&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Continual%20Lifelong%20Learning%20with%20Neural%20Networks%3A%20A%20Review%20Parisi%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Continual%20Lifelong%20Learning%20with%20Neural%20Networks%3A%20A%20Review&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 31, "section_title": "Continual & Lifelong Learning", "source_note": "Continual learning survey", "title": "Continual Lifelong Learning with Neural Networks: A Review", "work_type": "Survey or review", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Li & Hoiem", "id": 574, "links": { "canonical_url": "https://arxiv.org/abs/1606.09282", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1606.09282.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Learning%20without%20Forgetting&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Learning%20without%20Forgetting%20Li%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Learning%20without%20Forgetting&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1606.09282.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 31, "section_title": "Continual & Lifelong Learning", "source_note": "Knowledge distillation for continual learning", "title": "Learning without Forgetting", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Mallya & Lazebnik", "id": 575, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=PackNet%3A%20Adding%20Multiple%20Tasks%20to%20a%20Single%20Network&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=PackNet%3A%20Adding%20Multiple%20Tasks%20to%20a%20Single%20Network%20Mallya%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=PackNet%3A%20Adding%20Multiple%20Tasks%20to%20a%20Single%20Network&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 31, "section_title": "Continual & Lifelong Learning", "source_note": "Iterative pruning for multi-task", "title": "PackNet: Adding Multiple Tasks to a Single Network", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Rolnick et al.", "id": 576, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Experience%20Replay%20for%20Continual%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Experience%20Replay%20for%20Continual%20Learning%20Rolnick%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Experience%20Replay%20for%20Continual%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 31, "section_title": "Continual & Lifelong Learning", "source_note": "Replay buffers", "title": "Experience Replay for Continual Learning", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "De Lange et al.", "id": 577, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Comprehensive%20Survey%20of%20Continual%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Comprehensive%20Survey%20of%20Continual%20Learning%20De%20Lange%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Comprehensive%20Survey%20of%20Continual%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 31, "section_title": "Continual & Lifelong Learning", "source_note": "Modern continual learning survey", "title": "A Comprehensive Survey of Continual Learning", "work_type": "Survey or review", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Gururangan et al.", "id": 578, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Continual%20Pre-training%20of%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Continual%20Pre-training%20of%20Language%20Models%20Gururangan%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Continual%20Pre-training%20of%20Language%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 31, "section_title": "Continual & Lifelong Learning", "source_note": "Domain-adaptive pretraining", "title": "Continual Pre-training of Language Models", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Wang et al.", "id": 579, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=TRACE%3A%20A%20Comprehensive%20Benchmark%20for%20Continual%20Learning%20in%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=TRACE%3A%20A%20Comprehensive%20Benchmark%20for%20Continual%20Learning%20in%20LLMs%20Wang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=TRACE%3A%20A%20Comprehensive%20Benchmark%20for%20Continual%20Learning%20in%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 31, "section_title": "Continual & Lifelong Learning", "source_note": "LLM continual learning benchmark", "title": "TRACE: A Comprehensive Benchmark for Continual Learning in LLMs", "work_type": "Benchmark or dataset paper", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 580, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Online%20Continual%20Learning%20for%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Online%20Continual%20Learning%20for%20LLMs%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Online%20Continual%20Learning%20for%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 31, "section_title": "Continual & Lifelong Learning", "source_note": "Online adaptation of LLMs", "title": "Online Continual Learning for LLMs", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "He et al.", "id": 581, "links": { "canonical_url": "https://arxiv.org/abs/1911.05722", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1911.05722.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Momentum%20Contrast%20for%20Unsupervised%20Visual%20Representation%20Learning%20%28MoCo%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Momentum%20Contrast%20for%20Unsupervised%20Visual%20Representation%20Learning%20%28MoCo%29%20He%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Momentum%20Contrast%20for%20Unsupervised%20Visual%20Representation%20Learning%20%28MoCo%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1911.05722.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "MoCo — momentum contrast", "title": "Momentum Contrast for Unsupervised Visual Representation Learning (MoCo)", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Chen et al.", "id": 582, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MoCo%20v2&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MoCo%20v2%20Chen%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=MoCo%20v2&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "Improved MoCo", "title": "MoCo v2", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Chen et al.", "id": 583, "links": { "canonical_url": "https://arxiv.org/abs/2002.05709", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2002.05709.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Simple%20Framework%20for%20Contrastive%20Learning%20%28SimCLR%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Simple%20Framework%20for%20Contrastive%20Learning%20%28SimCLR%29%20Chen%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Simple%20Framework%20for%20Contrastive%20Learning%20%28SimCLR%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2002.05709.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "SimCLR — simple contrastive", "title": "A Simple Framework for Contrastive Learning (SimCLR)", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Grill et al.", "id": 584, "links": { "canonical_url": "https://arxiv.org/abs/2006.07733", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2006.07733.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Bootstrap%20Your%20Own%20Latent%20%28BYOL%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Bootstrap%20Your%20Own%20Latent%20%28BYOL%29%20Grill%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Bootstrap%20Your%20Own%20Latent%20%28BYOL%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2006.07733.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "No negatives needed", "title": "Bootstrap Your Own Latent (BYOL)", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Zbontar et al.", "id": 585, "links": { "canonical_url": "https://arxiv.org/abs/2103.03230", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2103.03230.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Barlow%20Twins%3A%20Self-Supervised%20Learning%20via%20Redundancy%20Reduction&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Barlow%20Twins%3A%20Self-Supervised%20Learning%20via%20Redundancy%20Reduction%20Zbontar%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Barlow%20Twins%3A%20Self-Supervised%20Learning%20via%20Redundancy%20Reduction&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2103.03230.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "Redundancy reduction", "title": "Barlow Twins: Self-Supervised Learning via Redundancy Reduction", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Bardes, Ponce, LeCun", "id": 586, "links": { "canonical_url": "https://arxiv.org/abs/2105.04906", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2105.04906.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=VICReg%3A%20Variance-Invariance-Covariance%20Regularization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=VICReg%3A%20Variance-Invariance-Covariance%20Regularization%20Bardes%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=VICReg%3A%20Variance-Invariance-Covariance%20Regularization&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2105.04906.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "Variance-invariance-covariance", "title": "VICReg: Variance-Invariance-Covariance Regularization", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Caron et al.", "id": 587, "links": { "canonical_url": "https://arxiv.org/abs/2104.14294", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2104.14294.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DINO%3A%20Emerging%20Properties%20in%20Self-Supervised%20Vision%20Transformers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DINO%3A%20Emerging%20Properties%20in%20Self-Supervised%20Vision%20Transformers%20Caron%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=DINO%3A%20Emerging%20Properties%20in%20Self-Supervised%20Vision%20Transformers&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2104.14294.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "Self-distillation for ViT", "title": "DINO: Emerging Properties in Self-Supervised Vision Transformers", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Oquab et al.", "id": 588, "links": { "canonical_url": "https://arxiv.org/abs/2304.07193", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2304.07193.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DINOv2%3A%20Learning%20Robust%20Visual%20Features&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DINOv2%3A%20Learning%20Robust%20Visual%20Features%20Oquab%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=DINOv2%3A%20Learning%20Robust%20Visual%20Features&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2304.07193.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "Improved self-supervised vision", "title": "DINOv2: Learning Robust Visual Features", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "He et al.", "id": 589, "links": { "canonical_url": "https://arxiv.org/abs/2111.06377", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2111.06377.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Masked%20Autoencoders%20Are%20Scalable%20Vision%20Learners%20%28MAE%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Masked%20Autoencoders%20Are%20Scalable%20Vision%20Learners%20%28MAE%29%20He%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Masked%20Autoencoders%20Are%20Scalable%20Vision%20Learners%20%28MAE%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2111.06377.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "Masked image modeling", "title": "Masked Autoencoders Are Scalable Vision Learners (MAE)", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Xie et al.", "id": 590, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SimMIM%3A%20A%20Simple%20Framework%20for%20Masked%20Image%20Modeling&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SimMIM%3A%20A%20Simple%20Framework%20for%20Masked%20Image%20Modeling%20Xie%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=SimMIM%3A%20A%20Simple%20Framework%20for%20Masked%20Image%20Modeling&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "Simplified masked image modeling", "title": "SimMIM: A Simple Framework for Masked Image Modeling", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Bao, Dong, Wei", "id": 591, "links": { "canonical_url": "https://arxiv.org/abs/2106.08254", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2106.08254.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BEiT%3A%20BERT%20Pre-Training%20of%20Image%20Transformers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BEiT%3A%20BERT%20Pre-Training%20of%20Image%20Transformers%20Bao%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=BEiT%3A%20BERT%20Pre-Training%20of%20Image%20Transformers&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2106.08254.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "BERT-style pretraining for vision", "title": "BEiT: BERT Pre-Training of Image Transformers", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Khosla et al.", "id": 592, "links": { "canonical_url": "https://arxiv.org/abs/2004.11362", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2004.11362.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Supervised%20Contrastive%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Supervised%20Contrastive%20Learning%20Khosla%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Supervised%20Contrastive%20Learning&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2004.11362.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "SupCon loss", "title": "Supervised Contrastive Learning", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Arora et al.", "id": 593, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Understanding%20Contrastive%20Representation%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Understanding%20Contrastive%20Representation%20Learning%20Arora%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Understanding%20Contrastive%20Representation%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "Theoretical analysis of contrastive learning", "title": "Understanding Contrastive Representation Learning", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Liu et al.", "id": 594, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Self-Supervised%20Learning%3A%20Generative%20or%20Contrastive%20%28Survey%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Self-Supervised%20Learning%3A%20Generative%20or%20Contrastive%20%28Survey%29%20Liu%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Self-Supervised%20Learning%3A%20Generative%20or%20Contrastive%20%28Survey%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "SSL survey", "title": "Self-Supervised Learning: Generative or Contrastive (Survey)", "work_type": "Survey or review", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Assran et al.", "id": 595, "links": { "canonical_url": "https://arxiv.org/abs/2301.08243", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2301.08243.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=I-JEPA%3A%20Image%20Joint-Embedding%20Predictive%20Architecture&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=I-JEPA%3A%20Image%20Joint-Embedding%20Predictive%20Architecture%20Assran%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=I-JEPA%3A%20Image%20Joint-Embedding%20Predictive%20Architecture&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2301.08243.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 32, "section_title": "Self-Supervised & Contrastive Learning", "source_note": "LeCun's JEPA for vision", "title": "I-JEPA: Image Joint-Embedding Predictive Architecture", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "McMahan et al.", "id": 596, "links": { "canonical_url": "https://arxiv.org/abs/1602.05629", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1602.05629.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Communication-Efficient%20Learning%20of%20Deep%20Networks%20from%20Decentralized%20Data%20%28FedAvg%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Communication-Efficient%20Learning%20of%20Deep%20Networks%20from%20Decentralized%20Data%20%28FedAvg%29%20McMahan%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Communication-Efficient%20Learning%20of%20Deep%20Networks%20from%20Decentralized%20Data%20%28FedAvg%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1602.05629.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 33, "section_title": "Federated & Privacy-Preserving AI", "source_note": "Federated averaging", "title": "Communication-Efficient Learning of Deep Networks from Decentralized Data (FedAvg)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Li et al.", "id": 597, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Federated%20Learning%3A%20Challenges%2C%20Methods%2C%20and%20Future%20Directions&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Federated%20Learning%3A%20Challenges%2C%20Methods%2C%20and%20Future%20Directions%20Li%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Federated%20Learning%3A%20Challenges%2C%20Methods%2C%20and%20Future%20Directions&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 33, "section_title": "Federated & Privacy-Preserving AI", "source_note": "FL survey", "title": "Federated Learning: Challenges, Methods, and Future Directions", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Kairouz et al.", "id": 598, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Advances%20and%20Open%20Problems%20in%20Federated%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Advances%20and%20Open%20Problems%20in%20Federated%20Learning%20Kairouz%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Advances%20and%20Open%20Problems%20in%20Federated%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 33, "section_title": "Federated & Privacy-Preserving AI", "source_note": "Comprehensive FL challenges", "title": "Advances and Open Problems in Federated Learning", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Abadi et al.", "id": 599, "links": { "canonical_url": "https://arxiv.org/abs/1607.00133", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1607.00133.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Deep%20Learning%20with%20Differential%20Privacy&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Deep%20Learning%20with%20Differential%20Privacy%20Abadi%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Deep%20Learning%20with%20Differential%20Privacy&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1607.00133.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 33, "section_title": "Federated & Privacy-Preserving AI", "source_note": "DP-SGD", "title": "Deep Learning with Differential Privacy", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Dwork & Roth", "id": 600, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Algorithmic%20Foundations%20of%20Differential%20Privacy&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Algorithmic%20Foundations%20of%20Differential%20Privacy%20Dwork%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Algorithmic%20Foundations%20of%20Differential%20Privacy&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 33, "section_title": "Federated & Privacy-Preserving AI", "source_note": "DP theory foundations", "title": "The Algorithmic Foundations of Differential Privacy", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Mohassel & Zhang", "id": 601, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SecureML%3A%20A%20System%20for%20Scalable%20Privacy-Preserving%20ML&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SecureML%3A%20A%20System%20for%20Scalable%20Privacy-Preserving%20ML%20Mohassel%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=SecureML%3A%20A%20System%20for%20Scalable%20Privacy-Preserving%20ML&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 33, "section_title": "Federated & Privacy-Preserving AI", "source_note": "Secure computation for ML", "title": "SecureML: A System for Scalable Privacy-Preserving ML", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Shokri et al.", "id": 602, "links": { "canonical_url": "https://arxiv.org/abs/1610.05820", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1610.05820.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Membership%20Inference%20Attacks%20Against%20ML%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Membership%20Inference%20Attacks%20Against%20ML%20Models%20Shokri%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Membership%20Inference%20Attacks%20Against%20ML%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1610.05820.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 33, "section_title": "Federated & Privacy-Preserving AI", "source_note": "Privacy attacks on models", "title": "Membership Inference Attacks Against ML Models", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Bourtoule et al.", "id": 603, "links": { "canonical_url": "https://arxiv.org/abs/2103.03279", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2103.03279.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Machine%20Unlearning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Machine%20Unlearning%20Bourtoule%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Machine%20Unlearning&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2103.03279.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 33, "section_title": "Federated & Privacy-Preserving AI", "source_note": "Removing data from trained models", "title": "Machine Unlearning", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Li et al.", "id": 604, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=FedProx%3A%20Federated%20Optimization%20in%20Heterogeneous%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=FedProx%3A%20Federated%20Optimization%20in%20Heterogeneous%20Networks%20Li%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=FedProx%3A%20Federated%20Optimization%20in%20Heterogeneous%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 33, "section_title": "Federated & Privacy-Preserving AI", "source_note": "Handling non-IID data in FL", "title": "FedProx: Federated Optimization in Heterogeneous Networks", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Karimireddy et al.", "id": 605, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scaffold%3A%20Stochastic%20Controlled%20Averaging%20for%20FL&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scaffold%3A%20Stochastic%20Controlled%20Averaging%20for%20FL%20Karimireddy%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scaffold%3A%20Stochastic%20Controlled%20Averaging%20for%20FL&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 33, "section_title": "Federated & Privacy-Preserving AI", "source_note": "Variance reduction in FL", "title": "Scaffold: Stochastic Controlled Averaging for FL", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Russakovsky et al.", "id": 606, "links": { "canonical_url": "https://arxiv.org/abs/1409.0575", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1409.0575.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ImageNet%20Large%20Scale%20Visual%20Recognition%20Challenge&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ImageNet%20Large%20Scale%20Visual%20Recognition%20Challenge%20Russakovsky%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=ImageNet%20Large%20Scale%20Visual%20Recognition%20Challenge&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1409.0575.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "ImageNet benchmark", "title": "ImageNet Large Scale Visual Recognition Challenge", "work_type": "Benchmark or dataset paper", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Rajpurkar et al.", "id": 607, "links": { "canonical_url": "https://arxiv.org/abs/1606.05250", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1606.05250.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SQuAD%3A%20100%2C000%2B%20Questions%20for%20Machine%20Comprehension&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SQuAD%3A%20100%2C000%2B%20Questions%20for%20Machine%20Comprehension%20Rajpurkar%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=SQuAD%3A%20100%2C000%2B%20Questions%20for%20Machine%20Comprehension&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1606.05250.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Reading comprehension", "title": "SQuAD: 100,000+ Questions for Machine Comprehension", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Wang et al.", "id": 608, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GLUE%3A%20A%20Multi-Task%20Benchmark%20for%20NLU&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GLUE%3A%20A%20Multi-Task%20Benchmark%20for%20NLU%20Wang%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=GLUE%3A%20A%20Multi-Task%20Benchmark%20for%20NLU&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "NLU benchmark", "title": "GLUE: A Multi-Task Benchmark for NLU", "work_type": "Benchmark or dataset paper", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Wang et al.", "id": 609, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SuperGLUE%3A%20A%20Stickier%20Benchmark%20for%20General-Purpose%20Language%20Understanding&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SuperGLUE%3A%20A%20Stickier%20Benchmark%20for%20General-Purpose%20Language%20Understanding%20Wang%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=SuperGLUE%3A%20A%20Stickier%20Benchmark%20for%20General-Purpose%20Language%20Understanding&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Harder NLU benchmark", "title": "SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding", "work_type": "Benchmark or dataset paper", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Hendrycks et al.", "id": 610, "links": { "canonical_url": "https://arxiv.org/abs/2009.03300", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2009.03300.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MMLU%3A%20Measuring%20Massive%20Multitask%20Language%20Understanding&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MMLU%3A%20Measuring%20Massive%20Multitask%20Language%20Understanding%20Hendrycks%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=MMLU%3A%20Measuring%20Massive%20Multitask%20Language%20Understanding&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2009.03300.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "57-subject knowledge test", "title": "MMLU: Measuring Massive Multitask Language Understanding", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Wang et al.", "id": 611, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MMLU-Pro&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MMLU-Pro%20Wang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=MMLU-Pro&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Harder MMLU variant", "title": "MMLU-Pro", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Srivastava et al.", "id": 612, "links": { "canonical_url": "https://arxiv.org/abs/2206.04615", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2206.04615.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BIG-Bench%3A%20Beyond%20the%20Imitation%20Game&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BIG-Bench%3A%20Beyond%20the%20Imitation%20Game%20Srivastava%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=BIG-Bench%3A%20Beyond%20the%20Imitation%20Game&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2206.04615.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "204 collaborative tasks", "title": "BIG-Bench: Beyond the Imitation Game", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zellers et al.", "id": 613, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=HellaSwag%3A%20Can%20a%20Machine%20Really%20Finish%20Your%20Sentence%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=HellaSwag%3A%20Can%20a%20Machine%20Really%20Finish%20Your%20Sentence%3F%20Zellers%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=HellaSwag%3A%20Can%20a%20Machine%20Really%20Finish%20Your%20Sentence%3F&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Common-sense completion", "title": "HellaSwag: Can a Machine Really Finish Your Sentence?", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Clark et al.", "id": 614, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ARC%3A%20Think%20You%20Have%20Solved%20Question%20Answering%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ARC%3A%20Think%20You%20Have%20Solved%20Question%20Answering%3F%20Clark%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=ARC%3A%20Think%20You%20Have%20Solved%20Question%20Answering%3F&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Science reasoning", "title": "ARC: Think You Have Solved Question Answering?", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Sakaguchi et al.", "id": 615, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=WinoGrande%3A%20An%20Adversarial%20Winograd%20Schema%20Challenge&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=WinoGrande%3A%20An%20Adversarial%20Winograd%20Schema%20Challenge%20Sakaguchi%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=WinoGrande%3A%20An%20Adversarial%20Winograd%20Schema%20Challenge&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Common-sense reasoning", "title": "WinoGrande: An Adversarial Winograd Schema Challenge", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Lin, Hilton, Evans", "id": 616, "links": { "canonical_url": "https://arxiv.org/abs/2109.07958", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2109.07958.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=TruthfulQA%3A%20Measuring%20How%20Models%20Mimic%20Human%20Falsehoods&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=TruthfulQA%3A%20Measuring%20How%20Models%20Mimic%20Human%20Falsehoods%20Lin%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=TruthfulQA%3A%20Measuring%20How%20Models%20Mimic%20Human%20Falsehoods&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2109.07958.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Truthfulness benchmark", "title": "TruthfulQA: Measuring How Models Mimic Human Falsehoods", "work_type": "Benchmark or dataset paper", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Zheng et al.", "id": 617, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Chatbot%20Arena%20/%20LMSYS%20Leaderboard&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Chatbot%20Arena%20/%20LMSYS%20Leaderboard%20Zheng%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Chatbot%20Arena%20/%20LMSYS%20Leaderboard&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Human preference rankings", "title": "Chatbot Arena / LMSYS Leaderboard", "work_type": "Benchmark or dataset paper", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zheng et al.", "id": 618, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MT-Bench&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MT-Bench%20Zheng%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=MT-Bench&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Multi-turn conversation benchmark", "title": "MT-Bench", "work_type": "Benchmark or dataset paper", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Li et al.", "id": 619, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AlpacaEval&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AlpacaEval%20Li%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=AlpacaEval&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Automatic LLM evaluation", "title": "AlpacaEval", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Rein et al.", "id": 620, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GPQA%3A%20A%20Graduate-Level%20Google-Proof%20Q%26A%20Benchmark&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GPQA%3A%20A%20Graduate-Level%20Google-Proof%20Q%26A%20Benchmark%20Rein%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=GPQA%3A%20A%20Graduate-Level%20Google-Proof%20Q%26A%20Benchmark&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Expert-level questions", "title": "GPQA: A Graduate-Level Google-Proof Q&A Benchmark", "work_type": "Benchmark or dataset paper", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "White et al.", "id": 621, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LiveBench%3A%20A%20Challenging%2C%20Contamination-Free%20LLM%20Benchmark&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LiveBench%3A%20A%20Challenging%2C%20Contamination-Free%20LLM%20Benchmark%20White%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=LiveBench%3A%20A%20Challenging%2C%20Contamination-Free%20LLM%20Benchmark&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Contamination-free eval", "title": "LiveBench: A Challenging, Contamination-Free LLM Benchmark", "work_type": "Benchmark or dataset paper", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Hendrycks; Cobbe", "id": 622, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MATH%20and%20GSM8K%20%28mentioned%20earlier%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MATH%20and%20GSM8K%20%28mentioned%20earlier%29%20Hendrycks%3B%20Cobbe%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=MATH%20and%20GSM8K%20%28mentioned%20earlier%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Math evaluation", "title": "MATH and GSM8K (mentioned earlier)", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Chen; Austin", "id": 623, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=HumanEval%20and%20MBPP%20%28mentioned%20earlier%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=HumanEval%20and%20MBPP%20%28mentioned%20earlier%29%20Chen%3B%20Austin%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=HumanEval%20and%20MBPP%20%28mentioned%20earlier%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Code evaluation", "title": "HumanEval and MBPP (mentioned earlier)", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Shi et al.", "id": 624, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MGSM%3A%20Multilingual%20Grade%20School%20Math&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MGSM%3A%20Multilingual%20Grade%20School%20Math%20Shi%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=MGSM%3A%20Multilingual%20Grade%20School%20Math&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Multilingual math", "title": "MGSM: Multilingual Grade School Math", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "OpenAI", "id": 625, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SimpleQA&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SimpleQA%20OpenAI%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=SimpleQA&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Factuality benchmark", "title": "SimpleQA", "work_type": "Benchmark or dataset paper", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zhou et al.", "id": 626, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=IFEval%3A%20Instruction-Following%20Evaluation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=IFEval%3A%20Instruction-Following%20Evaluation%20Zhou%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=IFEval%3A%20Instruction-Following%20Evaluation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Instruction following", "title": "IFEval: Instruction-Following Evaluation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Sprague et al.", "id": 627, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MuSR%3A%20Multi-Step%20Soft%20Reasoning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MuSR%3A%20Multi-Step%20Soft%20Reasoning%20Sprague%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=MuSR%3A%20Multi-Step%20Soft%20Reasoning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Multi-step reasoning", "title": "MuSR: Multi-Step Soft Reasoning", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zhou; Xie et al.", "id": 628, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Agentic%20Benchmarks%3A%20WebArena%2C%20OSWorld%2C%20etc.&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Agentic%20Benchmarks%3A%20WebArena%2C%20OSWorld%2C%20etc.%20Zhou%3B%20Xie%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Agentic%20Benchmarks%3A%20WebArena%2C%20OSWorld%2C%20etc.&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Agent environment benchmarks", "title": "Agentic Benchmarks: WebArena, OSWorld, etc.", "work_type": "Benchmark or dataset paper", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Lin et al.", "id": 629, "links": { "canonical_url": "https://arxiv.org/abs/1405.0312", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1405.0312.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=COCO%3A%20Common%20Objects%20in%20Context&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=COCO%3A%20Common%20Objects%20in%20Context%20Lin%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=COCO%3A%20Common%20Objects%20in%20Context&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1405.0312.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Object detection/captioning", "title": "COCO: Common Objects in Context", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Liang et al.", "id": 630, "links": { "canonical_url": "https://arxiv.org/abs/2211.09110", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2211.09110.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Holistic%20Evaluation%20of%20Language%20Models%20%28HELM%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Holistic%20Evaluation%20of%20Language%20Models%20%28HELM%29%20Liang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Holistic%20Evaluation%20of%20Language%20Models%20%28HELM%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2211.09110.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 34, "section_title": "Evaluation & Benchmarks", "source_note": "Comprehensive LM evaluation", "title": "Holistic Evaluation of Language Models (HELM)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Amodei et al.", "id": 631, "links": { "canonical_url": "https://arxiv.org/abs/1606.06565", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1606.06565.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Concrete%20Problems%20in%20AI%20Safety&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Concrete%20Problems%20in%20AI%20Safety%20Amodei%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Concrete%20Problems%20in%20AI%20Safety&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1606.06565.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Practical safety problems", "title": "Concrete Problems in AI Safety", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Ji et al.", "id": 632, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AI%20Alignment%3A%20A%20Comprehensive%20Survey&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AI%20Alignment%3A%20A%20Comprehensive%20Survey%20Ji%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=AI%20Alignment%3A%20A%20Comprehensive%20Survey&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Alignment survey", "title": "AI Alignment: A Comprehensive Survey", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as book or textbook, not as a research paper.", "severity": "warning" } ], "authors": "Christian", "id": 633, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Alignment%20Problem%20%28overview%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Alignment%20Problem%20%28overview%29%20Christian%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Alignment%20Problem%20%28overview%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "AI alignment book", "title": "The Alignment Problem (overview)", "work_type": "Book or textbook", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Skalse et al.", "id": 634, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Reward%20Hacking%20in%20Reinforcement%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Reward%20Hacking%20in%20Reinforcement%20Learning%20Skalse%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Reward%20Hacking%20in%20Reinforcement%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Reward misspecification", "title": "Reward Hacking in Reinforcement Learning", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Leike et al.", "id": 635, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scalable%20Agent%20Alignment%20via%20Reward%20Modeling%20%28Anthropic%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scalable%20Agent%20Alignment%20via%20Reward%20Modeling%20%28Anthropic%29%20Leike%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scalable%20Agent%20Alignment%20via%20Reward%20Modeling%20%28Anthropic%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Recursive reward modeling", "title": "Scalable Agent Alignment via Reward Modeling (Anthropic)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Turpin et al.", "id": 636, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Language%20Models%20Don%27t%20Always%20Say%20What%20They%20Think%3A%20Unfaithful%20Explanations&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Language%20Models%20Don%27t%20Always%20Say%20What%20They%20Think%3A%20Unfaithful%20Explanations%20Turpin%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Language%20Models%20Don%27t%20Always%20Say%20What%20They%20Think%3A%20Unfaithful%20Explanations&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Sycophancy and unfaithfulness", "title": "Language Models Don't Always Say What They Think: Unfaithful Explanations", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Hubinger et al.", "id": 637, "links": { "canonical_url": "https://arxiv.org/abs/2401.05566", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2401.05566.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Sleeper%20Agents%3A%20Training%20Deceptive%20LLMs%20that%20Persist%20Through%20Safety%20Training&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Sleeper%20Agents%3A%20Training%20Deceptive%20LLMs%20that%20Persist%20Through%20Safety%20Training%20Hubinger%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Sleeper%20Agents%3A%20Training%20Deceptive%20LLMs%20that%20Persist%20Through%20Safety%20Training&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2401.05566.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Backdoor persistence", "title": "Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Hubinger et al.", "id": 638, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Risks%20from%20Learned%20Optimization%20in%20Advanced%20ML%20Systems%20%28Mesa-Optimizers%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Risks%20from%20Learned%20Optimization%20in%20Advanced%20ML%20Systems%20%28Mesa-Optimizers%29%20Hubinger%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Risks%20from%20Learned%20Optimization%20in%20Advanced%20ML%20Systems%20%28Mesa-Optimizers%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Inner alignment", "title": "Risks from Learned Optimization in Advanced ML Systems (Mesa-Optimizers)", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Shah et al.", "id": 639, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Goal%20Misgeneralization%3A%20Why%20Correct%20Specifications%20Aren%27t%20Enough&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Goal%20Misgeneralization%3A%20Why%20Correct%20Specifications%20Aren%27t%20Enough%20Shah%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Goal%20Misgeneralization%3A%20Why%20Correct%20Specifications%20Aren%27t%20Enough&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Goal misgeneralization", "title": "Goal Misgeneralization: Why Correct Specifications Aren't Enough", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Ganguli et al.", "id": 640, "links": { "canonical_url": "https://arxiv.org/abs/2202.03286", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2202.03286.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Red%20Teaming%20Language%20Models%20to%20Reduce%20Harms&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Red%20Teaming%20Language%20Models%20to%20Reduce%20Harms%20Ganguli%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Red%20Teaming%20Language%20Models%20to%20Reduce%20Harms&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2202.03286.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Red teaming methodology", "title": "Red Teaming Language Models to Reduce Harms", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Perez et al.", "id": 641, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Red%20Teaming%20Language%20Models%20with%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Red%20Teaming%20Language%20Models%20with%20Language%20Models%20Perez%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Red%20Teaming%20Language%20Models%20with%20Language%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Automated red teaming", "title": "Red Teaming Language Models with Language Models", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Zou et al.", "id": 642, "links": { "canonical_url": "https://arxiv.org/abs/2307.15043", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2307.15043.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Universal%20and%20Transferable%20Adversarial%20Attacks%20on%20Aligned%20LMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Universal%20and%20Transferable%20Adversarial%20Attacks%20on%20Aligned%20LMs%20Zou%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Universal%20and%20Transferable%20Adversarial%20Attacks%20on%20Aligned%20LMs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2307.15043.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "GCG attack on aligned LLMs", "title": "Universal and Transferable Adversarial Attacks on Aligned LMs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Wei et al.", "id": 643, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Jailbroken%3A%20How%20Does%20LLM%20Safety%20Training%20Fail%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Jailbroken%3A%20How%20Does%20LLM%20Safety%20Training%20Fail%3F%20Wei%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Jailbroken%3A%20How%20Does%20LLM%20Safety%20Training%20Fail%3F&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Jailbreak analysis", "title": "Jailbroken: How Does LLM Safety Training Fail?", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Pan et al.", "id": 644, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Do%20the%20Rewards%20Justify%20the%20Means%3F%20Measuring%20Trade-Offs%20Between%20Rewards%20and%20Ethical%20Behavior&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Do%20the%20Rewards%20Justify%20the%20Means%3F%20Measuring%20Trade-Offs%20Between%20Rewards%20and%20Ethical%20Behavior%20Pan%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Do%20the%20Rewards%20Justify%20the%20Means%3F%20Measuring%20Trade-Offs%20Between%20Rewards%20and%20Ethical%20Behavior&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Safety-performance tradeoffs", "title": "Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "OpenAI", "id": 645, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Model%20Spec%20%28OpenAI%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Model%20Spec%20%28OpenAI%29%20OpenAI%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Model%20Spec%20%28OpenAI%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "LLM behavior specification", "title": "The Model Spec (OpenAI)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Anthropic", "id": 646, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Claude%27s%20Character%20%28Anthropic%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Claude%27s%20Character%20%28Anthropic%29%20Anthropic%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Claude%27s%20Character%20%28Anthropic%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Values-based AI behavior", "title": "Claude's Character (Anthropic)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Anthropic", "id": 647, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Responsible%20Scaling%20Policies%20%28RSPs%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Responsible%20Scaling%20Policies%20%28RSPs%29%20Anthropic%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Responsible%20Scaling%20Policies%20%28RSPs%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Scaling safety commitments", "title": "Responsible Scaling Policies (RSPs)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Bengio et al.", "id": 648, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Managing%20AI%20Risks%20in%20an%20Era%20of%20Rapid%20Progress&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Managing%20AI%20Risks%20in%20an%20Era%20of%20Rapid%20Progress%20Bengio%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Managing%20AI%20Risks%20in%20an%20Era%20of%20Rapid%20Progress&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Open letter on AI risks", "title": "Managing AI Risks in an Era of Rapid Progress", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Future of Life", "id": 649, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Pause%20Giant%20AI%20Experiments%3A%20An%20Open%20Letter&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Pause%20Giant%20AI%20Experiments%3A%20An%20Open%20Letter%20Future%20of%20Life%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Pause%20Giant%20AI%20Experiments%3A%20An%20Open%20Letter&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "AI moratorium call", "title": "Pause Giant AI Experiments: An Open Letter", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Bender et al.", "id": 650, "links": { "canonical_url": "https://dl.acm.org/doi/10.1145/3442188.3445922", "corrected_by_audit": false, "direct_url": "https://dl.acm.org/doi/10.1145/3442188.3445922", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=On%20the%20Dangers%20of%20Stochastic%20Parrots&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=On%20the%20Dangers%20of%20Stochastic%20Parrots%20Bender%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=On%20the%20Dangers%20of%20Stochastic%20Parrots&sort=relevance" }, "supplied_direct_url": "https://dl.acm.org/doi/10.1145/3442188.3445922" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "LLM risks and harms", "title": "On the Dangers of Stochastic Parrots", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as book or textbook, not as a research paper.", "severity": "warning" } ], "authors": "Barocas, Hardt, Narayanan", "id": 651, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Fairness%20and%20Machine%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Fairness%20and%20Machine%20Learning%20Barocas%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Fairness%20and%20Machine%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "ML fairness textbook", "title": "Fairness and Machine Learning", "work_type": "Book or textbook", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Buolamwini & Gebru", "id": 652, "links": { "canonical_url": "https://proceedings.mlr.press/v81/buolamwini18a.html", "corrected_by_audit": false, "direct_url": "https://proceedings.mlr.press/v81/buolamwini18a.html", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Gender%20Shades%3A%20Intersectional%20Accuracy%20Disparities%20in%20Commercial%20Gender%20Classification&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Gender%20Shades%3A%20Intersectional%20Accuracy%20Disparities%20in%20Commercial%20Gender%20Classification%20Buolamwini%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Gender%20Shades%3A%20Intersectional%20Accuracy%20Disparities%20in%20Commercial%20Gender%20Classification&sort=relevance" }, "supplied_direct_url": "https://proceedings.mlr.press/v81/buolamwini18a.html" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Bias in facial recognition", "title": "Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Gebru et al.", "id": 653, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Datasheets%20for%20Datasets&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Datasheets%20for%20Datasets%20Gebru%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Datasheets%20for%20Datasets&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Dataset documentation", "title": "Datasheets for Datasets", "work_type": "Benchmark or dataset paper", "year": 2021, "year_display": "2021" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as technical or industry report, not as a research paper.", "severity": "warning" } ], "authors": "Mitchell et al.", "id": 654, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Model%20Cards%20for%20Model%20Reporting&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Model%20Cards%20for%20Model%20Reporting%20Mitchell%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Model%20Cards%20for%20Model%20Reporting&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "Model documentation", "title": "Model Cards for Model Reporting", "work_type": "Technical or industry report", "year": 2019, "year_display": "2019" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as policy or official document, not as a research paper.", "severity": "warning" } ], "authors": "White House", "id": 655, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Blueprint%20for%20an%20AI%20Bill%20of%20Rights&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Blueprint%20for%20an%20AI%20Bill%20of%20Rights%20White%20House%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Blueprint%20for%20an%20AI%20Bill%20of%20Rights&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 35, "section_title": "AI Safety, Ethics & Alignment", "source_note": "AI rights framework", "title": "Blueprint for an AI Bill of Rights", "work_type": "Policy or official document", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Ribeiro et al.", "id": 656, "links": { "canonical_url": "https://arxiv.org/abs/1602.04938", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1602.04938.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=%22Why%20Should%20I%20Trust%20You%3F%22%20Explaining%20the%20Predictions%20of%20Any%20Classifier%20%28LIME%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=%22Why%20Should%20I%20Trust%20You%3F%22%20Explaining%20the%20Predictions%20of%20Any%20Classifier%20%28LIME%29%20Ribeiro%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=%22Why%20Should%20I%20Trust%20You%3F%22%20Explaining%20the%20Predictions%20of%20Any%20Classifier%20%28LIME%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1602.04938.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Local interpretable explanations", "title": "\"Why Should I Trust You?\" Explaining the Predictions of Any Classifier (LIME)", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Lundberg & Lee", "id": 657, "links": { "canonical_url": "https://arxiv.org/abs/1705.07874", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1705.07874.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Unified%20Approach%20to%20Interpreting%20Model%20Predictions%20%28SHAP%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Unified%20Approach%20to%20Interpreting%20Model%20Predictions%20%28SHAP%29%20Lundberg%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Unified%20Approach%20to%20Interpreting%20Model%20Predictions%20%28SHAP%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1705.07874.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Shapley values for ML", "title": "A Unified Approach to Interpreting Model Predictions (SHAP)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Selvaraju et al.", "id": 658, "links": { "canonical_url": "https://arxiv.org/abs/1610.02391", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1610.02391.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Grad-CAM%3A%20Visual%20Explanations%20from%20Deep%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Grad-CAM%3A%20Visual%20Explanations%20from%20Deep%20Networks%20Selvaraju%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Grad-CAM%3A%20Visual%20Explanations%20from%20Deep%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1610.02391.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Gradient-based attention maps", "title": "Grad-CAM: Visual Explanations from Deep Networks", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Jain & Wallace", "id": 659, "links": { "canonical_url": "https://arxiv.org/abs/1902.10186", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1902.10186.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Attention%20is%20not%20Explanation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Attention%20is%20not%20Explanation%20Jain%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Attention%20is%20not%20Explanation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1902.10186.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Questioning attention as explanation", "title": "Attention is not Explanation", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Wiegreffe & Pinter", "id": 660, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Attention%20is%20not%20not%20Explanation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Attention%20is%20not%20not%20Explanation%20Wiegreffe%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Attention%20is%20not%20not%20Explanation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Defense of attention explanations", "title": "Attention is not not Explanation", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Bau et al.", "id": 661, "links": { "canonical_url": "https://arxiv.org/abs/1704.05796", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1704.05796.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Network%20Dissection%3A%20Quantifying%20Interpretability%20of%20Deep%20Visual%20Representations&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Network%20Dissection%3A%20Quantifying%20Interpretability%20of%20Deep%20Visual%20Representations%20Bau%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Network%20Dissection%3A%20Quantifying%20Interpretability%20of%20Deep%20Visual%20Representations&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1704.05796.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Unit-level interpretability", "title": "Network Dissection: Quantifying Interpretability of Deep Visual Representations", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Olah et al.", "id": 662, "links": { "canonical_url": "https://distill.pub/2020/circuits/zoom-in/", "corrected_by_audit": false, "direct_url": "https://distill.pub/2020/circuits/zoom-in/", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Zoom%20In%3A%20An%20Introduction%20to%20Circuits&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Zoom%20In%3A%20An%20Introduction%20to%20Circuits%20Olah%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Zoom%20In%3A%20An%20Introduction%20to%20Circuits&sort=relevance" }, "supplied_direct_url": "https://distill.pub/2020/circuits/zoom-in/" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Mechanistic interpretability", "title": "Zoom In: An Introduction to Circuits", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Elhage et al.", "id": 663, "links": { "canonical_url": "https://transformer-circuits.pub/2021/framework/index.html", "corrected_by_audit": false, "direct_url": "https://transformer-circuits.pub/2021/framework/index.html", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Mathematical%20Framework%20for%20Transformer%20Circuits&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Mathematical%20Framework%20for%20Transformer%20Circuits%20Elhage%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Mathematical%20Framework%20for%20Transformer%20Circuits&sort=relevance" }, "supplied_direct_url": "https://transformer-circuits.pub/2021/framework/index.html" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Transformer mechanistic analysis", "title": "A Mathematical Framework for Transformer Circuits", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Elhage et al.", "id": 664, "links": { "canonical_url": "https://transformer-circuits.pub/2022/toy_model/index.html", "corrected_by_audit": false, "direct_url": "https://transformer-circuits.pub/2022/toy_model/index.html", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Toy%20Models%20of%20Superposition&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Toy%20Models%20of%20Superposition%20Elhage%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Toy%20Models%20of%20Superposition&sort=relevance" }, "supplied_direct_url": "https://transformer-circuits.pub/2022/toy_model/index.html" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Superposition in neural networks", "title": "Toy Models of Superposition", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Bricken et al.", "id": 665, "links": { "canonical_url": "https://transformer-circuits.pub/2023/monosemantic-features", "corrected_by_audit": false, "direct_url": "https://transformer-circuits.pub/2023/monosemantic-features", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Towards%20Monosemanticity%3A%20Decomposing%20Language%20Models%20with%20Dictionary%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Towards%20Monosemanticity%3A%20Decomposing%20Language%20Models%20with%20Dictionary%20Learning%20Bricken%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Towards%20Monosemanticity%3A%20Decomposing%20Language%20Models%20with%20Dictionary%20Learning&sort=relevance" }, "supplied_direct_url": "https://transformer-circuits.pub/2023/monosemantic-features" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Sparse autoencoders for interpretability", "title": "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Templeton et al.", "id": 666, "links": { "canonical_url": "https://transformer-circuits.pub/2024/scaling-monosemanticity/", "corrected_by_audit": false, "direct_url": "https://transformer-circuits.pub/2024/scaling-monosemanticity/", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scaling%20Monosemanticity%3A%20Extracting%20Interpretable%20Features%20from%20Claude%203%20Sonnet&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scaling%20Monosemanticity%3A%20Extracting%20Interpretable%20Features%20from%20Claude%203%20Sonnet%20Templeton%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scaling%20Monosemanticity%3A%20Extracting%20Interpretable%20Features%20from%20Claude%203%20Sonnet&sort=relevance" }, "supplied_direct_url": "https://transformer-circuits.pub/2024/scaling-monosemanticity/" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "SAE at scale on Claude", "title": "Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 987 ], "severity": "warning" } ], "authors": "Zou et al.", "id": 667, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Representation%20Engineering%3A%20A%20Top-Down%20Approach%20to%20AI%20Transparency&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Representation%20Engineering%3A%20A%20Top-Down%20Approach%20to%20AI%20Transparency%20Zou%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Representation%20Engineering%3A%20A%20Top-Down%20Approach%20to%20AI%20Transparency&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Representation-level interventions", "title": "Representation Engineering: A Top-Down Approach to AI Transparency", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Li et al.", "id": 668, "links": { "canonical_url": "https://arxiv.org/abs/2306.03341", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2306.03341.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Inference-Time%20Intervention%3A%20Eliciting%20Truthful%20Answers%20from%20a%20Language%20Model&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Inference-Time%20Intervention%3A%20Eliciting%20Truthful%20Answers%20from%20a%20Language%20Model%20Li%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Inference-Time%20Intervention%3A%20Eliciting%20Truthful%20Answers%20from%20a%20Language%20Model&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2306.03341.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "ITI for truthfulness", "title": "Inference-Time Intervention: Eliciting Truthful Answers from a Language Model", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Gurnee et al.", "id": 669, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Sparse%20Probing%20for%20LLM%20Representations&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Sparse%20Probing%20for%20LLM%20Representations%20Gurnee%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Sparse%20Probing%20for%20LLM%20Representations&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Probing LLM internals", "title": "Sparse Probing for LLM Representations", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Conmy et al.", "id": 670, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Circuit%20Discovery%20in%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Circuit%20Discovery%20in%20LLMs%20Conmy%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Circuit%20Discovery%20in%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Automated circuit finding", "title": "Circuit Discovery in LLMs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Bills et al.", "id": 671, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Interpretability%20in%20the%20Wild&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Interpretability%20in%20the%20Wild%20Bills%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Interpretability%20in%20the%20Wild&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "GPT-4 explaining neurons", "title": "Interpretability in the Wild", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Marks & Tegmark", "id": 672, "links": { "canonical_url": "https://arxiv.org/abs/2310.06824", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2310.06824.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Geometry%20of%20Truth%3A%20Emergent%20Linear%20Structure%20in%20LLM%20Representations&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Geometry%20of%20Truth%3A%20Emergent%20Linear%20Structure%20in%20LLM%20Representations%20Marks%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Geometry%20of%20Truth%3A%20Emergent%20Linear%20Structure%20in%20LLM%20Representations&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2310.06824.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Truth geometry in LLMs", "title": "The Geometry of Truth: Emergent Linear Structure in LLM Representations", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Anthropic", "id": 673, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Polysemanticity%20and%20Capacity%20in%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Polysemanticity%20and%20Capacity%20in%20Neural%20Networks%20Anthropic%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Polysemanticity%20and%20Capacity%20in%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Understanding polysemantic neurons", "title": "Polysemanticity and Capacity in Neural Networks", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Belinkov", "id": 674, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Probing%20Classifiers%3A%20Promises%2C%20Shortcomings%2C%20and%20Advances&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Probing%20Classifiers%3A%20Promises%2C%20Shortcomings%2C%20and%20Advances%20Belinkov%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Probing%20Classifiers%3A%20Promises%2C%20Shortcomings%2C%20and%20Advances&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Probing methodology", "title": "Probing Classifiers: Promises, Shortcomings, and Advances", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Geiger et al.", "id": 675, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Causal%20Abstraction%20for%20Faithful%20Model%20Interpretation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Causal%20Abstraction%20for%20Faithful%20Model%20Interpretation%20Geiger%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Causal%20Abstraction%20for%20Faithful%20Model%20Interpretation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 36, "section_title": "Interpretability & Explainability", "source_note": "Causal analysis of models", "title": "Causal Abstraction for Faithful Model Interpretation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Ahn et al.", "id": 676, "links": { "canonical_url": "https://arxiv.org/abs/2204.01691", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2204.01691.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Do%20As%20I%20Can%2C%20Not%20As%20I%20Say%3A%20Grounding%20Language%20in%20Robotic%20Affordances%20%28SayCan%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Do%20As%20I%20Can%2C%20Not%20As%20I%20Say%3A%20Grounding%20Language%20in%20Robotic%20Affordances%20%28SayCan%29%20Ahn%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Do%20As%20I%20Can%2C%20Not%20As%20I%20Say%3A%20Grounding%20Language%20in%20Robotic%20Affordances%20%28SayCan%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2204.01691.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "LLMs grounded in robot abilities", "title": "Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (SayCan)", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Brohan et al.", "id": 677, "links": { "canonical_url": "https://arxiv.org/abs/2212.06817", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2212.06817.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RT-1%3A%20Robotics%20Transformer%20for%20Real-World%20Control&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RT-1%3A%20Robotics%20Transformer%20for%20Real-World%20Control%20Brohan%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=RT-1%3A%20Robotics%20Transformer%20for%20Real-World%20Control&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2212.06817.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "Transformer for robot control", "title": "RT-1: Robotics Transformer for Real-World Control", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Brohan et al.", "id": 678, "links": { "canonical_url": "https://arxiv.org/abs/2307.15818", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2307.15818.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RT-2%3A%20Vision-Language-Action%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RT-2%3A%20Vision-Language-Action%20Models%20Brohan%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=RT-2%3A%20Vision-Language-Action%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2307.15818.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "VLM as robot policy", "title": "RT-2: Vision-Language-Action Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Open X-Embodiment", "id": 679, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Open%20X-Embodiment%3A%20Robotic%20Learning%20Datasets%20and%20RT-X%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Open%20X-Embodiment%3A%20Robotic%20Learning%20Datasets%20and%20RT-X%20Models%20Open%20X-Embodiment%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Open%20X-Embodiment%3A%20Robotic%20Learning%20Datasets%20and%20RT-X%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "Cross-embodiment dataset", "title": "Open X-Embodiment: Robotic Learning Datasets and RT-X Models", "work_type": "Benchmark or dataset paper", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Driess et al.", "id": 680, "links": { "canonical_url": "https://arxiv.org/abs/2303.03378", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2303.03378.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=PaLM-E%3A%20An%20Embodied%20Multimodal%20Language%20Model&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=PaLM-E%3A%20An%20Embodied%20Multimodal%20Language%20Model%20Driess%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=PaLM-E%3A%20An%20Embodied%20Multimodal%20Language%20Model&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2303.03378.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "Embodied multimodal LM", "title": "PaLM-E: An Embodied Multimodal Language Model", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Liang et al.", "id": 681, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Code%20as%20Policies%3A%20Language%20Model%20Programs%20for%20Embodied%20Control&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Code%20as%20Policies%3A%20Language%20Model%20Programs%20for%20Embodied%20Control%20Liang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Code%20as%20Policies%3A%20Language%20Model%20Programs%20for%20Embodied%20Control&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "Code for robot control", "title": "Code as Policies: Language Model Programs for Embodied Control", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Huang et al.", "id": 682, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Language%20Models%20as%20Zero-Shot%20Planners&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Language%20Models%20as%20Zero-Shot%20Planners%20Huang%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Language%20Models%20as%20Zero-Shot%20Planners&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "LLM planning for robots", "title": "Language Models as Zero-Shot Planners", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Wu et al.", "id": 683, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=TidyBot%3A%20Personalized%20Robot%20Assistance%20with%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=TidyBot%3A%20Personalized%20Robot%20Assistance%20with%20LLMs%20Wu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=TidyBot%3A%20Personalized%20Robot%20Assistance%20with%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "Personal robot assistant", "title": "TidyBot: Personalized Robot Assistance with LLMs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Bousmalis et al.", "id": 684, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RoboCat%3A%20A%20Self-Improving%20Generalist%20Agent%20for%20Robotic%20Manipulation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RoboCat%3A%20A%20Self-Improving%20Generalist%20Agent%20for%20Robotic%20Manipulation%20Bousmalis%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=RoboCat%3A%20A%20Self-Improving%20Generalist%20Agent%20for%20Robotic%20Manipulation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "Self-improving robot", "title": "RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zhao et al.", "id": 685, "links": { "canonical_url": "https://arxiv.org/abs/2304.13705", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2304.13705.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Learning%20Fine-Grained%20Bimanual%20Manipulation%20with%20Low-Cost%20Hardware%20%28ALOHA%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Learning%20Fine-Grained%20Bimanual%20Manipulation%20with%20Low-Cost%20Hardware%20%28ALOHA%29%20Zhao%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Learning%20Fine-Grained%20Bimanual%20Manipulation%20with%20Low-Cost%20Hardware%20%28ALOHA%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2304.13705.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "Low-cost bimanual manipulation", "title": "Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware (ALOHA)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Team et al.", "id": 686, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Octo%3A%20An%20Open-Source%20Generalist%20Robot%20Policy&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Octo%3A%20An%20Open-Source%20Generalist%20Robot%20Policy%20Team%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Octo%3A%20An%20Open-Source%20Generalist%20Robot%20Policy&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "Open robot foundation model", "title": "Octo: An Open-Source Generalist Robot Policy", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Physical Intelligence", "id": 687, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=%CF%800%3A%20A%20Vision-Language-Action%20Flow%20Model%20for%20General%20Robot%20Control&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=%CF%800%3A%20A%20Vision-Language-Action%20Flow%20Model%20for%20General%20Robot%20Control%20Physical%20Intelligence%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=%CF%800%3A%20A%20Vision-Language-Action%20Flow%20Model%20for%20General%20Robot%20Control&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "General-purpose robot control", "title": "π0: A Vision-Language-Action Flow Model for General Robot Control", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "NVIDIA", "id": 688, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=NVIDIA%20Isaac%20and%20Omniverse%20for%20Robotics&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=NVIDIA%20Isaac%20and%20Omniverse%20for%20Robotics%20NVIDIA%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=NVIDIA%20Isaac%20and%20Omniverse%20for%20Robotics&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "Simulation for robotics", "title": "NVIDIA Isaac and Omniverse for Robotics", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "OpenAI (Rubik's cube)", "id": 689, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Dexterous%20Manipulation%20with%20Reinforcement%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Dexterous%20Manipulation%20with%20Reinforcement%20Learning%20OpenAI%20%28Rubik%27s%20cube%29%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Dexterous%20Manipulation%20with%20Reinforcement%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "Dexterous robot hand", "title": "Dexterous Manipulation with Reinforcement Learning", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Fu et al.", "id": 690, "links": { "canonical_url": "https://arxiv.org/abs/2401.02117", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2401.02117.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mobile%20ALOHA%3A%20Learning%20Bimanual%20Mobile%20Manipulation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mobile%20ALOHA%3A%20Learning%20Bimanual%20Mobile%20Manipulation%20Fu%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mobile%20ALOHA%3A%20Learning%20Bimanual%20Mobile%20Manipulation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2401.02117.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 37, "section_title": "Robotics & Embodied AI", "source_note": "Mobile manipulation", "title": "Mobile ALOHA: Learning Bimanual Mobile Manipulation", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 418 ], "severity": "warning" } ], "authors": "Ha & Schmidhuber", "id": 691, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=World%20Models%20%28Ha%20%26%20Schmidhuber%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=World%20Models%20%28Ha%20%26%20Schmidhuber%29%20Ha%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=World%20Models%20%28Ha%20%26%20Schmidhuber%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 38, "section_title": "World Models & Simulation", "source_note": "Learning world models", "title": "World Models (Ha & Schmidhuber)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "LeCun", "id": 692, "links": { "canonical_url": "https://openreview.net/pdf?id=BZ5a1r-kVsf", "corrected_by_audit": false, "direct_url": "https://openreview.net/pdf?id=BZ5a1r-kVsf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Path%20Towards%20Autonomous%20Machine%20Intelligence&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Path%20Towards%20Autonomous%20Machine%20Intelligence%20LeCun%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Path%20Towards%20Autonomous%20Machine%20Intelligence&sort=relevance" }, "supplied_direct_url": "https://openreview.net/pdf?id=BZ5a1r-kVsf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 38, "section_title": "World Models & Simulation", "source_note": "JEPA and world model vision", "title": "A Path Towards Autonomous Machine Intelligence", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Bruce et al.", "id": 693, "links": { "canonical_url": "https://arxiv.org/abs/2402.15391", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2402.15391.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Genie%3A%20Generative%20Interactive%20Environments&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Genie%3A%20Generative%20Interactive%20Environments%20Bruce%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Genie%3A%20Generative%20Interactive%20Environments&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2402.15391.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 38, "section_title": "World Models & Simulation", "source_note": "Playable world generation", "title": "Genie: Generative Interactive Environments", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Alonso et al.", "id": 694, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DIAMOND%3A%20Diffusion%20for%20World%20Modeling&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DIAMOND%3A%20Diffusion%20for%20World%20Modeling%20Alonso%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=DIAMOND%3A%20Diffusion%20for%20World%20Modeling&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 38, "section_title": "World Models & Simulation", "source_note": "Diffusion world models", "title": "DIAMOND: Diffusion for World Modeling", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Yang et al.", "id": 695, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=UniSim%3A%20Learning%20Interactive%20Real-World%20Simulators&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=UniSim%3A%20Learning%20Interactive%20Real-World%20Simulators%20Yang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=UniSim%3A%20Learning%20Interactive%20Real-World%20Simulators&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 38, "section_title": "World Models & Simulation", "source_note": "Universal simulator", "title": "UniSim: Learning Interactive Real-World Simulators", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 696, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Genesis%3A%20Generative%20and%20Universal%20Physics%20Engine&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Genesis%3A%20Generative%20and%20Universal%20Physics%20Engine%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Genesis%3A%20Generative%20and%20Universal%20Physics%20Engine&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 38, "section_title": "World Models & Simulation", "source_note": "Physics simulation platform", "title": "Genesis: Generative and Universal Physics Engine", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Seo et al.", "id": 697, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Learning%20General%20World%20Models%20in%20a%20Handful%20of%20Reward-Free%20Deployments&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Learning%20General%20World%20Models%20in%20a%20Handful%20of%20Reward-Free%20Deployments%20Seo%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Learning%20General%20World%20Models%20in%20a%20Handful%20of%20Reward-Free%20Deployments&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 38, "section_title": "World Models & Simulation", "source_note": "Reward-free world models", "title": "Learning General World Models in a Handful of Reward-Free Deployments", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Hu et al.", "id": 698, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GAIA-1%3A%20A%20Generative%20World%20Model%20for%20Autonomous%20Driving&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GAIA-1%3A%20A%20Generative%20World%20Model%20for%20Autonomous%20Driving%20Hu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=GAIA-1%3A%20A%20Generative%20World%20Model%20for%20Autonomous%20Driving&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 38, "section_title": "World Models & Simulation", "source_note": "Driving world model", "title": "GAIA-1: A Generative World Model for Autonomous Driving", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Hao et al.", "id": 699, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Language%20Models%20Meet%20World%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Language%20Models%20Meet%20World%20Models%20Hao%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Language%20Models%20Meet%20World%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 38, "section_title": "World Models & Simulation", "source_note": "LLM-world model integration", "title": "Language Models Meet World Models", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 700, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Video%20as%20World%20Model&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Video%20as%20World%20Model%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Video%20as%20World%20Model&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 38, "section_title": "World Models & Simulation", "source_note": "Video generation as simulation", "title": "Video as World Model", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Jumper et al.", "id": 701, "links": { "canonical_url": "https://www.nature.com/articles/s41586-021-03819-2", "corrected_by_audit": false, "direct_url": "https://www.nature.com/articles/s41586-021-03819-2", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AlphaFold%3A%20Highly%20Accurate%20Protein%20Structure%20Prediction&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AlphaFold%3A%20Highly%20Accurate%20Protein%20Structure%20Prediction%20Jumper%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=AlphaFold%3A%20Highly%20Accurate%20Protein%20Structure%20Prediction&sort=relevance" }, "supplied_direct_url": "https://www.nature.com/articles/s41586-021-03819-2" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "**Protein folding solved**", "title": "AlphaFold: Highly Accurate Protein Structure Prediction", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Jumper et al.", "id": 702, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AlphaFold%202%20%28full%20paper%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AlphaFold%202%20%28full%20paper%29%20Jumper%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=AlphaFold%202%20%28full%20paper%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "Detailed AlphaFold architecture", "title": "AlphaFold 2 (full paper)", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Abramson et al.", "id": 703, "links": { "canonical_url": "https://www.nature.com/articles/s41586-024-07487-w", "corrected_by_audit": false, "direct_url": "https://www.nature.com/articles/s41586-024-07487-w", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AlphaFold%203&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AlphaFold%203%20Abramson%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=AlphaFold%203&sort=relevance" }, "supplied_direct_url": "https://www.nature.com/articles/s41586-024-07487-w" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "All-atom structure prediction", "title": "AlphaFold 3", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Baek et al.", "id": 704, "links": { "canonical_url": "https://www.science.org/doi/10.1126/science.abj8754", "corrected_by_audit": false, "direct_url": "https://www.science.org/doi/10.1126/science.abj8754", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RoseTTAFold&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RoseTTAFold%20Baek%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=RoseTTAFold&sort=relevance" }, "supplied_direct_url": "https://www.science.org/doi/10.1126/science.abj8754" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "Three-track protein prediction", "title": "RoseTTAFold", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Lin et al.", "id": 705, "links": { "canonical_url": "https://www.science.org/doi/10.1126/science.ade2574", "corrected_by_audit": false, "direct_url": "https://www.science.org/doi/10.1126/science.ade2574", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ESM-2%3A%20Language%20Models%20of%20Protein%20Sequences%20at%20the%20Scale%20of%20Evolution&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ESM-2%3A%20Language%20Models%20of%20Protein%20Sequences%20at%20the%20Scale%20of%20Evolution%20Lin%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=ESM-2%3A%20Language%20Models%20of%20Protein%20Sequences%20at%20the%20Scale%20of%20Evolution&sort=relevance" }, "supplied_direct_url": "https://www.science.org/doi/10.1126/science.ade2574" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "Protein language model", "title": "ESM-2: Language Models of Protein Sequences at the Scale of Evolution", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Dauparas et al.", "id": 706, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ProteinMPNN%3A%20Robust%20Protein%20Sequence%20Design&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ProteinMPNN%3A%20Robust%20Protein%20Sequence%20Design%20Dauparas%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=ProteinMPNN%3A%20Robust%20Protein%20Sequence%20Design&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "Inverse protein folding", "title": "ProteinMPNN: Robust Protein Sequence Design", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Merchant et al.", "id": 707, "links": { "canonical_url": "https://www.nature.com/articles/s41586-023-06735-9", "corrected_by_audit": false, "direct_url": "https://www.nature.com/articles/s41586-023-06735-9", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GNoME%3A%20Scaling%20Deep%20Learning%20for%20Materials%20Discovery&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GNoME%3A%20Scaling%20Deep%20Learning%20for%20Materials%20Discovery%20Merchant%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=GNoME%3A%20Scaling%20Deep%20Learning%20for%20Materials%20Discovery&sort=relevance" }, "supplied_direct_url": "https://www.nature.com/articles/s41586-023-06735-9" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "2.2M new materials", "title": "GNoME: Scaling Deep Learning for Materials Discovery", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zeni et al.", "id": 708, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MatterGen%3A%20A%20Generative%20Model%20for%20Inorganic%20Materials%20Design&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MatterGen%3A%20A%20Generative%20Model%20for%20Inorganic%20Materials%20Design%20Zeni%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=MatterGen%3A%20A%20Generative%20Model%20for%20Inorganic%20Materials%20Design&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "Materials generation", "title": "MatterGen: A Generative Model for Inorganic Materials Design", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Romera-Paredes et al.", "id": 709, "links": { "canonical_url": "https://www.nature.com/articles/s41586-023-06924-6", "corrected_by_audit": false, "direct_url": "https://www.nature.com/articles/s41586-023-06924-6", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=FunSearch%3A%20Mathematical%20Discoveries%20from%20Program%20Search&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=FunSearch%3A%20Mathematical%20Discoveries%20from%20Program%20Search%20Romera-Paredes%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=FunSearch%3A%20Mathematical%20Discoveries%20from%20Program%20Search&sort=relevance" }, "supplied_direct_url": "https://www.nature.com/articles/s41586-023-06924-6" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "LLM for mathematical discovery", "title": "FunSearch: Mathematical Discoveries from Program Search", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Trinh et al.", "id": 710, "links": { "canonical_url": "https://www.nature.com/articles/s41586-023-06747-5", "corrected_by_audit": false, "direct_url": "https://www.nature.com/articles/s41586-023-06747-5", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AlphaGeometry%3A%20Solving%20Olympiad%20Geometry%20without%20Human%20Demonstrations&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AlphaGeometry%3A%20Solving%20Olympiad%20Geometry%20without%20Human%20Demonstrations%20Trinh%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=AlphaGeometry%3A%20Solving%20Olympiad%20Geometry%20without%20Human%20Demonstrations&sort=relevance" }, "supplied_direct_url": "https://www.nature.com/articles/s41586-023-06747-5" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "AI for geometry proofs", "title": "AlphaGeometry: Solving Olympiad Geometry without Human Demonstrations", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Google DeepMind", "id": 711, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AlphaProof%20and%20AlphaGeometry%202&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AlphaProof%20and%20AlphaGeometry%202%20Google%20DeepMind%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=AlphaProof%20and%20AlphaGeometry%202&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "IMO-level mathematics", "title": "AlphaProof and AlphaGeometry 2", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Singhal et al.", "id": 712, "links": { "canonical_url": "https://arxiv.org/abs/2212.13138", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2212.13138.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Med-PaLM%3A%20Large%20Language%20Models%20Encode%20Clinical%20Knowledge&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Med-PaLM%3A%20Large%20Language%20Models%20Encode%20Clinical%20Knowledge%20Singhal%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Med-PaLM%3A%20Large%20Language%20Models%20Encode%20Clinical%20Knowledge&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2212.13138.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "Medical AI", "title": "Med-PaLM: Large Language Models Encode Clinical Knowledge", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Singhal et al.", "id": 713, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Med-PaLM%202&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Med-PaLM%202%20Singhal%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Med-PaLM%202&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "Expert-level medical QA", "title": "Med-PaLM 2", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Wu et al.", "id": 714, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=PMC-LLaMA%3A%20Towards%20Building%20Open-source%20Language%20Models%20for%20Medicine&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=PMC-LLaMA%3A%20Towards%20Building%20Open-source%20Language%20Models%20for%20Medicine%20Wu%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=PMC-LLaMA%3A%20Towards%20Building%20Open-source%20Language%20Models%20for%20Medicine&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "Open medical LLM", "title": "PMC-LLaMA: Towards Building Open-source Language Models for Medicine", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Luo et al.", "id": 715, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BioGPT%3A%20Generative%20Pre-trained%20Transformer%20for%20Biomedical%20Text&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BioGPT%3A%20Generative%20Pre-trained%20Transformer%20for%20Biomedical%20Text%20Luo%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=BioGPT%3A%20Generative%20Pre-trained%20Transformer%20for%20Biomedical%20Text&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "Biomedical LM", "title": "BioGPT: Generative Pre-trained Transformer for Biomedical Text", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Taylor et al.", "id": 716, "links": { "canonical_url": "https://arxiv.org/abs/2211.09085", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2211.09085.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Galactica%3A%20A%20Large%20Language%20Model%20for%20Science&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Galactica%3A%20A%20Large%20Language%20Model%20for%20Science%20Taylor%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Galactica%3A%20A%20Large%20Language%20Model%20for%20Science&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2211.09085.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "Science-focused LLM", "title": "Galactica: A Large Language Model for Science", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Lu et al.", "id": 717, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ScienceQA%3A%20Science%20Question%20Answering&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ScienceQA%3A%20Science%20Question%20Answering%20Lu%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=ScienceQA%3A%20Science%20Question%20Answering&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "Science reasoning", "title": "ScienceQA: Science Question Answering", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Bran et al.", "id": 718, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ChemCrow%3A%20Augmenting%20LLMs%20with%20Chemistry%20Tools&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ChemCrow%3A%20Augmenting%20LLMs%20with%20Chemistry%20Tools%20Bran%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=ChemCrow%3A%20Augmenting%20LLMs%20with%20Chemistry%20Tools&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "Chemistry agent", "title": "ChemCrow: Augmenting LLMs with Chemistry Tools", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Webersinke et al.", "id": 719, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ClimateBERT&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ClimateBERT%20Webersinke%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=ClimateBERT&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "Climate NLP", "title": "ClimateBERT", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Lam et al.", "id": 720, "links": { "canonical_url": "https://arxiv.org/abs/2212.12794", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2212.12794.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GraphCast%3A%20Learning%20Skillful%20Medium-Range%20Global%20Weather%20Forecasting&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GraphCast%3A%20Learning%20Skillful%20Medium-Range%20Global%20Weather%20Forecasting%20Lam%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=GraphCast%3A%20Learning%20Skillful%20Medium-Range%20Global%20Weather%20Forecasting&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2212.12794.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 39, "section_title": "Scientific AI & Domain Applications", "source_note": "ML weather forecasting", "title": "GraphCast: Learning Skillful Medium-Range Global Weather Forecasting", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Kaplan et al.", "id": 721, "links": { "canonical_url": "https://arxiv.org/abs/2001.08361", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2001.08361.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scaling%20Laws%20for%20Neural%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scaling%20Laws%20for%20Neural%20Language%20Models%20Kaplan%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scaling%20Laws%20for%20Neural%20Language%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2001.08361.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "**Power-law scaling relationships**", "title": "Scaling Laws for Neural Language Models", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 200 ], "severity": "warning" } ], "authors": "Hoffmann et al.", "id": 722, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Training%20Compute-Optimal%20LLMs%20%28Chinchilla%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Training%20Compute-Optimal%20LLMs%20%28Chinchilla%29%20Hoffmann%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Training%20Compute-Optimal%20LLMs%20%28Chinchilla%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "**Data-compute tradeoff**", "title": "Training Compute-Optimal LLMs (Chinchilla)", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Wei et al.", "id": 723, "links": { "canonical_url": "https://arxiv.org/abs/2206.07682", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2206.07682.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Emergent%20Abilities%20of%20Large%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Emergent%20Abilities%20of%20Large%20Language%20Models%20Wei%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Emergent%20Abilities%20of%20Large%20Language%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2206.07682.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "Emergence at scale", "title": "Emergent Abilities of Large Language Models", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Schaeffer et al.", "id": 724, "links": { "canonical_url": "https://arxiv.org/abs/2304.15004", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2304.15004.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Are%20Emergent%20Abilities%20of%20LLMs%20a%20Mirage%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Are%20Emergent%20Abilities%20of%20LLMs%20a%20Mirage%3F%20Schaeffer%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Are%20Emergent%20Abilities%20of%20LLMs%20a%20Mirage%3F&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2304.15004.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "Questioning emergent abilities", "title": "Are Emergent Abilities of LLMs a Mirage?", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Muennighoff et al.", "id": 725, "links": { "canonical_url": "https://arxiv.org/abs/2305.16264", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.16264.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scaling%20Data-Constrained%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scaling%20Data-Constrained%20Language%20Models%20Muennighoff%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scaling%20Data-Constrained%20Language%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.16264.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "Data-limited scaling", "title": "Scaling Data-Constrained Language Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Henighan et al.", "id": 726, "links": { "canonical_url": "https://arxiv.org/abs/2010.14701", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2010.14701.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scaling%20Laws%20for%20Autoregressive%20Generative%20Modeling&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scaling%20Laws%20for%20Autoregressive%20Generative%20Modeling%20Henighan%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scaling%20Laws%20for%20Autoregressive%20Generative%20Modeling&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2010.14701.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "Cross-modality scaling", "title": "Scaling Laws for Autoregressive Generative Modeling", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Caballero et al.", "id": 727, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Beyond%20Neural%20Scaling%20Laws&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Beyond%20Neural%20Scaling%20Laws%20Caballero%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Beyond%20Neural%20Scaling%20Laws&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "Broken neural scaling laws", "title": "Beyond Neural Scaling Laws", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Gao et al.", "id": 728, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scaling%20Laws%20for%20Reward%20Model%20Overoptimization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scaling%20Laws%20for%20Reward%20Model%20Overoptimization%20Gao%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scaling%20Laws%20for%20Reward%20Model%20Overoptimization&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "Reward model scaling", "title": "Scaling Laws for Reward Model Overoptimization", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zhai et al.", "id": 729, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scaling%20Vision%20Transformers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scaling%20Vision%20Transformers%20Zhai%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scaling%20Vision%20Transformers&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "ViT scaling laws", "title": "Scaling Vision Transformers", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Ruan et al.", "id": 730, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Observational%20Scaling%20Laws&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Observational%20Scaling%20Laws%20Ruan%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Observational%20Scaling%20Laws&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "Predicting LLM capabilities", "title": "Observational Scaling Laws", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 197, 782 ], "severity": "warning" } ], "authors": "Gunasekar et al.", "id": 731, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Textbooks%20Are%20All%20You%20Need%20%28Phi-1%20scaling%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Textbooks%20Are%20All%20You%20Need%20%28Phi-1%20scaling%29%20Gunasekar%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Textbooks%20Are%20All%20You%20Need%20%28Phi-1%20scaling%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "Data quality over quantity", "title": "Textbooks Are All You Need (Phi-1 scaling)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Gao et al.", "id": 732, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Pile%3A%20An%20800GB%20Dataset%20for%20Diverse%20Text%20Modeling&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Pile%3A%20An%20800GB%20Dataset%20for%20Diverse%20Text%20Modeling%20Gao%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Pile%3A%20An%20800GB%20Dataset%20for%20Diverse%20Text%20Modeling&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "Large-scale training data", "title": "The Pile: An 800GB Dataset for Diverse Text Modeling", "work_type": "Benchmark or dataset paper", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Together AI", "id": 733, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RedPajama%3A%20An%20Open%20Dataset%20for%20Training%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RedPajama%3A%20An%20Open%20Dataset%20for%20Training%20LLMs%20Together%20AI%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=RedPajama%3A%20An%20Open%20Dataset%20for%20Training%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "Open pretraining data", "title": "RedPajama: An Open Dataset for Training LLMs", "work_type": "Benchmark or dataset paper", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Penedo et al.", "id": 734, "links": { "canonical_url": "https://arxiv.org/abs/2406.17557", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2406.17557.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=FineWeb%3A%20Decanting%20the%20Web%20for%20the%20Finest%20Text%20Data&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=FineWeb%3A%20Decanting%20the%20Web%20for%20the%20Finest%20Text%20Data%20Penedo%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=FineWeb%3A%20Decanting%20the%20Web%20for%20the%20Finest%20Text%20Data&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2406.17557.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "High-quality web data", "title": "FineWeb: Decanting the Web for the Finest Text Data", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Gadre et al.", "id": 735, "links": { "canonical_url": "https://arxiv.org/abs/2304.14108", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2304.14108.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DataComp%3A%20In%20Search%20of%20the%20Next%20Generation%20of%20Multimodal%20Datasets&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DataComp%3A%20In%20Search%20of%20the%20Next%20Generation%20of%20Multimodal%20Datasets%20Gadre%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=DataComp%3A%20In%20Search%20of%20the%20Next%20Generation%20of%20Multimodal%20Datasets&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2304.14108.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 40, "section_title": "Scaling Laws & Emergent Abilities", "source_note": "Multimodal data curation", "title": "DataComp: In Search of the Next Generation of Multimodal Datasets", "work_type": "Benchmark or dataset paper", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Gu & Dao", "id": 736, "links": { "canonical_url": "https://arxiv.org/abs/2312.00752", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2312.00752.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mamba%3A%20Linear-Time%20Sequence%20Modeling%20with%20Selective%20State%20Spaces&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mamba%3A%20Linear-Time%20Sequence%20Modeling%20with%20Selective%20State%20Spaces%20Gu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mamba%3A%20Linear-Time%20Sequence%20Modeling%20with%20Selective%20State%20Spaces&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2312.00752.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "**Selective state space model**", "title": "Mamba: Linear-Time Sequence Modeling with Selective State Spaces", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Dao & Gu", "id": 737, "links": { "canonical_url": "https://arxiv.org/abs/2405.21060", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2405.21060.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mamba-2%3A%20Structured%20State%20Space%20Duality&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mamba-2%3A%20Structured%20State%20Space%20Duality%20Dao%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mamba-2%3A%20Structured%20State%20Space%20Duality&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2405.21060.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "Improved Mamba", "title": "Mamba-2: Structured State Space Duality", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Gu et al.", "id": 738, "links": { "canonical_url": "https://arxiv.org/abs/2111.00396", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2111.00396.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Efficiently%20Modeling%20Long%20Sequences%20with%20Structured%20State%20Spaces%20%28S4%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Efficiently%20Modeling%20Long%20Sequences%20with%20Structured%20State%20Spaces%20%28S4%29%20Gu%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Efficiently%20Modeling%20Long%20Sequences%20with%20Structured%20State%20Spaces%20%28S4%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2111.00396.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "S4 — structured SSMs", "title": "Efficiently Modeling Long Sequences with Structured State Spaces (S4)", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Poli et al.", "id": 739, "links": { "canonical_url": "https://arxiv.org/abs/2302.10866", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2302.10866.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Hyena%20Hierarchy%3A%20Towards%20Larger%20Convolutional%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Hyena%20Hierarchy%3A%20Towards%20Larger%20Convolutional%20Language%20Models%20Poli%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Hyena%20Hierarchy%3A%20Towards%20Larger%20Convolutional%20Language%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2302.10866.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "Long convolution alternative", "title": "Hyena Hierarchy: Towards Larger Convolutional Language Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Peng et al.", "id": 740, "links": { "canonical_url": "https://arxiv.org/abs/2305.13048", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.13048.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RWKV%3A%20Reinventing%20RNNs%20for%20the%20Transformer%20Era&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RWKV%3A%20Reinventing%20RNNs%20for%20the%20Transformer%20Era%20Peng%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=RWKV%3A%20Reinventing%20RNNs%20for%20the%20Transformer%20Era&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.13048.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "Linear RNN at transformer quality", "title": "RWKV: Reinventing RNNs for the Transformer Era", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "De et al.", "id": 741, "links": { "canonical_url": "https://arxiv.org/abs/2402.19427", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2402.19427.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Griffin%3A%20Mixing%20Gated%20Linear%20Recurrences%20with%20Local%20Attention&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Griffin%3A%20Mixing%20Gated%20Linear%20Recurrences%20with%20Local%20Attention%20De%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Griffin%3A%20Mixing%20Gated%20Linear%20Recurrences%20with%20Local%20Attention&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2402.19427.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "Hybrid recurrence + attention", "title": "Griffin: Mixing Gated Linear Recurrences with Local Attention", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Sun et al.", "id": 742, "links": { "canonical_url": "https://arxiv.org/abs/2307.08621", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2307.08621.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RetNet%3A%20Retentive%20Network%3A%20A%20Successor%20to%20Transformer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RetNet%3A%20Retentive%20Network%3A%20A%20Successor%20to%20Transformer%20Sun%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=RetNet%3A%20Retentive%20Network%3A%20A%20Successor%20to%20Transformer&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2307.08621.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "Retention mechanism", "title": "RetNet: Retentive Network: A Successor to Transformer", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Beck et al.", "id": 743, "links": { "canonical_url": "https://arxiv.org/abs/2405.04517", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2405.04517.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=xLSTM%3A%20Extended%20Long%20Short-Term%20Memory&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=xLSTM%3A%20Extended%20Long%20Short-Term%20Memory%20Beck%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=xLSTM%3A%20Extended%20Long%20Short-Term%20Memory&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2405.04517.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "Modernized LSTM", "title": "xLSTM: Extended Long Short-Term Memory", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 214 ], "severity": "warning" } ], "authors": "AI21 Labs", "id": 744, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Jamba%3A%20Hybrid%20Transformer-Mamba&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Jamba%3A%20Hybrid%20Transformer-Mamba%20AI21%20Labs%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Jamba%3A%20Hybrid%20Transformer-Mamba&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "SSM-Transformer hybrid", "title": "Jamba: Hybrid Transformer-Mamba", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Raposo et al.", "id": 745, "links": { "canonical_url": "https://arxiv.org/abs/2404.02258", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2404.02258.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mixture%20of%20Depths%3A%20Dynamically%20Allocating%20Compute%20in%20Transformer-Based%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mixture%20of%20Depths%3A%20Dynamically%20Allocating%20Compute%20in%20Transformer-Based%20Models%20Raposo%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mixture%20of%20Depths%3A%20Dynamically%20Allocating%20Compute%20in%20Transformer-Based%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2404.02258.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "Dynamic compute allocation", "title": "Mixture of Depths: Dynamically Allocating Compute in Transformer-Based Models", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zoph & Le", "id": 746, "links": { "canonical_url": "https://arxiv.org/abs/1611.01578", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1611.01578.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Neural%20Architecture%20Search%20%28NAS%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Neural%20Architecture%20Search%20%28NAS%29%20Zoph%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Neural%20Architecture%20Search%20%28NAS%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1611.01578.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "Automated architecture design", "title": "Neural Architecture Search (NAS)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 86 ], "severity": "warning" } ], "authors": "Tan & Le", "id": 747, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=EfficientNet%20%28NAS-derived%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=EfficientNet%20%28NAS-derived%29%20Tan%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=EfficientNet%20%28NAS-derived%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "NAS for efficient models", "title": "EfficientNet (NAS-derived)", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Ye et al.", "id": 748, "links": { "canonical_url": "https://arxiv.org/abs/2410.05258", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2410.05258.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Differential%20Transformer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Differential%20Transformer%20Ye%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Differential%20Transformer&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2410.05258.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "Differential attention mechanism", "title": "Differential Transformer", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Liu et al.", "id": 749, "links": { "canonical_url": "https://arxiv.org/abs/2404.19756", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2404.19756.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Kolmogorov-Arnold%20Networks%20%28KAN%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Kolmogorov-Arnold%20Networks%20%28KAN%29%20Liu%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Kolmogorov-Arnold%20Networks%20%28KAN%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2404.19756.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "Alternative to MLPs", "title": "Kolmogorov-Arnold Networks (KAN)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Sun et al.", "id": 750, "links": { "canonical_url": "https://arxiv.org/abs/2407.04620", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2407.04620.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=TTT%3A%20Learning%20to%20%28Learn%20at%20Test%20Time%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=TTT%3A%20Learning%20to%20%28Learn%20at%20Test%20Time%29%20Sun%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=TTT%3A%20Learning%20to%20%28Learn%20at%20Test%20Time%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2407.04620.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 41, "section_title": "Architecture Innovations & Beyond Transformers", "source_note": "Test-time training layers", "title": "TTT: Learning to (Learn at Test Time)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Bubeck et al.", "id": 751, "links": { "canonical_url": "https://arxiv.org/abs/2303.12712", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2303.12712.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Sparks%20of%20AGI%3A%20Early%20Experiments%20with%20GPT-4&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Sparks%20of%20AGI%3A%20Early%20Experiments%20with%20GPT-4%20Bubeck%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Sparks%20of%20AGI%3A%20Early%20Experiments%20with%20GPT-4&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2303.12712.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 42, "section_title": "AGI Theory & Frontier Research", "source_note": "AGI capabilities analysis", "title": "Sparks of AGI: Early Experiments with GPT-4", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Morris et al.", "id": 752, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Levels%20of%20AGI&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Levels%20of%20AGI%20Morris%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Levels%20of%20AGI&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 42, "section_title": "AGI Theory & Frontier Research", "source_note": "Taxonomy of AGI levels", "title": "Levels of AGI", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Sutton", "id": 753, "links": { "canonical_url": "https://www.incompleteideas.net/IncIdeas/BitterLesson.html", "corrected_by_audit": false, "direct_url": "https://www.incompleteideas.net/IncIdeas/BitterLesson.html", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Bitter%20Lesson&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Bitter%20Lesson%20Sutton%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Bitter%20Lesson&sort=relevance" }, "supplied_direct_url": "https://www.incompleteideas.net/IncIdeas/BitterLesson.html" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 42, "section_title": "AGI Theory & Frontier Research", "source_note": "Compute over engineering", "title": "The Bitter Lesson", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Silver et al.", "id": 754, "links": { "canonical_url": "https://www.sciencedirect.com/science/article/pii/S0004370221000862", "corrected_by_audit": false, "direct_url": "https://www.sciencedirect.com/science/article/pii/S0004370221000862", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Reward%20is%20Enough&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Reward%20is%20Enough%20Silver%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Reward%20is%20Enough&sort=relevance" }, "supplied_direct_url": "https://www.sciencedirect.com/science/article/pii/S0004370221000862" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 42, "section_title": "AGI Theory & Frontier Research", "source_note": "Reward maximization for intelligence", "title": "Reward is Enough", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Goertzel", "id": 755, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Artificial%20General%20Intelligence%3A%20Concept%2C%20State%20of%20the%20Art%2C%20and%20Future%20Prospects&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Artificial%20General%20Intelligence%3A%20Concept%2C%20State%20of%20the%20Art%2C%20and%20Future%20Prospects%20Goertzel%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Artificial%20General%20Intelligence%3A%20Concept%2C%20State%20of%20the%20Art%2C%20and%20Future%20Prospects&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 42, "section_title": "AGI Theory & Frontier Research", "source_note": "AGI survey", "title": "Artificial General Intelligence: Concept, State of the Art, and Future Prospects", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Chollet", "id": 756, "links": { "canonical_url": "https://arxiv.org/abs/1911.01547", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1911.01547.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=On%20the%20Measure%20of%20Intelligence&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=On%20the%20Measure%20of%20Intelligence%20Chollet%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=On%20the%20Measure%20of%20Intelligence&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1911.01547.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 42, "section_title": "AGI Theory & Frontier Research", "source_note": "ARC benchmark, intelligence definition", "title": "On the Measure of Intelligence", "work_type": "Benchmark or dataset paper", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Chollet et al.", "id": 757, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ARC%20Prize%20and%20ARC-AGI&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ARC%20Prize%20and%20ARC-AGI%20Chollet%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=ARC%20Prize%20and%20ARC-AGI&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 42, "section_title": "AGI Theory & Frontier Research", "source_note": "Abstraction reasoning challenge", "title": "ARC Prize and ARC-AGI", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 346 ], "severity": "warning" } ], "authors": "Zhou et al.", "id": 758, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Language%20Agent%20Tree%20Search%20Unifies%20Reasoning%2C%20Acting%2C%20and%20Planning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Language%20Agent%20Tree%20Search%20Unifies%20Reasoning%2C%20Acting%2C%20and%20Planning%20Zhou%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Language%20Agent%20Tree%20Search%20Unifies%20Reasoning%2C%20Acting%2C%20and%20Planning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 42, "section_title": "AGI Theory & Frontier Research", "source_note": "Unified agent framework", "title": "Language Agent Tree Search Unifies Reasoning, Acting, and Planning", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Bostrom", "id": 759, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Superintelligence%3A%20Paths%2C%20Dangers%2C%20Strategies%20%28summary%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Superintelligence%3A%20Paths%2C%20Dangers%2C%20Strategies%20%28summary%29%20Bostrom%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Superintelligence%3A%20Paths%2C%20Dangers%2C%20Strategies%20%28summary%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 42, "section_title": "AGI Theory & Frontier Research", "source_note": "Superintelligence risks", "title": "Superintelligence: Paths, Dangers, Strategies (summary)", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 760, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Case%20for%20AI%20Safety&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Case%20for%20AI%20Safety%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Case%20for%20AI%20Safety&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 42, "section_title": "AGI Theory & Frontier Research", "source_note": "Modern safety arguments", "title": "The Case for AI Safety", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Bordes et al.", "id": 761, "links": { "canonical_url": "https://papers.nips.cc/paper/2013/hash/1cecc7a77928ca8133fa24680a88d2f9-Abstract.html", "corrected_by_audit": false, "direct_url": "https://papers.nips.cc/paper/2013/hash/1cecc7a77928ca8133fa24680a88d2f9-Abstract.html", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Translating%20Embeddings%20for%20Modeling%20Multi-relational%20Data%20%28TransE%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Translating%20Embeddings%20for%20Modeling%20Multi-relational%20Data%20%28TransE%29%20Bordes%202013", "semantic_scholar": "https://www.semanticscholar.org/search?q=Translating%20Embeddings%20for%20Modeling%20Multi-relational%20Data%20%28TransE%29&sort=relevance" }, "supplied_direct_url": "https://papers.nips.cc/paper/2013/hash/1cecc7a77928ca8133fa24680a88d2f9-Abstract.html" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 43, "section_title": "Knowledge Graphs & Structured Knowledge", "source_note": "Knowledge graph embeddings", "title": "Translating Embeddings for Modeling Multi-relational Data (TransE)", "work_type": "Research-paper candidate", "year": 2013, "year_display": "2013" }, { "audit_flags": [], "authors": "Wang et al.", "id": 762, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Knowledge%20Graph%20Embedding%20by%20Translating%20on%20Hyperplanes%20%28TransH%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Knowledge%20Graph%20Embedding%20by%20Translating%20on%20Hyperplanes%20%28TransH%29%20Wang%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Knowledge%20Graph%20Embedding%20by%20Translating%20on%20Hyperplanes%20%28TransH%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 43, "section_title": "Knowledge Graphs & Structured Knowledge", "source_note": "Improved KG embeddings", "title": "Knowledge Graph Embedding by Translating on Hyperplanes (TransH)", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Sun et al.", "id": 763, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RotatE%3A%20Knowledge%20Graph%20Embedding%20by%20Relational%20Rotation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RotatE%3A%20Knowledge%20Graph%20Embedding%20by%20Relational%20Rotation%20Sun%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=RotatE%3A%20Knowledge%20Graph%20Embedding%20by%20Relational%20Rotation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 43, "section_title": "Knowledge Graphs & Structured Knowledge", "source_note": "Rotation-based KG embedding", "title": "RotatE: Knowledge Graph Embedding by Relational Rotation", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 764, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=KGQA%3A%20Knowledge%20Graph%20Question%20Answering&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=KGQA%3A%20Knowledge%20Graph%20Question%20Answering%20Various%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=KGQA%3A%20Knowledge%20Graph%20Question%20Answering&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 43, "section_title": "Knowledge Graphs & Structured Knowledge", "source_note": "QA over knowledge graphs", "title": "KGQA: Knowledge Graph Question Answering", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Pan et al.", "id": 765, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Unifying%20LLMs%20and%20Knowledge%20Graphs%3A%20A%20Roadmap&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Unifying%20LLMs%20and%20Knowledge%20Graphs%3A%20A%20Roadmap%20Pan%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Unifying%20LLMs%20and%20Knowledge%20Graphs%3A%20A%20Roadmap&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 43, "section_title": "Knowledge Graphs & Structured Knowledge", "source_note": "LLM + KG integration survey", "title": "Unifying LLMs and Knowledge Graphs: A Roadmap", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Sun et al.", "id": 766, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Think-on-Graph%3A%20Deep%20and%20Responsible%20Reasoning%20of%20LLMs%20on%20KGs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Think-on-Graph%3A%20Deep%20and%20Responsible%20Reasoning%20of%20LLMs%20on%20KGs%20Sun%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Think-on-Graph%3A%20Deep%20and%20Responsible%20Reasoning%20of%20LLMs%20on%20KGs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 43, "section_title": "Knowledge Graphs & Structured Knowledge", "source_note": "LLM reasoning with KGs", "title": "Think-on-Graph: Deep and Responsible Reasoning of LLMs on KGs", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Chen et al.", "id": 767, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=KnowPrompt%3A%20Knowledge-aware%20Prompt-tuning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=KnowPrompt%3A%20Knowledge-aware%20Prompt-tuning%20Chen%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=KnowPrompt%3A%20Knowledge-aware%20Prompt-tuning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 43, "section_title": "Knowledge Graphs & Structured Knowledge", "source_note": "Knowledge-enhanced prompting", "title": "KnowPrompt: Knowledge-aware Prompt-tuning", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Vrandečić & Krötzsch", "id": 768, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Wikidata%20and%20Knowledge%20Graphs%20at%20Scale&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Wikidata%20and%20Knowledge%20Graphs%20at%20Scale%20Vrande%C4%8Di%C4%87%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Wikidata%20and%20Knowledge%20Graphs%20at%20Scale&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 43, "section_title": "Knowledge Graphs & Structured Knowledge", "source_note": "Wikidata for AI", "title": "Wikidata and Knowledge Graphs at Scale", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Yasunaga et al.", "id": 769, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=QA-GNN%3A%20Reasoning%20with%20Language%20Models%20and%20KGs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=QA-GNN%3A%20Reasoning%20with%20Language%20Models%20and%20KGs%20Yasunaga%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=QA-GNN%3A%20Reasoning%20with%20Language%20Models%20and%20KGs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 43, "section_title": "Knowledge Graphs & Structured Knowledge", "source_note": "GNN + LLM for QA", "title": "QA-GNN: Reasoning with Language Models and KGs", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 770, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Graph-based%20Deep%20Learning%20for%20NLP&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Graph-based%20Deep%20Learning%20for%20NLP%20Various%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Graph-based%20Deep%20Learning%20for%20NLP&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 43, "section_title": "Knowledge Graphs & Structured Knowledge", "source_note": "Graph methods in NLP survey", "title": "Graph-based Deep Learning for NLP", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Chiu & Nichols", "id": 771, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Named%20Entity%20Recognition%20with%20Bidirectional%20LSTM-CNNs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Named%20Entity%20Recognition%20with%20Bidirectional%20LSTM-CNNs%20Chiu%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Named%20Entity%20Recognition%20with%20Bidirectional%20LSTM-CNNs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 44, "section_title": "Natural Language Understanding & Generation", "source_note": "NER with deep learning", "title": "Named Entity Recognition with Bidirectional LSTM-CNNs", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Ma & Hovy", "id": 772, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=End-to-end%20Sequence%20Labeling%20via%20Bi-directional%20LSTM-CNNs-CRF&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=End-to-end%20Sequence%20Labeling%20via%20Bi-directional%20LSTM-CNNs-CRF%20Ma%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=End-to-end%20Sequence%20Labeling%20via%20Bi-directional%20LSTM-CNNs-CRF&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 44, "section_title": "Natural Language Understanding & Generation", "source_note": "LSTM-CRF for NER", "title": "End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 921 ], "severity": "warning" } ], "authors": "Sennrich et al.", "id": 773, "links": { "canonical_url": "https://arxiv.org/abs/1508.07909", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1508.07909.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Neural%20Machine%20Translation%20of%20Rare%20Words%20with%20Subword%20Units%20%28BPE%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Neural%20Machine%20Translation%20of%20Rare%20Words%20with%20Subword%20Units%20%28BPE%29%20Sennrich%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Neural%20Machine%20Translation%20of%20Rare%20Words%20with%20Subword%20Units%20%28BPE%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1508.07909.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 44, "section_title": "Natural Language Understanding & Generation", "source_note": "Byte-pair encoding", "title": "Neural Machine Translation of Rare Words with Subword Units (BPE)", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Kudo & Richardson", "id": 774, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SentencePiece&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SentencePiece%20Kudo%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=SentencePiece&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 44, "section_title": "Natural Language Understanding & Generation", "source_note": "Unigram/BPE tokenizer", "title": "SentencePiece", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as technical or industry report, not as a research paper.", "severity": "warning" } ], "authors": "Post", "id": 775, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Call%20for%20Clarity%20in%20Reporting%20BLEU%20Scores&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Call%20for%20Clarity%20in%20Reporting%20BLEU%20Scores%20Post%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Call%20for%20Clarity%20in%20Reporting%20BLEU%20Scores&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 44, "section_title": "Natural Language Understanding & Generation", "source_note": "MT evaluation standards", "title": "A Call for Clarity in Reporting BLEU Scores", "work_type": "Technical or industry report", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 776, "links": { "canonical_url": "https://arxiv.org/abs/1904.09675", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1904.09675.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BERTScore%3A%20Evaluating%20Text%20Generation%20with%20BERT&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BERTScore%3A%20Evaluating%20Text%20Generation%20with%20BERT%20Zhang%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=BERTScore%3A%20Evaluating%20Text%20Generation%20with%20BERT&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1904.09675.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 44, "section_title": "Natural Language Understanding & Generation", "source_note": "Semantic evaluation metric", "title": "BERTScore: Evaluating Text Generation with BERT", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Lin", "id": 777, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ROUGE%3A%20A%20Package%20for%20Automatic%20Evaluation%20of%20Summaries&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ROUGE%3A%20A%20Package%20for%20Automatic%20Evaluation%20of%20Summaries%20Lin%202004", "semantic_scholar": "https://www.semanticscholar.org/search?q=ROUGE%3A%20A%20Package%20for%20Automatic%20Evaluation%20of%20Summaries&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 44, "section_title": "Natural Language Understanding & Generation", "source_note": "Summarization evaluation", "title": "ROUGE: A Package for Automatic Evaluation of Summaries", "work_type": "Research-paper candidate", "year": 2004, "year_display": "2004" }, { "audit_flags": [], "authors": "See et al.", "id": 778, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Get%20To%20The%20Point%3A%20Summarization%20with%20Pointer-Generator%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Get%20To%20The%20Point%3A%20Summarization%20with%20Pointer-Generator%20Networks%20See%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Get%20To%20The%20Point%3A%20Summarization%20with%20Pointer-Generator%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 44, "section_title": "Natural Language Understanding & Generation", "source_note": "Copy mechanism for summarization", "title": "Get To The Point: Summarization with Pointer-Generator Networks", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Nallapati et al.", "id": 779, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Abstractive%20Text%20Summarization%20using%20Seq-to-Seq%20RNNs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Abstractive%20Text%20Summarization%20using%20Seq-to-Seq%20RNNs%20Nallapati%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Abstractive%20Text%20Summarization%20using%20Seq-to-Seq%20RNNs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 44, "section_title": "Natural Language Understanding & Generation", "source_note": "Neural abstractive summarization", "title": "Abstractive Text Summarization using Seq-to-Seq RNNs", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Lin et al.", "id": 780, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Structured%20Self-Attentive%20Sentence%20Embedding&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Structured%20Self-Attentive%20Sentence%20Embedding%20Lin%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Structured%20Self-Attentive%20Sentence%20Embedding&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 44, "section_title": "Natural Language Understanding & Generation", "source_note": "Self-attention for sentence embedding", "title": "A Structured Self-Attentive Sentence Embedding", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 222 ], "severity": "warning" } ], "authors": "Wang et al.", "id": 781, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Self-Instruct&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Self-Instruct%20Wang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Self-Instruct&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 45, "section_title": "Synthetic Data & Data Generation", "source_note": "LLM-generated instructions", "title": "Self-Instruct", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as book or textbook, not as a research paper.", "severity": "warning" }, { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 197, 731 ], "severity": "warning" } ], "authors": "Gunasekar et al.", "id": 782, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Textbooks%20Are%20All%20You%20Need&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Textbooks%20Are%20All%20You%20Need%20Gunasekar%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Textbooks%20Are%20All%20You%20Need&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 45, "section_title": "Synthetic Data & Data Generation", "source_note": "Synthetic textbook data", "title": "Textbooks Are All You Need", "work_type": "Book or textbook", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "HuggingFace", "id": 783, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Cosmopedia%3A%20Creating%20Large-Scale%20Synthetic%20Data&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Cosmopedia%3A%20Creating%20Large-Scale%20Synthetic%20Data%20HuggingFace%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Cosmopedia%3A%20Creating%20Large-Scale%20Synthetic%20Data&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 45, "section_title": "Synthetic Data & Data Generation", "source_note": "Large synthetic dataset", "title": "Cosmopedia: Creating Large-Scale Synthetic Data", "work_type": "Benchmark or dataset paper", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Maini et al.", "id": 784, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Rephrasing%20the%20Web%3A%20A%20Recipe%20for%20Compute%20and%20Data-Efficient%20Language%20Modeling&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Rephrasing%20the%20Web%3A%20A%20Recipe%20for%20Compute%20and%20Data-Efficient%20Language%20Modeling%20Maini%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Rephrasing%20the%20Web%3A%20A%20Recipe%20for%20Compute%20and%20Data-Efficient%20Language%20Modeling&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 45, "section_title": "Synthetic Data & Data Generation", "source_note": "Web data rephrasing", "title": "Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Xu et al.", "id": 785, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Magpie%3A%20Alignment%20Data%20Synthesis%20from%20Scratch&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Magpie%3A%20Alignment%20Data%20Synthesis%20from%20Scratch%20Xu%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Magpie%3A%20Alignment%20Data%20Synthesis%20from%20Scratch&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 45, "section_title": "Synthetic Data & Data Generation", "source_note": "Synthetic alignment data", "title": "Magpie: Alignment Data Synthesis from Scratch", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 229 ], "severity": "warning" } ], "authors": "Xu et al.", "id": 786, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=WizardLM%3A%20Empowering%20LLMs%20to%20Follow%20Complex%20Instructions&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=WizardLM%3A%20Empowering%20LLMs%20to%20Follow%20Complex%20Instructions%20Xu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=WizardLM%3A%20Empowering%20LLMs%20to%20Follow%20Complex%20Instructions&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 45, "section_title": "Synthetic Data & Data Generation", "source_note": "Evol-Instruct", "title": "WizardLM: Empowering LLMs to Follow Complex Instructions", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Mitra et al.", "id": 787, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AgentInstruct%3A%20Toward%20Generative%20Teaching%20with%20Agentic%20Flows&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AgentInstruct%3A%20Toward%20Generative%20Teaching%20with%20Agentic%20Flows%20Mitra%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=AgentInstruct%3A%20Toward%20Generative%20Teaching%20with%20Agentic%20Flows&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 45, "section_title": "Synthetic Data & Data Generation", "source_note": "Agent-generated training data", "title": "AgentInstruct: Toward Generative Teaching with Agentic Flows", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 245 ], "severity": "warning" } ], "authors": "Chen et al.", "id": 788, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SPIN%3A%20Self-Play%20Fine-Tuning%20Converts%20Weak%20LMs%20to%20Strong&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SPIN%3A%20Self-Play%20Fine-Tuning%20Converts%20Weak%20LMs%20to%20Strong%20Chen%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=SPIN%3A%20Self-Play%20Fine-Tuning%20Converts%20Weak%20LMs%20to%20Strong&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 45, "section_title": "Synthetic Data & Data Generation", "source_note": "Self-play data generation", "title": "SPIN: Self-Play Fine-Tuning Converts Weak LMs to Strong", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Patel et al.", "id": 789, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DataDreamer%3A%20A%20Tool%20for%20Synthetically%20Generating%2C%20Transforming%2C%20and%20Analyzing%20NLP%20Data&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DataDreamer%3A%20A%20Tool%20for%20Synthetically%20Generating%2C%20Transforming%2C%20and%20Analyzing%20NLP%20Data%20Patel%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=DataDreamer%3A%20A%20Tool%20for%20Synthetically%20Generating%2C%20Transforming%2C%20and%20Analyzing%20NLP%20Data&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 45, "section_title": "Synthetic Data & Data Generation", "source_note": "Synthetic data toolkit", "title": "DataDreamer: A Tool for Synthetically Generating, Transforming, and Analyzing NLP Data", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Chan et al.", "id": 790, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scaling%20Synthetic%20Data%20Creation%20with%201B%20Personas&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scaling%20Synthetic%20Data%20Creation%20with%201B%20Personas%20Chan%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scaling%20Synthetic%20Data%20Creation%20with%201B%20Personas&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 45, "section_title": "Synthetic Data & Data Generation", "source_note": "Persona-driven synthetic data", "title": "Scaling Synthetic Data Creation with 1B Personas", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Wu et al.", "id": 791, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Memorizing%20Transformers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Memorizing%20Transformers%20Wu%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Memorizing%20Transformers&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 46, "section_title": "Long Context & Memory Systems", "source_note": "kNN-augmented attention", "title": "Memorizing Transformers", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Martins et al.", "id": 792, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=%E2%88%9E-former%3A%20Infinite%20Memory%20Transformer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=%E2%88%9E-former%3A%20Infinite%20Memory%20Transformer%20Martins%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=%E2%88%9E-former%3A%20Infinite%20Memory%20Transformer&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 46, "section_title": "Long Context & Memory Systems", "source_note": "Unbounded memory", "title": "∞-former: Infinite Memory Transformer", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Ding et al.", "id": 793, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LongNet%3A%20Scaling%20Transformers%20to%201B%20Tokens&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LongNet%3A%20Scaling%20Transformers%20to%201B%20Tokens%20Ding%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=LongNet%3A%20Scaling%20Transformers%20to%201B%20Tokens&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 46, "section_title": "Long Context & Memory Systems", "source_note": "Dilated attention", "title": "LongNet: Scaling Transformers to 1B Tokens", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Munkhdalai et al.", "id": 794, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Leave%20No%20Context%20Behind%3A%20Efficient%20Infinite-Context%20Transformers%20with%20Infini-attention&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Leave%20No%20Context%20Behind%3A%20Efficient%20Infinite-Context%20Transformers%20with%20Infini-attention%20Munkhdalai%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Leave%20No%20Context%20Behind%3A%20Efficient%20Infinite-Context%20Transformers%20with%20Infini-attention&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 46, "section_title": "Long Context & Memory Systems", "source_note": "Compressive memory", "title": "Leave No Context Behind: Efficient Infinite-Context Transformers with Infini-attention", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Kamradt", "id": 795, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Needle%20in%20a%20Haystack%20Evaluation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Needle%20in%20a%20Haystack%20Evaluation%20Kamradt%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Needle%20in%20a%20Haystack%20Evaluation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 46, "section_title": "Long Context & Memory Systems", "source_note": "Long context evaluation", "title": "Needle in a Haystack Evaluation", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Hsieh et al.", "id": 796, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Ruler%3A%20What%27s%20the%20Real%20Context%20Size%20of%20Your%20LLM%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Ruler%3A%20What%27s%20the%20Real%20Context%20Size%20of%20Your%20LLM%3F%20Hsieh%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Ruler%3A%20What%27s%20the%20Real%20Context%20Size%20of%20Your%20LLM%3F&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 46, "section_title": "Long Context & Memory Systems", "source_note": "Long context benchmark", "title": "Ruler: What's the Real Context Size of Your LLM?", "work_type": "Benchmark or dataset paper", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Packer et al.", "id": 797, "links": { "canonical_url": "https://arxiv.org/abs/2310.08560", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2310.08560.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MemGPT%3A%20Towards%20LLMs%20as%20Operating%20Systems&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MemGPT%3A%20Towards%20LLMs%20as%20Operating%20Systems%20Packer%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=MemGPT%3A%20Towards%20LLMs%20as%20Operating%20Systems&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2310.08560.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 46, "section_title": "Long Context & Memory Systems", "source_note": "Virtual context management", "title": "MemGPT: Towards LLMs as Operating Systems", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Ding et al.", "id": 798, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LongRoPE%3A%20Extending%20LLM%20Context%20Window%20Beyond%202M%20Tokens&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LongRoPE%3A%20Extending%20LLM%20Context%20Window%20Beyond%202M%20Tokens%20Ding%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=LongRoPE%3A%20Extending%20LLM%20Context%20Window%20Beyond%202M%20Tokens&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 46, "section_title": "Long Context & Memory Systems", "source_note": "Extreme context extension", "title": "LongRoPE: Extending LLM Context Window Beyond 2M Tokens", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Anthropic", "id": 799, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Claude%27s%20200K%20Context%20%28Anthropic%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Claude%27s%20200K%20Context%20%28Anthropic%29%20Anthropic%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Claude%27s%20200K%20Context%20%28Anthropic%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 46, "section_title": "Long Context & Memory Systems", "source_note": "Long context in production", "title": "Claude's 200K Context (Anthropic)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Google DeepMind", "id": 800, "links": { "canonical_url": "https://arxiv.org/abs/2403.05530", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2403.05530.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Gemini%201.5%20Pro%3A%20Long%20Context%20%281M%20tokens%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Gemini%201.5%20Pro%3A%20Long%20Context%20%281M%20tokens%29%20Google%20DeepMind%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Gemini%201.5%20Pro%3A%20Long%20Context%20%281M%20tokens%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2403.05530.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 46, "section_title": "Long Context & Memory Systems", "source_note": "Million-token context", "title": "Gemini 1.5 Pro: Long Context (1M tokens)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Willard & Louf", "id": 801, "links": { "canonical_url": "https://arxiv.org/abs/2307.09702", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2307.09702.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Outlines%3A%20Structured%20Text%20Generation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Outlines%3A%20Structured%20Text%20Generation%20Willard%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Outlines%3A%20Structured%20Text%20Generation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2307.09702.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 47, "section_title": "Structured & Constrained Generation", "source_note": "Guaranteed JSON/schema output", "title": "Outlines: Structured Text Generation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Microsoft", "id": 802, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Guidance%3A%20Constrained%20Generation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Guidance%3A%20Constrained%20Generation%20Microsoft%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Guidance%3A%20Constrained%20Generation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 47, "section_title": "Structured & Constrained Generation", "source_note": "Constrained LLM output", "title": "Guidance: Constrained Generation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 803, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Grammar%20of%20Thought%3A%20LLM%20Structured%20Reasoning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Grammar%20of%20Thought%3A%20LLM%20Structured%20Reasoning%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Grammar%20of%20Thought%3A%20LLM%20Structured%20Reasoning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 47, "section_title": "Structured & Constrained Generation", "source_note": "Grammar-constrained reasoning", "title": "Grammar of Thought: LLM Structured Reasoning", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Beurer-Kellner et al.", "id": 804, "links": { "canonical_url": "https://arxiv.org/abs/2212.06094", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2212.06094.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LMQL%3A%20Language%20Model%20Query%20Language&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LMQL%3A%20Language%20Model%20Query%20Language%20Beurer-Kellner%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=LMQL%3A%20Language%20Model%20Query%20Language&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2212.06094.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 47, "section_title": "Structured & Constrained Generation", "source_note": "Query language for LLMs", "title": "LMQL: Language Model Query Language", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Khattab et al.", "id": 805, "links": { "canonical_url": "https://arxiv.org/abs/2310.03714", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2310.03714.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DSPy%3A%20Compiling%20Declarative%20Language%20Model%20Calls%20into%20Pipelines&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DSPy%3A%20Compiling%20Declarative%20Language%20Model%20Calls%20into%20Pipelines%20Khattab%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=DSPy%3A%20Compiling%20Declarative%20Language%20Model%20Calls%20into%20Pipelines&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2310.03714.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 47, "section_title": "Structured & Constrained Generation", "source_note": "Programming framework for LMs", "title": "DSPy: Compiling Declarative Language Model Calls into Pipelines", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zheng et al.", "id": 806, "links": { "canonical_url": "https://arxiv.org/abs/2312.07104", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2312.07104.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SGLang%3A%20Efficient%20Execution%20of%20Structured%20LM%20Programs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SGLang%3A%20Efficient%20Execution%20of%20Structured%20LM%20Programs%20Zheng%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=SGLang%3A%20Efficient%20Execution%20of%20Structured%20LM%20Programs&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2312.07104.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 47, "section_title": "Structured & Constrained Generation", "source_note": "Structured generation runtime", "title": "SGLang: Efficient Execution of Structured LM Programs", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Liu", "id": 807, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Instructor%3A%20Structured%20Outputs%20from%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Instructor%3A%20Structured%20Outputs%20from%20LLMs%20Liu%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Instructor%3A%20Structured%20Outputs%20from%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 47, "section_title": "Structured & Constrained Generation", "source_note": "Pydantic-based extraction", "title": "Instructor: Structured Outputs from LLMs", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Microsoft", "id": 808, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=TypeChat&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=TypeChat%20Microsoft%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=TypeChat&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 47, "section_title": "Structured & Constrained Generation", "source_note": "Type-safe LLM outputs", "title": "TypeChat", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 809, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=JSON%20Mode%20/%20Structured%20Outputs%20%28OpenAI%2C%20Anthropic%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=JSON%20Mode%20/%20Structured%20Outputs%20%28OpenAI%2C%20Anthropic%29%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=JSON%20Mode%20/%20Structured%20Outputs%20%28OpenAI%2C%20Anthropic%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 47, "section_title": "Structured & Constrained Generation", "source_note": "Native structured output", "title": "JSON Mode / Structured Outputs (OpenAI, Anthropic)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Microsoft", "id": 810, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Semantic%20Kernel&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Semantic%20Kernel%20Microsoft%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Semantic%20Kernel&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 47, "section_title": "Structured & Constrained Generation", "source_note": "AI orchestration SDK", "title": "Semantic Kernel", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Wu et al.", "id": 811, "links": { "canonical_url": "https://arxiv.org/abs/2303.17564", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2303.17564.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BloombergGPT%3A%20A%20Large%20Language%20Model%20for%20Finance&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BloombergGPT%3A%20A%20Large%20Language%20Model%20for%20Finance%20Wu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=BloombergGPT%3A%20A%20Large%20Language%20Model%20for%20Finance&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2303.17564.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 48, "section_title": "AI for Finance (BFSI-relevant)", "source_note": "Finance-specific LLM", "title": "BloombergGPT: A Large Language Model for Finance", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Yang et al.", "id": 812, "links": { "canonical_url": "https://arxiv.org/abs/2306.06031", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2306.06031.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=FinGPT%3A%20Open-Source%20Financial%20Large%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=FinGPT%3A%20Open-Source%20Financial%20Large%20Language%20Models%20Yang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=FinGPT%3A%20Open-Source%20Financial%20Large%20Language%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2306.06031.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 48, "section_title": "AI for Finance (BFSI-relevant)", "source_note": "Open finance LLM", "title": "FinGPT: Open-Source Financial Large Language Models", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Araci", "id": 813, "links": { "canonical_url": "https://arxiv.org/abs/1908.10063", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1908.10063.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=FinBERT%3A%20Financial%20Sentiment%20Analysis&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=FinBERT%3A%20Financial%20Sentiment%20Analysis%20Araci%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=FinBERT%3A%20Financial%20Sentiment%20Analysis&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1908.10063.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 48, "section_title": "AI for Finance (BFSI-relevant)", "source_note": "BERT for finance", "title": "FinBERT: Financial Sentiment Analysis", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 814, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Deep%20Learning%20for%20Stock%20Market%20Prediction&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Deep%20Learning%20for%20Stock%20Market%20Prediction%20Various%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Deep%20Learning%20for%20Stock%20Market%20Prediction&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 48, "section_title": "AI for Finance (BFSI-relevant)", "source_note": "DL in trading", "title": "Deep Learning for Stock Market Prediction", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 815, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLMs%20for%20Financial%20NLP%3A%20Opportunities%20and%20Challenges&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLMs%20for%20Financial%20NLP%3A%20Opportunities%20and%20Challenges%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLMs%20for%20Financial%20NLP%3A%20Opportunities%20and%20Challenges&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 48, "section_title": "AI for Finance (BFSI-relevant)", "source_note": "Finance NLP survey", "title": "LLMs for Financial NLP: Opportunities and Challenges", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 816, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Fraud%20Detection%20using%20Machine%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Fraud%20Detection%20using%20Machine%20Learning%20Various%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Fraud%20Detection%20using%20Machine%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 48, "section_title": "AI for Finance (BFSI-relevant)", "source_note": "ML for fraud", "title": "Fraud Detection using Machine Learning", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Lessmann et al.", "id": 817, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Credit%20Scoring%20with%20Machine%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Credit%20Scoring%20with%20Machine%20Learning%20Lessmann%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Credit%20Scoring%20with%20Machine%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 48, "section_title": "AI for Finance (BFSI-relevant)", "source_note": "ML credit scoring", "title": "Credit Scoring with Machine Learning", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 818, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=KYC/AML%20with%20NLP&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=KYC/AML%20with%20NLP%20Various%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=KYC/AML%20with%20NLP&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 48, "section_title": "AI for Finance (BFSI-relevant)", "source_note": "NLP for compliance", "title": "KYC/AML with NLP", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 819, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Explainable%20AI%20for%20Banking&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Explainable%20AI%20for%20Banking%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Explainable%20AI%20for%20Banking&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 48, "section_title": "AI for Finance (BFSI-relevant)", "source_note": "XAI in BFSI", "title": "Explainable AI for Banking", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 820, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Document%20AI%20for%20Financial%20Services&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Document%20AI%20for%20Financial%20Services%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Document%20AI%20for%20Financial%20Services&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 48, "section_title": "AI for Finance (BFSI-relevant)", "source_note": "Document processing in finance", "title": "Document AI for Financial Services", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Xu et al.", "id": 821, "links": { "canonical_url": "https://arxiv.org/abs/1912.13318", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1912.13318.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LayoutLM%3A%20Pre-training%20of%20Text%20and%20Layout%20for%20Document%20AI&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LayoutLM%3A%20Pre-training%20of%20Text%20and%20Layout%20for%20Document%20AI%20Xu%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=LayoutLM%3A%20Pre-training%20of%20Text%20and%20Layout%20for%20Document%20AI&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1912.13318.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 49, "section_title": "Document AI & Information Extraction", "source_note": "Layout-aware document model", "title": "LayoutLM: Pre-training of Text and Layout for Document AI", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Huang et al.", "id": 822, "links": { "canonical_url": "https://arxiv.org/abs/2204.08387", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2204.08387.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LayoutLMv3%3A%20Pre-training%20for%20Document%20AI%20with%20Unified%20Text%20and%20Image%20Masking&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LayoutLMv3%3A%20Pre-training%20for%20Document%20AI%20with%20Unified%20Text%20and%20Image%20Masking%20Huang%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=LayoutLMv3%3A%20Pre-training%20for%20Document%20AI%20with%20Unified%20Text%20and%20Image%20Masking&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2204.08387.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 49, "section_title": "Document AI & Information Extraction", "source_note": "Improved document model", "title": "LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Kim et al.", "id": 823, "links": { "canonical_url": "https://arxiv.org/abs/2111.15664", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2111.15664.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Donut%3A%20Document%20Understanding%20Transformer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Donut%3A%20Document%20Understanding%20Transformer%20Kim%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Donut%3A%20Document%20Understanding%20Transformer&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2111.15664.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 49, "section_title": "Document AI & Information Extraction", "source_note": "OCR-free document understanding", "title": "Donut: Document Understanding Transformer", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "PaddlePaddle", "id": 824, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=PaddleOCR&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=PaddleOCR%20PaddlePaddle%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=PaddleOCR&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 49, "section_title": "Document AI & Information Extraction", "source_note": "Open-source OCR toolkit", "title": "PaddleOCR", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Li et al.", "id": 825, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=TrOCR%3A%20Transformer-based%20Optical%20Character%20Recognition&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=TrOCR%3A%20Transformer-based%20Optical%20Character%20Recognition%20Li%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=TrOCR%3A%20Transformer-based%20Optical%20Character%20Recognition&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 49, "section_title": "Document AI & Information Extraction", "source_note": "Transformer for OCR", "title": "TrOCR: Transformer-based Optical Character Recognition", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Smock et al.", "id": 826, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Table%20Transformer%20%28TATR%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Table%20Transformer%20%28TATR%29%20Smock%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Table%20Transformer%20%28TATR%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 49, "section_title": "Document AI & Information Extraction", "source_note": "Table detection and structure", "title": "Table Transformer (TATR)", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Zhou et al.", "id": 827, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DocPrompting%3A%20Generating%20Code%20by%20Retrieving%20the%20Docs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DocPrompting%3A%20Generating%20Code%20by%20Retrieving%20the%20Docs%20Zhou%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=DocPrompting%3A%20Generating%20Code%20by%20Retrieving%20the%20Docs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 49, "section_title": "Document AI & Information Extraction", "source_note": "Document-augmented code gen", "title": "DocPrompting: Generating Code by Retrieving the Docs", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Blecher et al.", "id": 828, "links": { "canonical_url": "https://arxiv.org/abs/2308.13418", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2308.13418.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Nougat%3A%20Neural%20Optical%20Understanding%20for%20Academic%20Documents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Nougat%3A%20Neural%20Optical%20Understanding%20for%20Academic%20Documents%20Blecher%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Nougat%3A%20Neural%20Optical%20Understanding%20for%20Academic%20Documents&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2308.13418.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 49, "section_title": "Document AI & Information Extraction", "source_note": "Academic PDF to markdown", "title": "Nougat: Neural Optical Understanding for Academic Documents", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Faysse et al.", "id": 829, "links": { "canonical_url": "https://arxiv.org/abs/2407.01449", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2407.01449.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ColPali%3A%20Efficient%20Document%20Retrieval%20with%20Vision%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ColPali%3A%20Efficient%20Document%20Retrieval%20with%20Vision%20Language%20Models%20Faysse%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=ColPali%3A%20Efficient%20Document%20Retrieval%20with%20Vision%20Language%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2407.01449.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 49, "section_title": "Document AI & Information Extraction", "source_note": "Visual document retrieval", "title": "ColPali: Efficient Document Retrieval with Vision Language Models", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Datalab", "id": 830, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Marker%3A%20PDF%20to%20Markdown%20Conversion&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Marker%3A%20PDF%20to%20Markdown%20Conversion%20Datalab%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Marker%3A%20PDF%20to%20Markdown%20Conversion&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 49, "section_title": "Document AI & Information Extraction", "source_note": "PDF extraction", "title": "Marker: PDF to Markdown Conversion", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Bojarski et al.", "id": 831, "links": { "canonical_url": "https://arxiv.org/abs/1604.07316", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1604.07316.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=End%20to%20End%20Learning%20for%20Self-Driving%20Cars&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=End%20to%20End%20Learning%20for%20Self-Driving%20Cars%20Bojarski%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=End%20to%20End%20Learning%20for%20Self-Driving%20Cars&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1604.07316.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 50, "section_title": "Autonomous Driving & Navigation", "source_note": "End-to-end driving", "title": "End to End Learning for Self-Driving Cars", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Qi et al.", "id": 832, "links": { "canonical_url": "https://arxiv.org/abs/1612.00593", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1612.00593.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=PointNet%3A%20Deep%20Learning%20on%20Point%20Sets&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=PointNet%3A%20Deep%20Learning%20on%20Point%20Sets%20Qi%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=PointNet%3A%20Deep%20Learning%20on%20Point%20Sets&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1612.00593.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 50, "section_title": "Autonomous Driving & Navigation", "source_note": "3D point cloud processing", "title": "PointNet: Deep Learning on Point Sets", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Qi et al.", "id": 833, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=PointNet%2B%2B%3A%20Deep%20Hierarchical%20Feature%20Learning%20on%20Point%20Sets&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=PointNet%2B%2B%3A%20Deep%20Hierarchical%20Feature%20Learning%20on%20Point%20Sets%20Qi%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=PointNet%2B%2B%3A%20Deep%20Hierarchical%20Feature%20Learning%20on%20Point%20Sets&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 50, "section_title": "Autonomous Driving & Navigation", "source_note": "Hierarchical point processing", "title": "PointNet++: Deep Hierarchical Feature Learning on Point Sets", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Zhou & Tuzel", "id": 834, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=VoxelNet%3A%20End-to-End%20Learning%20for%20Point%20Cloud%20Based%203D%20Object%20Detection&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=VoxelNet%3A%20End-to-End%20Learning%20for%20Point%20Cloud%20Based%203D%20Object%20Detection%20Zhou%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=VoxelNet%3A%20End-to-End%20Learning%20for%20Point%20Cloud%20Based%203D%20Object%20Detection&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 50, "section_title": "Autonomous Driving & Navigation", "source_note": "Voxel-based 3D detection", "title": "VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Li et al.", "id": 835, "links": { "canonical_url": "https://arxiv.org/abs/2203.17270", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2203.17270.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BEVFormer%3A%20Learning%20Bird%27s-Eye-View%20Representation%20from%20Multi-Camera%20Images&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BEVFormer%3A%20Learning%20Bird%27s-Eye-View%20Representation%20from%20Multi-Camera%20Images%20Li%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=BEVFormer%3A%20Learning%20Bird%27s-Eye-View%20Representation%20from%20Multi-Camera%20Images&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2203.17270.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 50, "section_title": "Autonomous Driving & Navigation", "source_note": "Camera-based BEV", "title": "BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Hu et al.", "id": 836, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=UniAD%3A%20Planning-Oriented%20Autonomous%20Driving&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=UniAD%3A%20Planning-Oriented%20Autonomous%20Driving%20Hu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=UniAD%3A%20Planning-Oriented%20Autonomous%20Driving&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 50, "section_title": "Autonomous Driving & Navigation", "source_note": "Unified autonomous driving", "title": "UniAD: Planning-Oriented Autonomous Driving", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 837, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLM-based%20Driving%20Agents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLM-based%20Driving%20Agents%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLM-based%20Driving%20Agents&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 50, "section_title": "Autonomous Driving & Navigation", "source_note": "LLMs for driving decisions", "title": "LLM-based Driving Agents", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Sima et al.", "id": 838, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DriveLM%3A%20Driving%20with%20Graph%20Visual%20Question%20Answering&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DriveLM%3A%20Driving%20with%20Graph%20Visual%20Question%20Answering%20Sima%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=DriveLM%3A%20Driving%20with%20Graph%20Visual%20Question%20Answering&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 50, "section_title": "Autonomous Driving & Navigation", "source_note": "VLM for driving", "title": "DriveLM: Driving with Graph Visual Question Answering", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Xu et al.", "id": 839, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DriveGPT4%3A%20Interpretable%20End-to-end%20Autonomous%20Driving&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DriveGPT4%3A%20Interpretable%20End-to-end%20Autonomous%20Driving%20Xu%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=DriveGPT4%3A%20Interpretable%20End-to-end%20Autonomous%20Driving&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 50, "section_title": "Autonomous Driving & Navigation", "source_note": "GPT-4 for driving", "title": "DriveGPT4: Interpretable End-to-end Autonomous Driving", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Sun et al.", "id": 840, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Waymo%20Open%20Dataset&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Waymo%20Open%20Dataset%20Sun%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=Waymo%20Open%20Dataset&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 50, "section_title": "Autonomous Driving & Navigation", "source_note": "Large-scale driving dataset", "title": "Waymo Open Dataset", "work_type": "Benchmark or dataset paper", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Abadi et al.", "id": 841, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=TensorFlow%3A%20Large-Scale%20Machine%20Learning%20on%20Heterogeneous%20Systems&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=TensorFlow%3A%20Large-Scale%20Machine%20Learning%20on%20Heterogeneous%20Systems%20Abadi%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=TensorFlow%3A%20Large-Scale%20Machine%20Learning%20on%20Heterogeneous%20Systems&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 51, "section_title": "AI Infrastructure & MLOps", "source_note": "TensorFlow framework", "title": "TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Paszke et al.", "id": 842, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=PyTorch%3A%20An%20Imperative%20Style%2C%20High-Performance%20Deep%20Learning%20Library&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=PyTorch%3A%20An%20Imperative%20Style%2C%20High-Performance%20Deep%20Learning%20Library%20Paszke%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=PyTorch%3A%20An%20Imperative%20Style%2C%20High-Performance%20Deep%20Learning%20Library&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 51, "section_title": "AI Infrastructure & MLOps", "source_note": "PyTorch framework", "title": "PyTorch: An Imperative Style, High-Performance Deep Learning Library", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Bradbury et al.", "id": 843, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=JAX%3A%20Composable%20Transformations%20of%20Python%2BNumPy&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=JAX%3A%20Composable%20Transformations%20of%20Python%2BNumPy%20Bradbury%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=JAX%3A%20Composable%20Transformations%20of%20Python%2BNumPy&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 51, "section_title": "AI Infrastructure & MLOps", "source_note": "JAX framework", "title": "JAX: Composable Transformations of Python+NumPy", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Zaharia et al.", "id": 844, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MLflow%3A%20A%20Platform%20for%20the%20ML%20Lifecycle&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MLflow%3A%20A%20Platform%20for%20the%20ML%20Lifecycle%20Zaharia%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=MLflow%3A%20A%20Platform%20for%20the%20ML%20Lifecycle&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 51, "section_title": "AI Infrastructure & MLOps", "source_note": "ML experiment tracking", "title": "MLflow: A Platform for the ML Lifecycle", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Sculley et al.", "id": 845, "links": { "canonical_url": "https://papers.nips.cc/paper/2015/hash/86df7dcfd896fcaf2674f757a2463eba-Abstract.html", "corrected_by_audit": false, "direct_url": "https://papers.nips.cc/paper/2015/hash/86df7dcfd896fcaf2674f757a2463eba-Abstract.html", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Hidden%20Technical%20Debt%20in%20ML%20Systems&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Hidden%20Technical%20Debt%20in%20ML%20Systems%20Sculley%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Hidden%20Technical%20Debt%20in%20ML%20Systems&sort=relevance" }, "supplied_direct_url": "https://papers.nips.cc/paper/2015/hash/86df7dcfd896fcaf2674f757a2463eba-Abstract.html" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 51, "section_title": "AI Infrastructure & MLOps", "source_note": "ML technical debt", "title": "Hidden Technical Debt in ML Systems", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Moritz et al.", "id": 846, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Ray%3A%20A%20Distributed%20Framework%20for%20Emerging%20AI%20Applications&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Ray%3A%20A%20Distributed%20Framework%20for%20Emerging%20AI%20Applications%20Moritz%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Ray%3A%20A%20Distributed%20Framework%20for%20Emerging%20AI%20Applications&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 51, "section_title": "AI Infrastructure & MLOps", "source_note": "Distributed computing for AI", "title": "Ray: A Distributed Framework for Emerging AI Applications", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 847, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Kubernetes%20for%20ML%20Workloads%20%28Kubeflow%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Kubernetes%20for%20ML%20Workloads%20%28Kubeflow%29%20Various%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Kubernetes%20for%20ML%20Workloads%20%28Kubeflow%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 51, "section_title": "AI Infrastructure & MLOps", "source_note": "ML on Kubernetes", "title": "Kubernetes for ML Workloads (Kubeflow)", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Baylor et al.", "id": 848, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Feature%20Stores%20for%20ML&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Feature%20Stores%20for%20ML%20Baylor%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Feature%20Stores%20for%20ML&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 51, "section_title": "AI Infrastructure & MLOps", "source_note": "Feature management", "title": "Feature Stores for ML", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Sato et al.", "id": 849, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Continuous%20Delivery%20for%20ML%20%28CD4ML%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Continuous%20Delivery%20for%20ML%20%28CD4ML%29%20Sato%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Continuous%20Delivery%20for%20ML%20%28CD4ML%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 51, "section_title": "AI Infrastructure & MLOps", "source_note": "MLOps practices", "title": "Continuous Delivery for ML (CD4ML)", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [ { "code": "non_paper_or_multi_work", "message": "A multi-generation document family rather than one work.", "required_action": "Split into canonical architecture white papers with individual years and URLs.", "severity": "blocking" } ], "authors": "NVIDIA", "id": 850, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=NVIDIA%20GPU%20Architecture%3A%20From%20Pascal%20to%20Hopper&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=NVIDIA%20GPU%20Architecture%3A%20From%20Pascal%20to%20Hopper%20NVIDIA%202016-2024", "semantic_scholar": "https://www.semanticscholar.org/search?q=NVIDIA%20GPU%20Architecture%3A%20From%20Pascal%20to%20Hopper&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 51, "section_title": "AI Infrastructure & MLOps", "source_note": "GPU evolution for AI", "title": "NVIDIA GPU Architecture: From Pascal to Hopper", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016-2024" }, { "audit_flags": [], "authors": "Zhou et al.", "id": 851, "links": { "canonical_url": "https://arxiv.org/abs/2307.13854", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2307.13854.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=WebArena%3A%20A%20Realistic%20Web%20Environment%20for%20Building%20Autonomous%20Agents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=WebArena%3A%20A%20Realistic%20Web%20Environment%20for%20Building%20Autonomous%20Agents%20Zhou%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=WebArena%3A%20A%20Realistic%20Web%20Environment%20for%20Building%20Autonomous%20Agents&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2307.13854.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 52, "section_title": "Agentic Web & Computer Use", "source_note": "Web browsing benchmark", "title": "WebArena: A Realistic Web Environment for Building Autonomous Agents", "work_type": "Benchmark or dataset paper", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Deng et al.", "id": 852, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mind2Web%3A%20Towards%20a%20Generalist%20Agent%20for%20the%20Web&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mind2Web%3A%20Towards%20a%20Generalist%20Agent%20for%20the%20Web%20Deng%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mind2Web%3A%20Towards%20a%20Generalist%20Agent%20for%20the%20Web&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 52, "section_title": "Agentic Web & Computer Use", "source_note": "Web navigation agent", "title": "Mind2Web: Towards a Generalist Agent for the Web", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Xie et al.", "id": 853, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=OS-World%3A%20Benchmarking%20Multimodal%20Agents%20for%20Open-Ended%20Tasks%20in%20Real%20Computer%20Environments&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=OS-World%3A%20Benchmarking%20Multimodal%20Agents%20for%20Open-Ended%20Tasks%20in%20Real%20Computer%20Environments%20Xie%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=OS-World%3A%20Benchmarking%20Multimodal%20Agents%20for%20Open-Ended%20Tasks%20in%20Real%20Computer%20Environments&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 52, "section_title": "Agentic Web & Computer Use", "source_note": "OS-level agent benchmark", "title": "OS-World: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments", "work_type": "Benchmark or dataset paper", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 913 ], "severity": "warning" } ], "authors": "Anthropic", "id": 854, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Computer%20Use%20%28Anthropic%20Claude%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Computer%20Use%20%28Anthropic%20Claude%29%20Anthropic%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Computer%20Use%20%28Anthropic%20Claude%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 52, "section_title": "Agentic Web & Computer Use", "source_note": "GUI interaction capability", "title": "Computer Use (Anthropic Claude)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Hong et al.", "id": 855, "links": { "canonical_url": "https://arxiv.org/abs/2312.08914", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2312.08914.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=CogAgent%3A%20A%20Visual%20Language%20Model%20for%20GUI%20Agents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=CogAgent%3A%20A%20Visual%20Language%20Model%20for%20GUI%20Agents%20Hong%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=CogAgent%3A%20A%20Visual%20Language%20Model%20for%20GUI%20Agents&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2312.08914.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 52, "section_title": "Agentic Web & Computer Use", "source_note": "Visual GUI agent", "title": "CogAgent: A Visual Language Model for GUI Agents", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 856, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AppAgent%3A%20Multimodal%20Agents%20as%20Smartphone%20Users&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AppAgent%3A%20Multimodal%20Agents%20as%20Smartphone%20Users%20Zhang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=AppAgent%3A%20Multimodal%20Agents%20as%20Smartphone%20Users&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 52, "section_title": "Agentic Web & Computer Use", "source_note": "Mobile app agents", "title": "AppAgent: Multimodal Agents as Smartphone Users", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Niu et al.", "id": 857, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=ScreenAgent%3A%20A%20Vision%20Language%20Model-Driven%20Computer%20Control%20Agent&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=ScreenAgent%3A%20A%20Vision%20Language%20Model-Driven%20Computer%20Control%20Agent%20Niu%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=ScreenAgent%3A%20A%20Vision%20Language%20Model-Driven%20Computer%20Control%20Agent&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 52, "section_title": "Agentic Web & Computer Use", "source_note": "Screen interaction agent", "title": "ScreenAgent: A Vision Language Model-Driven Computer Control Agent", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 858, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=UFO%3A%20A%20UI-Focused%20Agent%20for%20Windows%20OS%20Interaction&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=UFO%3A%20A%20UI-Focused%20Agent%20for%20Windows%20OS%20Interaction%20Zhang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=UFO%3A%20A%20UI-Focused%20Agent%20for%20Windows%20OS%20Interaction&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 52, "section_title": "Agentic Web & Computer Use", "source_note": "Windows UI agent", "title": "UFO: A UI-Focused Agent for Windows OS Interaction", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "He et al.", "id": 859, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=WebVoyager%3A%20Building%20an%20End-to-End%20Web%20Agent&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=WebVoyager%3A%20Building%20an%20End-to-End%20Web%20Agent%20He%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=WebVoyager%3A%20Building%20an%20End-to-End%20Web%20Agent&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 52, "section_title": "Agentic Web & Computer Use", "source_note": "Web browsing agent", "title": "WebVoyager: Building an End-to-End Web Agent", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Anthropic", "id": 860, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Anthropic%20MCP%20for%20Agents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Anthropic%20MCP%20for%20Agents%20Anthropic%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Anthropic%20MCP%20for%20Agents&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 52, "section_title": "Agentic Web & Computer Use", "source_note": "Agent-tool protocol", "title": "Anthropic MCP for Agents", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Mildenhall et al.", "id": 861, "links": { "canonical_url": "https://arxiv.org/abs/2003.08934", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2003.08934.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=NeRF%3A%20Representing%20Scenes%20as%20Neural%20Radiance%20Fields&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=NeRF%3A%20Representing%20Scenes%20as%20Neural%20Radiance%20Fields%20Mildenhall%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=NeRF%3A%20Representing%20Scenes%20as%20Neural%20Radiance%20Fields&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2003.08934.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 53, "section_title": "3D Generation & Neural Rendering", "source_note": "Neural radiance fields", "title": "NeRF: Representing Scenes as Neural Radiance Fields", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Müller et al.", "id": 862, "links": { "canonical_url": "https://arxiv.org/abs/2201.05989", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2201.05989.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Instant%20NGP&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Instant%20NGP%20M%C3%BCller%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Instant%20NGP&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2201.05989.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 53, "section_title": "3D Generation & Neural Rendering", "source_note": "Fast neural graphics primitives", "title": "Instant NGP", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [ { "code": "wrong_supplied_mapping_corrected", "message": "The supplied link named a different work and is corrected in this edition.", "original_target_title": "Flexible Techniques for Differentiable Rendering with 3D Gaussians", "severity": "resolved" } ], "authors": "Kerbl et al.", "id": 863, "links": { "canonical_url": "https://arxiv.org/abs/2308.04079", "corrected_by_audit": true, "direct_url": "https://arxiv.org/pdf/2308.04079.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=3D%20Gaussian%20Splatting%20for%20Real-Time%20Radiance%20Field%20Rendering&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=3D%20Gaussian%20Splatting%20for%20Real-Time%20Radiance%20Field%20Rendering%20Kerbl%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=3D%20Gaussian%20Splatting%20for%20Real-Time%20Radiance%20Field%20Rendering&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2308.14737.pdf" }, "publication_identity_status": "audit_corrected_discovery", "section_id": 53, "section_title": "3D Generation & Neural Rendering", "source_note": "Gaussian splatting", "title": "3D Gaussian Splatting for Real-Time Radiance Field Rendering", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Poole et al.", "id": 864, "links": { "canonical_url": "https://arxiv.org/abs/2209.14988", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2209.14988.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DreamFusion%3A%20Text-to-3D%20using%202D%20Diffusion&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DreamFusion%3A%20Text-to-3D%20using%202D%20Diffusion%20Poole%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=DreamFusion%3A%20Text-to-3D%20using%202D%20Diffusion&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2209.14988.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 53, "section_title": "3D Generation & Neural Rendering", "source_note": "Text-to-3D generation", "title": "DreamFusion: Text-to-3D using 2D Diffusion", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Lin et al.", "id": 865, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Magic3D%3A%20High-Resolution%20Text-to-3D%20Content%20Creation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Magic3D%3A%20High-Resolution%20Text-to-3D%20Content%20Creation%20Lin%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Magic3D%3A%20High-Resolution%20Text-to-3D%20Content%20Creation&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 53, "section_title": "3D Generation & Neural Rendering", "source_note": "High-res 3D generation", "title": "Magic3D: High-Resolution Text-to-3D Content Creation", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Liu et al.", "id": 866, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Zero-1-to-3%3A%20Zero-shot%20One%20Image%20to%203D%20Object&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Zero-1-to-3%3A%20Zero-shot%20One%20Image%20to%203D%20Object%20Liu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Zero-1-to-3%3A%20Zero-shot%20One%20Image%20to%203D%20Object&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 53, "section_title": "3D Generation & Neural Rendering", "source_note": "Single image to 3D", "title": "Zero-1-to-3: Zero-shot One Image to 3D Object", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Nichol et al.", "id": 867, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Point-E%3A%20A%20System%20for%20Generating%203D%20Point%20Clouds%20from%20Complex%20Prompts&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Point-E%3A%20A%20System%20for%20Generating%203D%20Point%20Clouds%20from%20Complex%20Prompts%20Nichol%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Point-E%3A%20A%20System%20for%20Generating%203D%20Point%20Clouds%20from%20Complex%20Prompts&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 53, "section_title": "3D Generation & Neural Rendering", "source_note": "Text-to-3D point cloud", "title": "Point-E: A System for Generating 3D Point Clouds from Complex Prompts", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Jun & Nichol", "id": 868, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Shap-E%3A%20Generating%20Conditional%203D%20Implicit%20Functions&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Shap-E%3A%20Generating%20Conditional%203D%20Implicit%20Functions%20Jun%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Shap-E%3A%20Generating%20Conditional%203D%20Implicit%20Functions&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 53, "section_title": "3D Generation & Neural Rendering", "source_note": "3D implicit generation", "title": "Shap-E: Generating Conditional 3D Implicit Functions", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 869, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Meshy%20/%20TripoSR%20/%20LRM&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Meshy%20/%20TripoSR%20/%20LRM%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Meshy%20/%20TripoSR%20/%20LRM&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 53, "section_title": "3D Generation & Neural Rendering", "source_note": "Fast 3D reconstruction", "title": "Meshy / TripoSR / LRM", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 870, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=4D%20Generation%3A%20Recent%20Progress%20and%20Opportunities&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=4D%20Generation%3A%20Recent%20Progress%20and%20Opportunities%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=4D%20Generation%3A%20Recent%20Progress%20and%20Opportunities&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 53, "section_title": "3D Generation & Neural Rendering", "source_note": "Dynamic 3D generation", "title": "4D Generation: Recent Progress and Opportunities", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Szegedy et al.", "id": 871, "links": { "canonical_url": "https://arxiv.org/abs/1312.6199", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1312.6199.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Intriguing%20Properties%20of%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Intriguing%20Properties%20of%20Neural%20Networks%20Szegedy%202014", "semantic_scholar": "https://www.semanticscholar.org/search?q=Intriguing%20Properties%20of%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1312.6199.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 54, "section_title": "Adversarial ML & Robustness", "source_note": "Adversarial examples discovered", "title": "Intriguing Properties of Neural Networks", "work_type": "Research-paper candidate", "year": 2014, "year_display": "2014" }, { "audit_flags": [], "authors": "Goodfellow, Shlens, Szegedy", "id": 872, "links": { "canonical_url": "https://arxiv.org/abs/1412.6572", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1412.6572.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Explaining%20and%20Harnessing%20Adversarial%20Examples%20%28FGSM%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Explaining%20and%20Harnessing%20Adversarial%20Examples%20%28FGSM%29%20Goodfellow%202015", "semantic_scholar": "https://www.semanticscholar.org/search?q=Explaining%20and%20Harnessing%20Adversarial%20Examples%20%28FGSM%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1412.6572.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 54, "section_title": "Adversarial ML & Robustness", "source_note": "Fast gradient sign method", "title": "Explaining and Harnessing Adversarial Examples (FGSM)", "work_type": "Research-paper candidate", "year": 2015, "year_display": "2015" }, { "audit_flags": [], "authors": "Madry et al.", "id": 873, "links": { "canonical_url": "https://arxiv.org/abs/1706.06083", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1706.06083.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Towards%20Deep%20Learning%20Models%20Resistant%20to%20Adversarial%20Attacks%20%28PGD%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Towards%20Deep%20Learning%20Models%20Resistant%20to%20Adversarial%20Attacks%20%28PGD%29%20Madry%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Towards%20Deep%20Learning%20Models%20Resistant%20to%20Adversarial%20Attacks%20%28PGD%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1706.06083.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 54, "section_title": "Adversarial ML & Robustness", "source_note": "PGD adversarial training", "title": "Towards Deep Learning Models Resistant to Adversarial Attacks (PGD)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Cohen, Rosenfeld, Kolter", "id": 874, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Certified%20Adversarial%20Robustness%20via%20Randomized%20Smoothing&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Certified%20Adversarial%20Robustness%20via%20Randomized%20Smoothing%20Cohen%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Certified%20Adversarial%20Robustness%20via%20Randomized%20Smoothing&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 54, "section_title": "Adversarial ML & Robustness", "source_note": "Certified defenses", "title": "Certified Adversarial Robustness via Randomized Smoothing", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Moosavi-Dezfooli et al.", "id": 875, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeepFool%3A%20A%20Simple%20and%20Accurate%20Method%20to%20Fool%20Deep%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeepFool%3A%20A%20Simple%20and%20Accurate%20Method%20to%20Fool%20Deep%20Neural%20Networks%20Moosavi-Dezfooli%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeepFool%3A%20A%20Simple%20and%20Accurate%20Method%20to%20Fool%20Deep%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 54, "section_title": "Adversarial ML & Robustness", "source_note": "Minimal adversarial perturbation", "title": "DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Kurakin et al.", "id": 876, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Adversarial%20Examples%20in%20the%20Physical%20World&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Adversarial%20Examples%20in%20the%20Physical%20World%20Kurakin%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Adversarial%20Examples%20in%20the%20Physical%20World&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 54, "section_title": "Adversarial ML & Robustness", "source_note": "Physical adversarial examples", "title": "Adversarial Examples in the Physical World", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Chen et al.", "id": 877, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Robust%20and%20Accurate%20Object%20Detection%20via%20Adversarial%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Robust%20and%20Accurate%20Object%20Detection%20via%20Adversarial%20Learning%20Chen%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Robust%20and%20Accurate%20Object%20Detection%20via%20Adversarial%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 54, "section_title": "Adversarial ML & Robustness", "source_note": "Adversarial training for detection", "title": "Robust and Accurate Object Detection via Adversarial Learning", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 878, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Adversarial%20Attacks%20on%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Adversarial%20Attacks%20on%20LLMs%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Adversarial%20Attacks%20on%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 54, "section_title": "Adversarial ML & Robustness", "source_note": "LLM robustness survey", "title": "Adversarial Attacks on LLMs", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "non_paper_or_multi_work", "message": "A research topic rather than a uniquely identifiable publication.", "required_action": "Replace with specific prompt-injection papers and canonical identifiers.", "severity": "blocking" } ], "authors": "Various", "id": 879, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Prompt%20Injection%20Attacks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Prompt%20Injection%20Attacks%20Various%202023-2024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Prompt%20Injection%20Attacks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 54, "section_title": "Adversarial ML & Robustness", "source_note": "LLM prompt injection", "title": "Prompt Injection Attacks", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023-2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 880, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Backdoor%20Attacks%20on%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Backdoor%20Attacks%20on%20LLMs%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Backdoor%20Attacks%20on%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 54, "section_title": "Adversarial ML & Robustness", "source_note": "Backdoor vulnerabilities", "title": "Backdoor Attacks on LLMs", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Finn, Abbeel, Levine", "id": 881, "links": { "canonical_url": "https://arxiv.org/abs/1703.03400", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1703.03400.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Model-Agnostic%20Meta-Learning%20%28MAML%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Model-Agnostic%20Meta-Learning%20%28MAML%29%20Finn%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Model-Agnostic%20Meta-Learning%20%28MAML%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1703.03400.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 55, "section_title": "Meta-Learning & Few-Shot Learning", "source_note": "MAML", "title": "Model-Agnostic Meta-Learning (MAML)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Vinyals et al.", "id": 882, "links": { "canonical_url": "https://arxiv.org/abs/1606.04080", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1606.04080.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Matching%20Networks%20for%20One%20Shot%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Matching%20Networks%20for%20One%20Shot%20Learning%20Vinyals%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Matching%20Networks%20for%20One%20Shot%20Learning&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1606.04080.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 55, "section_title": "Meta-Learning & Few-Shot Learning", "source_note": "Metric-based few-shot", "title": "Matching Networks for One Shot Learning", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Snell, Swersky, Zemel", "id": 883, "links": { "canonical_url": "https://arxiv.org/abs/1703.05175", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1703.05175.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Prototypical%20Networks%20for%20Few-Shot%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Prototypical%20Networks%20for%20Few-Shot%20Learning%20Snell%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Prototypical%20Networks%20for%20Few-Shot%20Learning&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1703.05175.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 55, "section_title": "Meta-Learning & Few-Shot Learning", "source_note": "Prototype-based classification", "title": "Prototypical Networks for Few-Shot Learning", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Santoro et al.", "id": 884, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Learning%20to%20Learn%20with%20Compound%20HD%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Learning%20to%20Learn%20with%20Compound%20HD%20Models%20Santoro%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Learning%20to%20Learn%20with%20Compound%20HD%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 55, "section_title": "Meta-Learning & Few-Shot Learning", "source_note": "Meta-learning with memory", "title": "Learning to Learn with Compound HD Models", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Hospedales et al.", "id": 885, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Meta-Learning%3A%20A%20Survey&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Meta-Learning%3A%20A%20Survey%20Hospedales%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Meta-Learning%3A%20A%20Survey&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 55, "section_title": "Meta-Learning & Few-Shot Learning", "source_note": "Meta-learning survey", "title": "Meta-Learning: A Survey", "work_type": "Survey or review", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Nichol, Achiam, Schulman", "id": 886, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Reptile%3A%20A%20Scalable%20Metalearning%20Algorithm&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Reptile%3A%20A%20Scalable%20Metalearning%20Algorithm%20Nichol%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Reptile%3A%20A%20Scalable%20Metalearning%20Algorithm&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 55, "section_title": "Meta-Learning & Few-Shot Learning", "source_note": "Simple meta-learning", "title": "Reptile: A Scalable Metalearning Algorithm", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Rusu et al.", "id": 887, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LEO%3A%20Latent%20Embedding%20Optimization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LEO%3A%20Latent%20Embedding%20Optimization%20Rusu%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=LEO%3A%20Latent%20Embedding%20Optimization&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 55, "section_title": "Meta-Learning & Few-Shot Learning", "source_note": "Latent space meta-learning", "title": "LEO: Latent Embedding Optimization", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Antoniou et al.", "id": 888, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=How%20to%20Train%20Your%20MAML&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=How%20to%20Train%20Your%20MAML%20Antoniou%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=How%20to%20Train%20Your%20MAML&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 55, "section_title": "Meta-Learning & Few-Shot Learning", "source_note": "MAML training improvements", "title": "How to Train Your MAML", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 889, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Few-Shot%20Learning%20via%20Saliency-Guided%20Hallucination&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Few-Shot%20Learning%20via%20Saliency-Guided%20Hallucination%20Zhang%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Few-Shot%20Learning%20via%20Saliency-Guided%20Hallucination&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 55, "section_title": "Meta-Learning & Few-Shot Learning", "source_note": "Data augmentation for few-shot", "title": "Few-Shot Learning via Saliency-Guided Hallucination", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Hu et al.", "id": 890, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=P%3EM%3EF%3A%20Pre-training%2C%20Meta-training%2C%20Fine-tuning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=P%3EM%3EF%3A%20Pre-training%2C%20Meta-training%2C%20Fine-tuning%20Hu%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=P%3EM%3EF%3A%20Pre-training%2C%20Meta-training%2C%20Fine-tuning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 55, "section_title": "Meta-Learning & Few-Shot Learning", "source_note": "Combining paradigms", "title": "P>M>F: Pre-training, Meta-training, Fine-tuning", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Garcez et al.", "id": 891, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Neural-Symbolic%20Computing%3A%20An%20Effective%20Methodology%20for%20Principled%20Integration&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Neural-Symbolic%20Computing%3A%20An%20Effective%20Methodology%20for%20Principled%20Integration%20Garcez%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Neural-Symbolic%20Computing%3A%20An%20Effective%20Methodology%20for%20Principled%20Integration&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 56, "section_title": "Neuro-Symbolic AI", "source_note": "Neuro-symbolic survey", "title": "Neural-Symbolic Computing: An Effective Methodology for Principled Integration", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Andreas et al.", "id": 892, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Neural%20Module%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Neural%20Module%20Networks%20Andreas%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Neural%20Module%20Networks&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 56, "section_title": "Neuro-Symbolic AI", "source_note": "Compositional neural reasoning", "title": "Neural Module Networks", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Rocktäschel & Riedel", "id": 893, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=End-to-End%20Differentiable%20Proving%20%28NTP%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=End-to-End%20Differentiable%20Proving%20%28NTP%29%20Rockt%C3%A4schel%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=End-to-End%20Differentiable%20Proving%20%28NTP%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 56, "section_title": "Neuro-Symbolic AI", "source_note": "Differentiable reasoning", "title": "End-to-End Differentiable Proving (NTP)", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Manhaeve et al.", "id": 894, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeepProbLog%3A%20Neural%20Probabilistic%20Logic%20Programming&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeepProbLog%3A%20Neural%20Probabilistic%20Logic%20Programming%20Manhaeve%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeepProbLog%3A%20Neural%20Probabilistic%20Logic%20Programming&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 56, "section_title": "Neuro-Symbolic AI", "source_note": "Neural + probabilistic logic", "title": "DeepProbLog: Neural Probabilistic Logic Programming", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Li et al.", "id": 895, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scallop%3A%20A%20Language%20for%20Neurosymbolic%20Programming&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scallop%3A%20A%20Language%20for%20Neurosymbolic%20Programming%20Li%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scallop%3A%20A%20Language%20for%20Neurosymbolic%20Programming&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 56, "section_title": "Neuro-Symbolic AI", "source_note": "Neurosymbolic programming", "title": "Scallop: A Language for Neurosymbolic Programming", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 896, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLMs%20and%20Symbolic%20Reasoning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLMs%20and%20Symbolic%20Reasoning%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLMs%20and%20Symbolic%20Reasoning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 56, "section_title": "Neuro-Symbolic AI", "source_note": "LLM + symbolic integration", "title": "LLMs and Symbolic Reasoning", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 897, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Program%20Synthesis%20with%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Program%20Synthesis%20with%20LLMs%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Program%20Synthesis%20with%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 56, "section_title": "Neuro-Symbolic AI", "source_note": "LLMs for program synthesis", "title": "Program Synthesis with LLMs", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Pan et al.", "id": 898, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Logic-LM%3A%20Empowering%20LLMs%20with%20Symbolic%20Solvers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Logic-LM%3A%20Empowering%20LLMs%20with%20Symbolic%20Solvers%20Pan%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Logic-LM%3A%20Empowering%20LLMs%20with%20Symbolic%20Solvers&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 56, "section_title": "Neuro-Symbolic AI", "source_note": "LLM + logic solvers", "title": "Logic-LM: Empowering LLMs with Symbolic Solvers", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 899, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Code-as-Reasoning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Code-as-Reasoning%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Code-as-Reasoning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 56, "section_title": "Neuro-Symbolic AI", "source_note": "Code generation as reasoning", "title": "Code-as-Reasoning", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Cheng et al.", "id": 900, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Binding%20Language%20Models%20in%20Symbolic%20Languages&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Binding%20Language%20Models%20in%20Symbolic%20Languages%20Cheng%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Binding%20Language%20Models%20in%20Symbolic%20Languages&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 56, "section_title": "Neuro-Symbolic AI", "source_note": "Binder framework", "title": "Binding Language Models in Symbolic Languages", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as policy or official document, not as a research paper.", "severity": "warning" } ], "authors": "EU", "id": 901, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=EU%20AI%20Act%20%28technical%20analysis%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=EU%20AI%20Act%20%28technical%20analysis%29%20EU%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=EU%20AI%20Act%20%28technical%20analysis%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 57, "section_title": "AI Governance & Policy", "source_note": "AI regulation framework", "title": "EU AI Act (technical analysis)", "work_type": "Policy or official document", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "White House", "id": 902, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Executive%20Order%20on%20AI%20Safety%20%28US%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Executive%20Order%20on%20AI%20Safety%20%28US%29%20White%20House%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Executive%20Order%20on%20AI%20Safety%20%28US%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 57, "section_title": "AI Governance & Policy", "source_note": "US AI safety policy", "title": "Executive Order on AI Safety (US)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 903, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Governing%20AI%3A%20A%20Blueprint%20for%20the%20Future&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Governing%20AI%3A%20A%20Blueprint%20for%20the%20Future%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Governing%20AI%3A%20A%20Blueprint%20for%20the%20Future&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 57, "section_title": "AI Governance & Policy", "source_note": "AI governance proposals", "title": "Governing AI: A Blueprint for the Future", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as technical or industry report, not as a research paper.", "severity": "warning" } ], "authors": "AI Safety Summit", "id": 904, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=International%20AI%20Safety%20Report&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=International%20AI%20Safety%20Report%20AI%20Safety%20Summit%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=International%20AI%20Safety%20Report&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 57, "section_title": "AI Governance & Policy", "source_note": "Global AI safety assessment", "title": "International AI Safety Report", "work_type": "Technical or industry report", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Bommasani et al.", "id": 905, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Foundation%20Model%20Transparency%20Index&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Foundation%20Model%20Transparency%20Index%20Bommasani%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Foundation%20Model%20Transparency%20Index&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 57, "section_title": "AI Governance & Policy", "source_note": "Model transparency scoring", "title": "Foundation Model Transparency Index", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 364 ], "severity": "warning" } ], "authors": "Wang et al.", "id": 906, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mixture%20of%20Agents%20%28MoA%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mixture%20of%20Agents%20%28MoA%29%20Wang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mixture%20of%20Agents%20%28MoA%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "LLM-based agent ensembles", "title": "Mixture of Agents (MoA)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Sardana & Frankle", "id": 907, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Inference%20Scaling%20Laws&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Inference%20Scaling%20Laws%20Sardana%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Inference%20Scaling%20Laws&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "Test-time compute scaling", "title": "Inference Scaling Laws", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Packer et al.; Various", "id": 908, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLM%20Operating%20Systems&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLM%20Operating%20Systems%20Packer%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLM%20Operating%20Systems&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "LLMs as OS kernels", "title": "LLM Operating Systems", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "OpenAI", "id": 909, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SWE-bench%20Verified&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SWE-bench%20Verified%20OpenAI%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=SWE-bench%20Verified&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "Verified agent coding", "title": "SWE-bench Verified", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Anthropic", "id": 910, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Anthropic%27s%20Responsible%20Scaling%20Policy%20%28RSP%29%20Update&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Anthropic%27s%20Responsible%20Scaling%20Policy%20%28RSP%29%20Update%20Anthropic%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Anthropic%27s%20Responsible%20Scaling%20Policy%20%28RSP%29%20Update&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "Updated safety policy", "title": "Anthropic's Responsible Scaling Policy (RSP) Update", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "unverified", "message": "The record itself attributes the work to 'Various (speculated/inferred)' and does not identify a publication. Not verified/citable until repaired.", "required_action": "Remove or replace with named, public process-reward-model papers.", "severity": "blocking" } ], "authors": "Various (speculated/inferred)", "id": 911, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Q%2A%20/%20Process%20Reward%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Q%2A%20/%20Process%20Reward%20Models%20Various%20%28speculated/inferred%29%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Q%2A%20/%20Process%20Reward%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "unverified_not_citable", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "Search + reward for reasoning", "title": "Q* / Process Reward Models", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "OpenAI", "id": 912, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=OpenAI%20o1%20and%20o1-pro&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=OpenAI%20o1%20and%20o1-pro%20OpenAI%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=OpenAI%20o1%20and%20o1-pro&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "Reasoning models", "title": "OpenAI o1 and o1-pro", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 854 ], "severity": "warning" } ], "authors": "Anthropic", "id": 913, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Claude%203.5%20Sonnet%20and%20Computer%20Use&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Claude%203.5%20Sonnet%20and%20Computer%20Use%20Anthropic%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Claude%203.5%20Sonnet%20and%20Computer%20Use&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "Frontier + computer use", "title": "Claude 3.5 Sonnet and Computer Use", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Google DeepMind", "id": 914, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Gemini%202.0%20Flash&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Gemini%202.0%20Flash%20Google%20DeepMind%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Gemini%202.0%20Flash&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "Agentic multimodal model", "title": "Gemini 2.0 Flash", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 279 ], "severity": "warning" } ], "authors": "DeepSeek", "id": 915, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=DeepSeek-R1&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=DeepSeek-R1%20DeepSeek%202025", "semantic_scholar": "https://www.semanticscholar.org/search?q=DeepSeek-R1&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "Open reasoning model", "title": "DeepSeek-R1", "work_type": "Research-paper candidate", "year": 2025, "year_display": "2025" }, { "audit_flags": [], "authors": "xAI", "id": 916, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Grok-2&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Grok-2%20xAI%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Grok-2&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "Real-time information model", "title": "Grok-2", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "NVIDIA", "id": 917, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Nemotron-4&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Nemotron-4%20NVIDIA%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Nemotron-4&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "Synthetic data generation", "title": "Nemotron-4", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Apple", "id": 918, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Apple%20Intelligence%20%28technical%20overview%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Apple%20Intelligence%20%28technical%20overview%29%20Apple%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Apple%20Intelligence%20%28technical%20overview%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "On-device LLM", "title": "Apple Intelligence (technical overview)", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Meta", "id": 919, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Llama%203.1%20405B&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Llama%203.1%20405B%20Meta%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Llama%203.1%20405B&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "Largest open-weight model", "title": "Llama 3.1 405B", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 920, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scaling%20Test-Time%20Compute%20%28Survey%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scaling%20Test-Time%20Compute%20%28Survey%29%20Various%202025", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scaling%20Test-Time%20Compute%20%28Survey%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 58, "section_title": "Emerging Frontiers (2024–2025)", "source_note": "Comprehensive test-time survey", "title": "Scaling Test-Time Compute (Survey)", "work_type": "Survey or review", "year": 2025, "year_display": "2025" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 773 ], "severity": "warning" } ], "authors": "Sennrich et al.", "id": 921, "links": { "canonical_url": "https://arxiv.org/abs/1508.07909", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1508.07909.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Byte%20Pair%20Encoding%20%28BPE%29%20for%20NMT&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Byte%20Pair%20Encoding%20%28BPE%29%20for%20NMT%20Sennrich%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=Byte%20Pair%20Encoding%20%28BPE%29%20for%20NMT&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1508.07909.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 59, "section_title": "Tokenization & Data Processing", "source_note": "Subword tokenization", "title": "Byte Pair Encoding (BPE) for NMT", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [], "authors": "Kudo & Richardson", "id": 922, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=SentencePiece%3A%20Unsupervised%20Text%20Tokenizer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=SentencePiece%3A%20Unsupervised%20Text%20Tokenizer%20Kudo%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=SentencePiece%3A%20Unsupervised%20Text%20Tokenizer&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 59, "section_title": "Tokenization & Data Processing", "source_note": "Language-agnostic tokenizer", "title": "SentencePiece: Unsupervised Text Tokenizer", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 923, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Tokenizer%20Choice%20Matters&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Tokenizer%20Choice%20Matters%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Tokenizer%20Choice%20Matters&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 59, "section_title": "Tokenization & Data Processing", "source_note": "Impact of tokenization on LLMs", "title": "Tokenizer Choice Matters", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Yu et al.", "id": 924, "links": { "canonical_url": "https://arxiv.org/abs/2305.07185", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2305.07185.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=MegaByte%3A%20Predicting%20Million-Byte%20Sequences&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=MegaByte%3A%20Predicting%20Million-Byte%20Sequences%20Yu%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=MegaByte%3A%20Predicting%20Million-Byte%20Sequences&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2305.07185.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 59, "section_title": "Tokenization & Data Processing", "source_note": "Byte-level modeling", "title": "MegaByte: Predicting Million-Byte Sequences", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Meta", "id": 925, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=BLT%3A%20Byte%20Latent%20Transformer&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=BLT%3A%20Byte%20Latent%20Transformer%20Meta%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=BLT%3A%20Byte%20Latent%20Transformer&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 59, "section_title": "Tokenization & Data Processing", "source_note": "Dynamic tokenization-free model", "title": "BLT: Byte Latent Transformer", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 926, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Tokenizer%20Landscape%20for%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Tokenizer%20Landscape%20for%20LLMs%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Tokenizer%20Landscape%20for%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 59, "section_title": "Tokenization & Data Processing", "source_note": "Tokenizer comparison", "title": "The Tokenizer Landscape for LLMs", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "OpenAI", "id": 927, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Tiktoken%20%28OpenAI%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Tiktoken%20%28OpenAI%29%20OpenAI%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Tiktoken%20%28OpenAI%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 59, "section_title": "Tokenization & Data Processing", "source_note": "Fast BPE tokenizer", "title": "Tiktoken (OpenAI)", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Lee et al.", "id": 928, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Data%20Deduplication%20for%20LLM%20Training&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Data%20Deduplication%20for%20LLM%20Training%20Lee%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Data%20Deduplication%20for%20LLM%20Training&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 59, "section_title": "Tokenization & Data Processing", "source_note": "Near-dedup for training data", "title": "Data Deduplication for LLM Training", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 929, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Quality%20Filtering%20for%20LLM%20Training%20Data&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Quality%20Filtering%20for%20LLM%20Training%20Data%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Quality%20Filtering%20for%20LLM%20Training%20Data&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 59, "section_title": "Tokenization & Data Processing", "source_note": "Data quality methods", "title": "Quality Filtering for LLM Training Data", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Soldaini et al.", "id": 930, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Dolma%3A%20An%20Open%20Corpus%20of%20Trillion%20Tokens&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Dolma%3A%20An%20Open%20Corpus%20of%20Trillion%20Tokens%20Soldaini%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Dolma%3A%20An%20Open%20Corpus%20of%20Trillion%20Tokens&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 59, "section_title": "Tokenization & Data Processing", "source_note": "Open training corpus", "title": "Dolma: An Open Corpus of Trillion Tokens", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zhao et al.", "id": 931, "links": { "canonical_url": "https://arxiv.org/abs/2303.18223", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2303.18223.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Survey%20of%20Large%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Survey%20of%20Large%20Language%20Models%20Zhao%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Survey%20of%20Large%20Language%20Models&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2303.18223.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Comprehensive LLM survey", "title": "A Survey of Large Language Models", "work_type": "Survey or review", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Yang et al.", "id": 932, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Harnessing%20the%20Power%20of%20LLMs%20in%20Practice&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Harnessing%20the%20Power%20of%20LLMs%20in%20Practice%20Yang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Harnessing%20the%20Power%20of%20LLMs%20in%20Practice&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Practical LLM guide", "title": "Harnessing the Power of LLMs in Practice", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Huang et al.", "id": 933, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Survey%20on%20Hallucination%20in%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Survey%20on%20Hallucination%20in%20LLMs%20Huang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Survey%20on%20Hallucination%20in%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Hallucination survey", "title": "A Survey on Hallucination in LLMs", "work_type": "Survey or review", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 934, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Siren%27s%20Song%20in%20the%20AI%20Ocean%3A%20A%20Survey%20on%20Hallucination&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Siren%27s%20Song%20in%20the%20AI%20Ocean%3A%20A%20Survey%20on%20Hallucination%20Zhang%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Siren%27s%20Song%20in%20the%20AI%20Ocean%3A%20A%20Survey%20on%20Hallucination&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Hallucination taxonomy", "title": "Siren's Song in the AI Ocean: A Survey on Hallucination", "work_type": "Survey or review", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Yin et al.", "id": 935, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Survey%20on%20Multimodal%20Large%20Language%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Survey%20on%20Multimodal%20Large%20Language%20Models%20Yin%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Survey%20on%20Multimodal%20Large%20Language%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "MLLM survey", "title": "A Survey on Multimodal Large Language Models", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Chang et al.", "id": 936, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Survey%20on%20Evaluation%20of%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Survey%20on%20Evaluation%20of%20LLMs%20Chang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Survey%20on%20Evaluation%20of%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "LLM evaluation survey", "title": "A Survey on Evaluation of LLMs", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Han et al.", "id": 937, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Comprehensive%20Survey%20on%20Vector%20Database&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Comprehensive%20Survey%20on%20Vector%20Database%20Han%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Comprehensive%20Survey%20on%20Vector%20Database&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Vector DB survey", "title": "A Comprehensive Survey on Vector Database", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zhao et al.", "id": 938, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Retrieval-Augmented%20Generation%20for%20AI-Generated%20Content%3A%20A%20Survey&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Retrieval-Augmented%20Generation%20for%20AI-Generated%20Content%3A%20A%20Survey%20Zhao%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Retrieval-Augmented%20Generation%20for%20AI-Generated%20Content%3A%20A%20Survey&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "RAG survey", "title": "Retrieval-Augmented Generation for AI-Generated Content: A Survey", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Qin et al.", "id": 939, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Tool%20Learning%20with%20Foundation%20Models&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Tool%20Learning%20with%20Foundation%20Models%20Qin%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Tool%20Learning%20with%20Foundation%20Models&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Tool use survey", "title": "Tool Learning with Foundation Models", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 940, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLM%20Agents%3A%20A%20Survey%20of%20Applications&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLM%20Agents%3A%20A%20Survey%20of%20Applications%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLM%20Agents%3A%20A%20Survey%20of%20Applications&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Agent applications survey", "title": "LLM Agents: A Survey of Applications", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Masterman et al.", "id": 941, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Landscape%20of%20Emerging%20AI%20Agent%20Architectures&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Landscape%20of%20Emerging%20AI%20Agent%20Architectures%20Masterman%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Landscape%20of%20Emerging%20AI%20Agent%20Architectures&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Agent architecture survey", "title": "The Landscape of Emerging AI Agent Architectures", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Tao et al.", "id": 942, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=A%20Survey%20on%20Self-Evolution%20of%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=A%20Survey%20on%20Self-Evolution%20of%20LLMs%20Tao%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=A%20Survey%20on%20Self-Evolution%20of%20LLMs&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Self-improvement survey", "title": "A Survey on Self-Evolution of LLMs", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 943, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=From%20RAG%20to%20Rich%3A%20Retrieval-Augmented%20Generation%20Survey&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=From%20RAG%20to%20Rich%3A%20Retrieval-Augmented%20Generation%20Survey%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=From%20RAG%20to%20Rich%3A%20Retrieval-Augmented%20Generation%20Survey&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Advanced RAG survey", "title": "From RAG to Rich: Retrieval-Augmented Generation Survey", "work_type": "Survey or review", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Kapoor et al.", "id": 944, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AI%20Agents%20That%20Matter&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AI%20Agents%20That%20Matter%20Kapoor%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=AI%20Agents%20That%20Matter&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Agent evaluation framework", "title": "AI Agents That Matter", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various", "id": 945, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Position%3A%20What%20Can%20LLMs%20Do%20for%20ME%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Position%3A%20What%20Can%20LLMs%20Do%20for%20ME%3F%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Position%3A%20What%20Can%20LLMs%20Do%20for%20ME%3F&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Practical applications", "title": "Position: What Can LLMs Do for ME?", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as technical or industry report, not as a research paper.", "severity": "warning" } ], "authors": "Benaich & Hogarth", "id": 946, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20State%20of%20AI%20Report%202024&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20State%20of%20AI%20Report%202024%20Benaich%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20State%20of%20AI%20Report%202024&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Annual AI overview", "title": "The State of AI Report 2024", "work_type": "Technical or industry report", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as technical or industry report, not as a research paper.", "severity": "warning" } ], "authors": "Stanford", "id": 947, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Stanford%20AI%20Index%20Report%202024&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Stanford%20AI%20Index%20Report%202024%20Stanford%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Stanford%20AI%20Index%20Report%202024&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "AI progress metrics", "title": "Stanford AI Index Report 2024", "work_type": "Technical or industry report", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Guo et al.", "id": 948, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Attention%20Mechanisms%20in%20Computer%20Vision%3A%20A%20Survey&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Attention%20Mechanisms%20in%20Computer%20Vision%3A%20A%20Survey%20Guo%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Attention%20Mechanisms%20in%20Computer%20Vision%3A%20A%20Survey&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Attention in vision survey", "title": "Attention Mechanisms in Computer Vision: A Survey", "work_type": "Survey or review", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Khan et al.", "id": 949, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Vision%20Transformers%3A%20A%20Survey&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Vision%20Transformers%3A%20A%20Survey%20Khan%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Vision%20Transformers%3A%20A%20Survey&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "ViT survey", "title": "Vision Transformers: A Survey", "work_type": "Survey or review", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Tay et al.", "id": 950, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Efficient%20Transformers%3A%20A%20Survey&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Efficient%20Transformers%3A%20A%20Survey%20Tay%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=Efficient%20Transformers%3A%20A%20Survey&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 60, "section_title": "Surveys, Tutorials & Meta-Papers", "source_note": "Efficient attention survey", "title": "Efficient Transformers: A Survey", "work_type": "Survey or review", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Halevy, Norvig, Pereira", "id": 951, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Unreasonable%20Effectiveness%20of%20Data&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Unreasonable%20Effectiveness%20of%20Data%20Halevy%202009", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Unreasonable%20Effectiveness%20of%20Data&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Data over algorithms", "title": "The Unreasonable Effectiveness of Data", "work_type": "Research-paper candidate", "year": 2009, "year_display": "2009" }, { "audit_flags": [], "authors": "Santurkar et al.", "id": 952, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Batch%20Normalization%20%28revisited%20for%20theory%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Batch%20Normalization%20%28revisited%20for%20theory%29%20Santurkar%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Batch%20Normalization%20%28revisited%20for%20theory%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Why BN works", "title": "Batch Normalization (revisited for theory)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 953, "links": { "canonical_url": "https://arxiv.org/abs/1710.09412", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1710.09412.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Mixup%3A%20Beyond%20Empirical%20Risk%20Minimization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Mixup%3A%20Beyond%20Empirical%20Risk%20Minimization%20Zhang%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Mixup%3A%20Beyond%20Empirical%20Risk%20Minimization&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1710.09412.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Data augmentation via interpolation", "title": "Mixup: Beyond Empirical Risk Minimization", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Yun et al.", "id": 954, "links": { "canonical_url": "https://arxiv.org/abs/1905.04899", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1905.04899.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=CutMix%3A%20Regularization%20Strategy%20to%20Train%20Strong%20Classifiers&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=CutMix%3A%20Regularization%20Strategy%20to%20Train%20Strong%20Classifiers%20Yun%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=CutMix%3A%20Regularization%20Strategy%20to%20Train%20Strong%20Classifiers&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1905.04899.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Cut-and-paste augmentation", "title": "CutMix: Regularization Strategy to Train Strong Classifiers", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Cubuk et al.", "id": 955, "links": { "canonical_url": "https://arxiv.org/abs/1909.13719", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1909.13719.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RandAugment%3A%20Practical%20Automated%20Data%20Augmentation&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RandAugment%3A%20Practical%20Automated%20Data%20Augmentation%20Cubuk%202020", "semantic_scholar": "https://www.semanticscholar.org/search?q=RandAugment%3A%20Practical%20Automated%20Data%20Augmentation&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1909.13719.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Simplified augmentation", "title": "RandAugment: Practical Automated Data Augmentation", "work_type": "Research-paper candidate", "year": 2020, "year_display": "2020" }, { "audit_flags": [], "authors": "Cubuk et al.", "id": 956, "links": { "canonical_url": "https://arxiv.org/abs/1805.09501", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1805.09501.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=AutoAugment%3A%20Learning%20Augmentation%20Strategies%20from%20Data&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=AutoAugment%3A%20Learning%20Augmentation%20Strategies%20from%20Data%20Cubuk%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=AutoAugment%3A%20Learning%20Augmentation%20Strategies%20from%20Data&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1805.09501.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Learned augmentation", "title": "AutoAugment: Learning Augmentation Strategies from Data", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 958 ], "severity": "warning" } ], "authors": "Müller et al.", "id": 957, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Label%20Smoothing%20Revisited&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Label%20Smoothing%20Revisited%20M%C3%BCller%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Label%20Smoothing%20Revisited&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Label smoothing analysis", "title": "Label Smoothing Revisited", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 957 ], "severity": "warning" } ], "authors": "Müller et al.", "id": 958, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=When%20Does%20Label%20Smoothing%20Help%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=When%20Does%20Label%20Smoothing%20Help%3F%20M%C3%BCller%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=When%20Does%20Label%20Smoothing%20Help%3F&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Label smoothing theory", "title": "When Does Label Smoothing Help?", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Ramachandran et al.", "id": 959, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Swish%3A%20A%20Self-Gated%20Activation%20Function&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Swish%3A%20A%20Self-Gated%20Activation%20Function%20Ramachandran%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Swish%3A%20A%20Self-Gated%20Activation%20Function&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Swish/SiLU activation", "title": "Swish: A Self-Gated Activation Function", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Hendrycks & Gimpel", "id": 960, "links": { "canonical_url": "https://arxiv.org/abs/1606.08415", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1606.08415.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=GELU%3A%20Gaussian%20Error%20Linear%20Units&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=GELU%3A%20Gaussian%20Error%20Linear%20Units%20Hendrycks%202016", "semantic_scholar": "https://www.semanticscholar.org/search?q=GELU%3A%20Gaussian%20Error%20Linear%20Units&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1606.08415.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "GELU activation", "title": "GELU: Gaussian Error Linear Units", "work_type": "Research-paper candidate", "year": 2016, "year_display": "2016" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 85 ], "severity": "warning" } ], "authors": "Hu et al.", "id": 961, "links": { "canonical_url": "https://arxiv.org/abs/1709.01507", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1709.01507.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Squeeze-and-Excitation%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Squeeze-and-Excitation%20Networks%20Hu%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Squeeze-and-Excitation%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1709.01507.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Channel attention mechanism", "title": "Squeeze-and-Excitation Networks", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Woo et al.", "id": 962, "links": { "canonical_url": "https://arxiv.org/abs/1807.06521", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1807.06521.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=CBAM%3A%20Convolutional%20Block%20Attention%20Module&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=CBAM%3A%20Convolutional%20Block%20Attention%20Module%20Woo%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=CBAM%3A%20Convolutional%20Block%20Attention%20Module&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1807.06521.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Spatial + channel attention", "title": "CBAM: Convolutional Block Attention Module", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Wang et al.", "id": 963, "links": { "canonical_url": "https://arxiv.org/abs/1711.07971", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1711.07971.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Non-local%20Neural%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Non-local%20Neural%20Networks%20Wang%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=Non-local%20Neural%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1711.07971.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Self-attention for vision", "title": "Non-local Neural Networks", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Dai et al.", "id": 964, "links": { "canonical_url": "https://arxiv.org/abs/1703.06211", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1703.06211.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Deformable%20Convolutional%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Deformable%20Convolutional%20Networks%20Dai%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Deformable%20Convolutional%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1703.06211.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Deformable convolutions", "title": "Deformable Convolutional Networks", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Sabour, Frosst, Hinton", "id": 965, "links": { "canonical_url": "https://arxiv.org/abs/1710.09829", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1710.09829.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Dynamic%20Routing%20Between%20Capsules&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Dynamic%20Routing%20Between%20Capsules%20Sabour%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Dynamic%20Routing%20Between%20Capsules&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1710.09829.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Capsule networks", "title": "Dynamic Routing Between Capsules", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 116 ], "severity": "warning" } ], "authors": "Bai et al.", "id": 966, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=An%20Empirical%20Evaluation%20of%20Generic%20Convolutional%20and%20Recurrent%20Networks%20%28TCN%20paper%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=An%20Empirical%20Evaluation%20of%20Generic%20Convolutional%20and%20Recurrent%20Networks%20%28TCN%20paper%29%20Bai%202018", "semantic_scholar": "https://www.semanticscholar.org/search?q=An%20Empirical%20Evaluation%20of%20Generic%20Convolutional%20and%20Recurrent%20Networks%20%28TCN%20paper%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "TCN vs RNN comparison", "title": "An Empirical Evaluation of Generic Convolutional and Recurrent Networks (TCN paper)", "work_type": "Research-paper candidate", "year": 2018, "year_display": "2018" }, { "audit_flags": [], "authors": "Qiao et al.", "id": 967, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Weight%20Standardization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Weight%20Standardization%20Qiao%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Weight%20Standardization&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Micro-batch normalization", "title": "Weight Standardization", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Zhang et al.", "id": 968, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Fixup%20Initialization%3A%20Residual%20Learning%20Without%20Normalization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Fixup%20Initialization%3A%20Residual%20Learning%20Without%20Normalization%20Zhang%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Fixup%20Initialization%3A%20Residual%20Learning%20Without%20Normalization&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Training without BN", "title": "Fixup Initialization: Residual Learning Without Normalization", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Zaheer et al.", "id": 969, "links": { "canonical_url": "https://arxiv.org/abs/1703.06114", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1703.06114.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Deep%20Sets&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Deep%20Sets%20Zaheer%202017", "semantic_scholar": "https://www.semanticscholar.org/search?q=Deep%20Sets&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1703.06114.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Permutation-invariant architectures", "title": "Deep Sets", "work_type": "Research-paper candidate", "year": 2017, "year_display": "2017" }, { "audit_flags": [], "authors": "Bello et al.", "id": 970, "links": { "canonical_url": "https://arxiv.org/abs/1904.09925", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/1904.09925.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Attention%20Augmented%20Convolutional%20Networks&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Attention%20Augmented%20Convolutional%20Networks%20Bello%202019", "semantic_scholar": "https://www.semanticscholar.org/search?q=Attention%20Augmented%20Convolutional%20Networks&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/1904.09925.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Self-attention in CNNs", "title": "Attention Augmented Convolutional Networks", "work_type": "Research-paper candidate", "year": 2019, "year_display": "2019" }, { "audit_flags": [], "authors": "Raghu et al.", "id": 971, "links": { "canonical_url": "https://arxiv.org/abs/2108.08810", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2108.08810.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Do%20Vision%20Transformers%20See%20Like%20Convolutional%20Neural%20Networks%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Do%20Vision%20Transformers%20See%20Like%20Convolutional%20Neural%20Networks%3F%20Raghu%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Do%20Vision%20Transformers%20See%20Like%20Convolutional%20Neural%20Networks%3F&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2108.08810.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "ViT vs CNN representation analysis", "title": "Do Vision Transformers See Like Convolutional Neural Networks?", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Park & Kim", "id": 972, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=What%20Do%20Vision%20Transformers%20Learn%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=What%20Do%20Vision%20Transformers%20Learn%3F%20Park%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=What%20Do%20Vision%20Transformers%20Learn%3F&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "ViT feature analysis", "title": "What Do Vision Transformers Learn?", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [], "authors": "Riquelme et al.", "id": 973, "links": { "canonical_url": "https://arxiv.org/abs/2106.05974", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2106.05974.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Scaling%20Vision%20with%20Sparse%20MoE&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Scaling%20Vision%20with%20Sparse%20MoE%20Riquelme%202021", "semantic_scholar": "https://www.semanticscholar.org/search?q=Scaling%20Vision%20with%20Sparse%20MoE&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2106.05974.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "MoE for vision", "title": "Scaling Vision with Sparse MoE", "work_type": "Research-paper candidate", "year": 2021, "year_display": "2021" }, { "audit_flags": [], "authors": "Bolya et al.", "id": 974, "links": { "canonical_url": "https://arxiv.org/abs/2210.09461", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2210.09461.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Token%20Merging%3A%20Your%20ViT%20but%20Faster&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Token%20Merging%3A%20Your%20ViT%20but%20Faster%20Bolya%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Token%20Merging%3A%20Your%20ViT%20but%20Faster&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2210.09461.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "Token efficiency in ViTs", "title": "Token Merging: Your ViT but Faster", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Lee-Thorp et al.", "id": 975, "links": { "canonical_url": "https://arxiv.org/abs/2105.03824", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2105.03824.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=FNet%3A%20Mixing%20Tokens%20with%20Fourier%20Transforms&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=FNet%3A%20Mixing%20Tokens%20with%20Fourier%20Transforms%20Lee-Thorp%202022", "semantic_scholar": "https://www.semanticscholar.org/search?q=FNet%3A%20Mixing%20Tokens%20with%20Fourier%20Transforms&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2105.03824.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 61, "section_title": "Additional Foundational & Influential Papers", "source_note": "FFT replaces attention", "title": "FNet: Mixing Tokens with Fourier Transforms", "work_type": "Research-paper candidate", "year": 2022, "year_display": "2022" }, { "audit_flags": [ { "code": "non_paper_type", "message": "Classified for discovery as product or topic analysis, not as a research paper.", "severity": "warning" }, { "code": "unverified", "message": "A product-analysis label without a canonical publication title. Not verified/citable until repaired.", "required_action": "Classify and cite a named system card, technical report or product source.", "severity": "blocking" } ], "authors": "OpenAI", "id": 976, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=OpenAI%20o3%20%28analysis%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=OpenAI%20o3%20%28analysis%29%20OpenAI%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=OpenAI%20o3%20%28analysis%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "unverified_not_citable", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Advanced reasoning model", "title": "OpenAI o3 (analysis)", "work_type": "Product or topic analysis", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Anthropic", "id": 977, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Claude%204%20/%20Opus%204%20%28model%20card%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Claude%204%20/%20Opus%204%20%28model%20card%29%20Anthropic%202025", "semantic_scholar": "https://www.semanticscholar.org/search?q=Claude%204%20/%20Opus%204%20%28model%20card%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Frontier model", "title": "Claude 4 / Opus 4 (model card)", "work_type": "Research-paper candidate", "year": 2025, "year_display": "2025" }, { "audit_flags": [], "authors": "Google DeepMind", "id": 978, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Gemini%202.0%20Pro&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Gemini%202.0%20Pro%20Google%20DeepMind%202025", "semantic_scholar": "https://www.semanticscholar.org/search?q=Gemini%202.0%20Pro&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Advanced multimodal", "title": "Gemini 2.0 Pro", "work_type": "Research-paper candidate", "year": 2025, "year_display": "2025" }, { "audit_flags": [], "authors": "Meta", "id": 979, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Llama%204&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Llama%204%20Meta%202025", "semantic_scholar": "https://www.semanticscholar.org/search?q=Llama%204&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Next-gen open model", "title": "Llama 4", "work_type": "Research-paper candidate", "year": 2025, "year_display": "2025" }, { "audit_flags": [], "authors": "Gloeckle et al.", "id": 980, "links": { "canonical_url": "https://arxiv.org/abs/2404.19737", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2404.19737.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Multi-Token%20Prediction&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Multi-Token%20Prediction%20Gloeckle%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Multi-Token%20Prediction&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2404.19737.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Predicting multiple tokens", "title": "Multi-Token Prediction", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" }, { "code": "unverified", "message": "Exact-title search did not identify a matching publication; authors are listed as Various. Not verified/citable until repaired.", "required_action": "Replace with specific comparative architecture papers.", "severity": "blocking" } ], "authors": "Various", "id": 981, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Native%20Multi-Modality%20vs%20Late%20Fusion&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Native%20Multi-Modality%20vs%20Late%20Fusion%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Native%20Multi-Modality%20vs%20Late%20Fusion&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "unverified_not_citable", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Architecture comparison", "title": "Native Multi-Modality vs Late Fusion", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" }, { "code": "unverified", "message": "A method-family label with authors listed as Various rather than a unique work. Not verified/citable until repaired.", "required_action": "Replace with named RLVR papers and canonical identifiers.", "severity": "blocking" } ], "authors": "Various", "id": 982, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=RLVR%3A%20Reinforcement%20Learning%20with%20Verifiable%20Rewards&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=RLVR%3A%20Reinforcement%20Learning%20with%20Verifiable%20Rewards%20Various%202025", "semantic_scholar": "https://www.semanticscholar.org/search?q=RLVR%3A%20Reinforcement%20Learning%20with%20Verifiable%20Rewards&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "unverified_not_citable", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Verifiable reward RL", "title": "RLVR: Reinforcement Learning with Verifiable Rewards", "work_type": "Research-paper candidate", "year": 2025, "year_display": "2025" }, { "audit_flags": [ { "code": "unverified", "message": "Exact-title search did not identify an Anthropic publication with this title. Not verified/citable until repaired.", "required_action": "Replace with the canonical Constitutional AI paper or a specifically named later source.", "severity": "blocking" } ], "authors": "Anthropic", "id": 983, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Constitutional%20AI%202.0%20Concepts&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Constitutional%20AI%202.0%20Concepts%20Anthropic%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Constitutional%20AI%202.0%20Concepts&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "unverified_not_citable", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Advanced alignment research", "title": "Constitutional AI 2.0 Concepts", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" }, { "code": "unverified", "message": "A topic label with authors listed as Various rather than a unique work. Not verified/citable until repaired.", "required_action": "Replace with specific post-training scaling publications.", "severity": "blocking" } ], "authors": "Various", "id": 984, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Post-Training%20Scaling&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Post-Training%20Scaling%20Various%202025", "semantic_scholar": "https://www.semanticscholar.org/search?q=Post-Training%20Scaling&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "unverified_not_citable", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Scaling after pretraining", "title": "Post-Training Scaling", "work_type": "Research-paper candidate", "year": 2025, "year_display": "2025" }, { "audit_flags": [], "authors": "Burns et al.", "id": 985, "links": { "canonical_url": "https://arxiv.org/abs/2312.09390", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2312.09390.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Weak-to-Strong%20Generalization&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Weak-to-Strong%20Generalization%20Burns%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Weak-to-Strong%20Generalization&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2312.09390.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Superalignment research", "title": "Weak-to-Strong Generalization", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Huh et al.", "id": 986, "links": { "canonical_url": "https://arxiv.org/abs/2405.07987", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2405.07987.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Platonic%20Representation%20Hypothesis&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Platonic%20Representation%20Hypothesis%20Huh%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Platonic%20Representation%20Hypothesis&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2405.07987.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Convergent representations", "title": "The Platonic Representation Hypothesis", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "duplicate", "message": "The same or a materially identical work appears elsewhere in the curriculum.", "related_ids": [ 667 ], "severity": "warning" } ], "authors": "Zou et al.", "id": 987, "links": { "canonical_url": "https://arxiv.org/abs/2310.01405", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2310.01405.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Representation%20Engineering&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Representation%20Engineering%20Zou%202023", "semantic_scholar": "https://www.semanticscholar.org/search?q=Representation%20Engineering&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2310.01405.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Control via representations", "title": "Representation Engineering", "work_type": "Research-paper candidate", "year": 2023, "year_display": "2023" }, { "audit_flags": [], "authors": "Yang et al.", "id": 988, "links": { "canonical_url": "https://arxiv.org/abs/2309.03409", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2309.03409.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLMs%20as%20Optimizers%20%28OPRO%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLMs%20as%20Optimizers%20%28OPRO%29%20Yang%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLMs%20as%20Optimizers%20%28OPRO%29&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2309.03409.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Prompt optimization with LLMs", "title": "LLMs as Optimizers (OPRO)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Si et al.", "id": 989, "links": { "canonical_url": "https://arxiv.org/abs/2409.04109", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2409.04109.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Can%20LLMs%20Generate%20Novel%20Research%20Ideas%3F&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Can%20LLMs%20Generate%20Novel%20Research%20Ideas%3F%20Si%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Can%20LLMs%20Generate%20Novel%20Research%20Ideas%3F&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2409.04109.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "AI for scientific ideation", "title": "Can LLMs Generate Novel Research Ideas?", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Lu et al.", "id": 990, "links": { "canonical_url": "https://arxiv.org/abs/2408.06292", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2408.06292.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20AI%20Scientist%3A%20Towards%20Fully%20Automated%20Open-Ended%20Scientific%20Discovery&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20AI%20Scientist%3A%20Towards%20Fully%20Automated%20Open-Ended%20Scientific%20Discovery%20Lu%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20AI%20Scientist%3A%20Towards%20Fully%20Automated%20Open-Ended%20Scientific%20Discovery&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2408.06292.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Autonomous research agent", "title": "The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Zhao et al.", "id": 991, "links": { "canonical_url": "https://arxiv.org/abs/2505.03335", "corrected_by_audit": false, "direct_url": "https://arxiv.org/pdf/2505.03335.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Absolute%20Zero%3A%20Reinforced%20Self-Play%20Reasoning%20with%20Zero%20Data&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Absolute%20Zero%3A%20Reinforced%20Self-Play%20Reasoning%20with%20Zero%20Data%20Zhao%202025", "semantic_scholar": "https://www.semanticscholar.org/search?q=Absolute%20Zero%3A%20Reinforced%20Self-Play%20Reasoning%20with%20Zero%20Data&sort=relevance" }, "supplied_direct_url": "https://arxiv.org/pdf/2505.03335.pdf" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Self-play from nothing", "title": "Absolute Zero: Reinforced Self-Play Reasoning with Zero Data", "work_type": "Research-paper candidate", "year": 2025, "year_display": "2025" }, { "audit_flags": [], "authors": "Zaharia et al.", "id": 992, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Agentic%20Workflows%20and%20Compound%20AI%20Systems&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Agentic%20Workflows%20and%20Compound%20AI%20Systems%20Zaharia%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Agentic%20Workflows%20and%20Compound%20AI%20Systems&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Compound AI systems vision", "title": "Agentic Workflows and Compound AI Systems", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Matei Zaharia", "id": 993, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=From%20Models%20to%20Compound%20AI%20Systems&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=From%20Models%20to%20Compound%20AI%20Systems%20Matei%20Zaharia%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=From%20Models%20to%20Compound%20AI%20Systems&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Systems > models", "title": "From Models to Compound AI Systems", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author_corrected", "message": "The source used a vague attribution; named authorship is supplied by the audit.", "severity": "resolved" }, { "code": "metadata_corrected", "message": "Canonical title, authorship and arXiv identity were supplied by the audit.", "severity": "resolved" } ], "authors": "Chuanneng Sun, Songjun Huang, Dario Pompili", "id": 994, "links": { "canonical_url": "https://arxiv.org/abs/2405.11106", "corrected_by_audit": true, "direct_url": "https://arxiv.org/pdf/2405.11106.pdf", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=LLM-Based%20Multi-Agent%20Reinforcement%20Learning&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=LLM-Based%20Multi-Agent%20Reinforcement%20Learning%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=LLM-Based%20Multi-Agent%20Reinforcement%20Learning&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "audit_corrected_discovery", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "MARL with LLMs", "title": "LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" }, { "code": "unverified", "message": "A generic topic label with authors listed as Various. Not verified/citable until repaired.", "required_action": "Replace with uniquely identifiable self-improvement papers.", "severity": "blocking" } ], "authors": "Various", "id": 995, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Self-Improving%20AI%20Systems&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Self-Improving%20AI%20Systems%20Various%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Self-Improving%20AI%20Systems&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "unverified_not_citable", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Recursive self-improvement", "title": "Self-Improving AI Systems", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" } ], "authors": "Various govts", "id": 996, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Frontier%20AI%20Safety%20Commitments%20%28Seoul%20Declaration%29&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Frontier%20AI%20Safety%20Commitments%20%28Seoul%20Declaration%29%20Various%20govts%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Frontier%20AI%20Safety%20Commitments%20%28Seoul%20Declaration%29&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "needs_repair", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "International safety commitments", "title": "Frontier AI Safety Commitments (Seoul Declaration)", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Aschenbrenner", "id": 997, "links": { "canonical_url": "https://situational-awareness.ai/", "corrected_by_audit": false, "direct_url": "https://situational-awareness.ai/", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Situational%20Awareness&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Situational%20Awareness%20Aschenbrenner%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Situational%20Awareness&sort=relevance" }, "supplied_direct_url": "https://situational-awareness.ai/" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "AGI timeline analysis", "title": "Situational Awareness", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Yan et al.", "id": 998, "links": { "canonical_url": "https://www.oreilly.com/radar/what-we-learned-from-a-year-of-building-with-llms/", "corrected_by_audit": false, "direct_url": "https://www.oreilly.com/radar/what-we-learned-from-a-year-of-building-with-llms/", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=What%20We%20Learned%20from%20a%20Year%20of%20Building%20with%20LLMs&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=What%20We%20Learned%20from%20a%20Year%20of%20Building%20with%20LLMs%20Yan%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=What%20We%20Learned%20from%20a%20Year%20of%20Building%20with%20LLMs&sort=relevance" }, "supplied_direct_url": "https://www.oreilly.com/radar/what-we-learned-from-a-year-of-building-with-llms/" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Practical LLM lessons", "title": "What We Learned from a Year of Building with LLMs", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [], "authors": "Anthropic", "id": 999, "links": { "canonical_url": "https://www.anthropic.com/research/building-effective-agents", "corrected_by_audit": false, "direct_url": "https://www.anthropic.com/research/building-effective-agents", "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=Building%20Effective%20Agents&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=Building%20Effective%20Agents%20Anthropic%202024", "semantic_scholar": "https://www.semanticscholar.org/search?q=Building%20Effective%20Agents&sort=relevance" }, "supplied_direct_url": "https://www.anthropic.com/research/building-effective-agents" }, "publication_identity_status": "discovery_only_not_independently_verified", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Agent design patterns", "title": "Building Effective Agents", "work_type": "Research-paper candidate", "year": 2024, "year_display": "2024" }, { "audit_flags": [ { "code": "vague_author", "message": "Named authorship is unresolved.", "severity": "blocking" }, { "code": "unverified", "message": "Exact-title search did not identify a matching publication; authors are listed as Various. Not verified/citable until repaired.", "required_action": "Remove until a canonical source is supplied.", "severity": "blocking" } ], "authors": "Various", "id": 1000, "links": { "canonical_url": null, "corrected_by_audit": false, "direct_url": null, "fallbacks": { "arxiv_search": "https://arxiv.org/search/?query=The%20Next%20Wave%3A%20AI%20Systems%20that%20Reason%2C%20Act%2C%20and%20Learn&searchtype=all", "google_scholar": "https://scholar.google.com/scholar?q=The%20Next%20Wave%3A%20AI%20Systems%20that%20Reason%2C%20Act%2C%20and%20Learn%20Various%202025", "semantic_scholar": "https://www.semanticscholar.org/search?q=The%20Next%20Wave%3A%20AI%20Systems%20that%20Reason%2C%20Act%2C%20and%20Learn&sort=relevance" }, "supplied_direct_url": null }, "publication_identity_status": "unverified_not_citable", "section_id": 62, "section_title": "Final Frontier Papers (976–1000)", "source_note": "Future of agentic AI", "title": "The Next Wave: AI Systems that Reason, Act, and Learn", "work_type": "Research-paper candidate", "year": 2025, "year_display": "2025" } ], "schema_version": "1.0", "sections": [ { "id": 1, "record_ids": [ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 ], "title": "Mathematical & Statistical Foundations" }, { "id": 2, "record_ids": [ 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35 ], "title": "Classical Machine Learning Foundations" }, { "id": 3, "record_ids": [ 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55 ], "title": "Neural Network Foundations" }, { "id": 4, "record_ids": [ 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75 ], "title": "Optimization & Training Techniques" }, { "id": 5, "record_ids": [ 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100 ], "title": "Convolutional Neural Networks & Computer Vision" }, { "id": 6, "record_ids": [ 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120 ], "title": "Recurrent Neural Networks & Sequence Modeling" }, { "id": 7, "record_ids": [ 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140 ], "title": "Generative Models" }, { "id": 8, "record_ids": [ 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160 ], "title": "Attention Mechanisms & Transformers" }, { "id": 9, "record_ids": [ 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185 ], "title": "Pre-trained Language Models" }, { "id": 10, "record_ids": [ 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 215 ], "title": "Large Language Models (LLMs)" }, { "id": 11, "record_ids": [ 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227, 228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245 ], "title": "LLM Training & Alignment" }, { "id": 12, "record_ids": [ 246, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260 ], "title": "Prompt Engineering & In-Context Learning" }, { "id": 13, "record_ids": [ 261, 262, 263, 264, 265, 266, 267, 268, 269, 270, 271, 272, 273, 274, 275, 276, 277, 278, 279, 280, 281, 282, 283, 284, 285 ], "title": "Reasoning & Chain-of-Thought" }, { "id": 14, "record_ids": [ 286, 287, 288, 289, 290, 291, 292, 293, 294, 295, 296, 297, 298, 299, 300, 301, 302, 303, 304, 305 ], "title": "Retrieval-Augmented Generation (RAG)" }, { "id": 15, "record_ids": [ 306, 307, 308, 309, 310, 311, 312, 313, 314, 315, 316, 317, 318, 319, 320 ], "title": "Tool Use & Function Calling" }, { "id": 16, "record_ids": [ 321, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340 ], "title": "AI Agents — Foundations" }, { "id": 17, "record_ids": [ 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355 ], "title": "AI Agents — Planning & Reasoning" }, { "id": 18, "record_ids": [ 356, 357, 358, 359, 360, 361, 362, 363, 364, 365, 366, 367, 368, 369, 370 ], "title": "Multi-Agent Systems" }, { "id": 19, "record_ids": [ 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 382, 383, 384, 385, 386, 387, 388, 389, 390 ], "title": "Code Generation & Software Engineering Agents" }, { "id": 20, "record_ids": [ 391, 392, 393, 394, 395, 396, 397, 398, 399, 400 ], "title": "Reinforcement Learning Foundations" }, { "id": 21, "record_ids": [ 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413, 414, 415, 416, 417, 418, 419, 420 ], "title": "Deep Reinforcement Learning" }, { "id": 22, "record_ids": [ 421, 422, 423, 424, 425, 426, 427, 428, 429, 430, 431, 432, 433, 434, 435 ], "title": "Multimodal AI" }, { "id": 23, "record_ids": [ 436, 437, 438, 439, 440, 441, 442, 443, 444, 445, 446, 447, 448, 449, 450, 451, 452, 453, 454, 455 ], "title": "Vision-Language Models" }, { "id": 24, "record_ids": [ 456, 457, 458, 459, 460, 461, 462, 463, 464, 465, 466, 467, 468, 469, 470, 471, 472, 473, 474, 475 ], "title": "Speech & Audio Models" }, { "id": 25, "record_ids": [ 476, 477, 478, 479, 480, 481, 482, 483, 484, 485, 486, 487, 488, 489, 490, 491, 492, 493, 494, 495, 496, 497, 498, 499, 500 ], "title": "Diffusion Models & Image Generation" }, { "id": 26, "record_ids": [ 501, 502, 503, 504, 505, 506, 507, 508, 509, 510, 511, 512, 513, 514, 515 ], "title": "Video Generation & Understanding" }, { "id": 27, "record_ids": [ 516, 517, 518, 519, 520, 521, 522, 523, 524, 525, 526, 527, 528, 529, 530 ], "title": "Graph Neural Networks" }, { "id": 28, "record_ids": [ 531, 532, 533, 534, 535, 536, 537, 538, 539, 540, 541, 542, 543, 544, 545, 546, 547, 548, 549, 550 ], "title": "Efficient AI & Model Compression" }, { "id": 29, "record_ids": [ 551, 552, 553, 554, 555, 556, 557, 558, 559, 560 ], "title": "Mixture of Experts" }, { "id": 30, "record_ids": [ 561, 562, 563, 564, 565, 566, 567, 568, 569, 570 ], "title": "Knowledge Distillation & Transfer Learning" }, { "id": 31, "record_ids": [ 571, 572, 573, 574, 575, 576, 577, 578, 579, 580 ], "title": "Continual & Lifelong Learning" }, { "id": 32, "record_ids": [ 581, 582, 583, 584, 585, 586, 587, 588, 589, 590, 591, 592, 593, 594, 595 ], "title": "Self-Supervised & Contrastive Learning" }, { "id": 33, "record_ids": [ 596, 597, 598, 599, 600, 601, 602, 603, 604, 605 ], "title": "Federated & Privacy-Preserving AI" }, { "id": 34, "record_ids": [ 606, 607, 608, 609, 610, 611, 612, 613, 614, 615, 616, 617, 618, 619, 620, 621, 622, 623, 624, 625, 626, 627, 628, 629, 630 ], "title": "Evaluation & Benchmarks" }, { "id": 35, "record_ids": [ 631, 632, 633, 634, 635, 636, 637, 638, 639, 640, 641, 642, 643, 644, 645, 646, 647, 648, 649, 650, 651, 652, 653, 654, 655 ], "title": "AI Safety, Ethics & Alignment" }, { "id": 36, "record_ids": [ 656, 657, 658, 659, 660, 661, 662, 663, 664, 665, 666, 667, 668, 669, 670, 671, 672, 673, 674, 675 ], "title": "Interpretability & Explainability" }, { "id": 37, "record_ids": [ 676, 677, 678, 679, 680, 681, 682, 683, 684, 685, 686, 687, 688, 689, 690 ], "title": "Robotics & Embodied AI" }, { "id": 38, "record_ids": [ 691, 692, 693, 694, 695, 696, 697, 698, 699, 700 ], "title": "World Models & Simulation" }, { "id": 39, "record_ids": [ 701, 702, 703, 704, 705, 706, 707, 708, 709, 710, 711, 712, 713, 714, 715, 716, 717, 718, 719, 720 ], "title": "Scientific AI & Domain Applications" }, { "id": 40, "record_ids": [ 721, 722, 723, 724, 725, 726, 727, 728, 729, 730, 731, 732, 733, 734, 735 ], "title": "Scaling Laws & Emergent Abilities" }, { "id": 41, "record_ids": [ 736, 737, 738, 739, 740, 741, 742, 743, 744, 745, 746, 747, 748, 749, 750 ], "title": "Architecture Innovations & Beyond Transformers" }, { "id": 42, "record_ids": [ 751, 752, 753, 754, 755, 756, 757, 758, 759, 760 ], "title": "AGI Theory & Frontier Research" }, { "id": 43, "record_ids": [ 761, 762, 763, 764, 765, 766, 767, 768, 769, 770 ], "title": "Knowledge Graphs & Structured Knowledge" }, { "id": 44, "record_ids": [ 771, 772, 773, 774, 775, 776, 777, 778, 779, 780 ], "title": "Natural Language Understanding & Generation" }, { "id": 45, "record_ids": [ 781, 782, 783, 784, 785, 786, 787, 788, 789, 790 ], "title": "Synthetic Data & Data Generation" }, { "id": 46, "record_ids": [ 791, 792, 793, 794, 795, 796, 797, 798, 799, 800 ], "title": "Long Context & Memory Systems" }, { "id": 47, "record_ids": [ 801, 802, 803, 804, 805, 806, 807, 808, 809, 810 ], "title": "Structured & Constrained Generation" }, { "id": 48, "record_ids": [ 811, 812, 813, 814, 815, 816, 817, 818, 819, 820 ], "title": "AI for Finance (BFSI-relevant)" }, { "id": 49, "record_ids": [ 821, 822, 823, 824, 825, 826, 827, 828, 829, 830 ], "title": "Document AI & Information Extraction" }, { "id": 50, "record_ids": [ 831, 832, 833, 834, 835, 836, 837, 838, 839, 840 ], "title": "Autonomous Driving & Navigation" }, { "id": 51, "record_ids": [ 841, 842, 843, 844, 845, 846, 847, 848, 849, 850 ], "title": "AI Infrastructure & MLOps" }, { "id": 52, "record_ids": [ 851, 852, 853, 854, 855, 856, 857, 858, 859, 860 ], "title": "Agentic Web & Computer Use" }, { "id": 53, "record_ids": [ 861, 862, 863, 864, 865, 866, 867, 868, 869, 870 ], "title": "3D Generation & Neural Rendering" }, { "id": 54, "record_ids": [ 871, 872, 873, 874, 875, 876, 877, 878, 879, 880 ], "title": "Adversarial ML & Robustness" }, { "id": 55, "record_ids": [ 881, 882, 883, 884, 885, 886, 887, 888, 889, 890 ], "title": "Meta-Learning & Few-Shot Learning" }, { "id": 56, "record_ids": [ 891, 892, 893, 894, 895, 896, 897, 898, 899, 900 ], "title": "Neuro-Symbolic AI" }, { "id": 57, "record_ids": [ 901, 902, 903, 904, 905 ], "title": "AI Governance & Policy" }, { "id": 58, "record_ids": [ 906, 907, 908, 909, 910, 911, 912, 913, 914, 915, 916, 917, 918, 919, 920 ], "title": "Emerging Frontiers (2024–2025)" }, { "id": 59, "record_ids": [ 921, 922, 923, 924, 925, 926, 927, 928, 929, 930 ], "title": "Tokenization & Data Processing" }, { "id": 60, "record_ids": [ 931, 932, 933, 934, 935, 936, 937, 938, 939, 940, 941, 942, 943, 944, 945, 946, 947, 948, 949, 950 ], "title": "Surveys, Tutorials & Meta-Papers" }, { "id": 61, "record_ids": [ 951, 952, 953, 954, 955, 956, 957, 958, 959, 960, 961, 962, 963, 964, 965, 966, 967, 968, 969, 970, 971, 972, 973, 974, 975 ], "title": "Additional Foundational & Influential Papers" }, { "id": 62, "record_ids": [ 976, 977, 978, 979, 980, 981, 982, 983, 984, 985, 986, 987, 988, 989, 990, 991, 992, 993, 994, 995, 996, 997, 998, 999, 1000 ], "title": "Final Frontier Papers (976–1000)" } ], "status": "discovery_curriculum_not_verified_bibliography", "title": "Top 1,000 AI Papers — Audited Discovery Edition" }