{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/cosine-annealing/papers/34","list_of":"/method/cosine-annealing","method":"Cosine Annealing","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":34,"pages_in_order":40,"rows_per_page":100,"rows":[3301,3400],"of":3965,"counts":{"archive_papers_tagged":3965,"with_a_code_link":1734,"where_syntology_ran_a_sample":627,"not_listed_spam_title":0,"listed":3965,"listed_where_code_ran":627,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":513,"every_run_a_failure_of_syntologys_instrument":114,"listed_with_a_run_with_no_instrument_failure":513,"listed_every_run_a_failure_of_syntologys_instrument":114,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/cosine-annealing","prev":"/method/cosine-annealing/papers/33","next":"/method/cosine-annealing/papers/35","papers":[{"paper":"/paper/when-classifying-grammatical-role-bert-doesn-1","slug":"when-classifying-grammatical-role-bert-doesn-1","title":"When classifying grammatical role, BERT doesn't care about word order... except when it matters","date":"2022-03-11","arxiv_id":"2203.06204","n_code_links":1,"syntology":null},{"paper":"/paper/autonomous-mosquito-habitat-detection-using","slug":"autonomous-mosquito-habitat-detection-using","title":"Autonomous Mosquito Habitat Detection Using Satellite Imagery and Convolutional Neural Networks for Disease Risk Mapping","date":"2022-03-09","arxiv_id":"2203.04463","n_code_links":1,"syntology":null},{"paper":"/paper/coarse-to-fine-sparse-transformer-for","slug":"coarse-to-fine-sparse-transformer-for","title":"Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction","date":"2022-03-09","arxiv_id":"2203.04845","n_code_links":1,"syntology":{"ran":13,"of":16,"n_ran_checked":9,"n_instrument":4,"unverified":3,"pointer_only":0,"phrase":"13 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["caiyuanhao1998/MST"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":8,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/nlx-gpt-a-model-for-natural-language","slug":"nlx-gpt-a-model-for-natural-language","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","date":"2022-03-09","arxiv_id":"2203.05081","n_code_links":1,"syntology":null},{"paper":"/paper/tensor-programs-v-tuning-large-neural","slug":"tensor-programs-v-tuning-large-neural","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","date":"2022-03-07","arxiv_id":"2203.03466","n_code_links":7,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/mup"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/litetransformersearch-training-free-on-device","slug":"litetransformersearch-training-free-on-device","title":"LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models","date":"2022-03-04","arxiv_id":"2203.02094","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/archai"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/training-language-models-to-follow","slug":"training-language-models-to-follow","title":"Training language models to follow instructions with human feedback","date":"2022-03-04","arxiv_id":"2203.02155","n_code_links":11,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openai/following-instructions-human-feedback"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/parameter-efficient-mixture-of-experts","slug":"parameter-efficient-mixture-of-experts","title":"Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models","date":"2022-03-02","arxiv_id":"2203.01104","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rucaibox/mpo","rucaibox/mpoe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/exploring-and-adapting-chinese-gpt-to-pinyin-1","slug":"exploring-and-adapting-chinese-gpt-to-pinyin-1","title":"Exploring and Adapting Chinese GPT to Pinyin Input Method","date":"2022-03-01","arxiv_id":"2203.00249","n_code_links":1,"syntology":null},{"paper":"/paper/a-systematic-evaluation-of-large-language","slug":"a-systematic-evaluation-of-large-language","title":"A Systematic Evaluation of Large Language Models of Code","date":"2022-02-26","arxiv_id":"2202.13169","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eleutherai/gpt-neox","vhellendoorn/code-lms"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/rethinking-the-role-of-demonstrations-what","slug":"rethinking-the-role-of-demonstrations-what","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","date":"2022-02-25","arxiv_id":"2202.12837","n_code_links":2,"syntology":null},{"paper":"/paper/from-natural-language-to-simulations-applying","slug":"from-natural-language-to-simulations-applying","title":"From Natural Language to Simulations: Applying GPT-3 Codex to Automate Simulation Modeling of Logistics Systems","date":"2022-02-24","arxiv_id":"2202.12107","n_code_links":1,"syntology":null},{"paper":null,"slug":"consistent-dropout-for-policy-gradient","title":"Consistent Dropout for Policy Gradient Reinforcement Learning","date":"2022-02-23","arxiv_id":"2202.11818","n_code_links":0,"syntology":null},{"paper":null,"slug":"mirror-yolo-an-attention-based-instance","title":"Mirror-Yolo: A Novel Attention Focus, Instance Segmentation and Mirror Detection Model","date":"2022-02-17","arxiv_id":"2202.08498","n_code_links":0,"syntology":null},{"paper":"/paper/sgpt-gpt-sentence-embeddings-for-semantic","slug":"sgpt-gpt-sentence-embeddings-for-semantic","title":"SGPT: GPT Sentence Embeddings for Semantic Search","date":"2022-02-17","arxiv_id":"2202.08904","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["muennighoff/sgpt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"defending-against-reconstruction-attacks-with","title":"Defending against Reconstruction Attacks with Rényi Differential Privacy","date":"2022-02-15","arxiv_id":"2202.07623","n_code_links":0,"syntology":null},{"paper":"/paper/maximizing-communication-efficiency-for-large","slug":"maximizing-communication-efficiency-for-large","title":"Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam","date":"2022-02-12","arxiv_id":"2202.06009","n_code_links":1,"syntology":null},{"paper":"/paper/vehicle-and-license-plate-recognition-with","slug":"vehicle-and-license-plate-recognition-with","title":"Vehicle and License Plate Recognition with Novel Dataset for Toll Collection","date":"2022-02-11","arxiv_id":"2202.05631","n_code_links":3,"syntology":null},{"paper":"/paper/semantic-features-of-object-concepts","slug":"semantic-features-of-object-concepts","title":"Semantic features of object concepts generated with GPT-3","date":"2022-02-08","arxiv_id":"2202.03753","n_code_links":1,"syntology":null},{"paper":"/paper/what-are-the-best-systems-new-perspectives-on","slug":"what-are-the-best-systems-new-perspectives-on","title":"What are the best systems? New perspectives on NLP Benchmarking","date":"2022-02-08","arxiv_id":"2202.03799","n_code_links":1,"syntology":null},{"paper":"/paper/cedille-a-large-autoregressive-french","slug":"cedille-a-large-autoregressive-french","title":"Cedille: A large autoregressive French language model","date":"2022-02-07","arxiv_id":"2202.03371","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrated-multiscale-domain-adaptive-yolo","title":"Integrated Multiscale Domain Adaptive YOLO","date":"2022-02-07","arxiv_id":"2202.03527","n_code_links":0,"syntology":null},{"paper":null,"slug":"ethics-rules-of-engagement-and-ai-neural","title":"Ethics, Rules of Engagement, and AI: Neural Narrative Mapping Using Large Transformer Language Models","date":"2022-02-05","arxiv_id":"2202.02647","n_code_links":0,"syntology":null},{"paper":null,"slug":"influence-of-different-factors-on-survival-of","title":"Influence of different factors on survival of patients with colorectal cancer","date":"2022-02-05","arxiv_id":"2202.03425","n_code_links":0,"syntology":null},{"paper":"/paper/a-benchmark-corpus-for-the-detection-of","slug":"a-benchmark-corpus-for-the-detection-of","title":"A Benchmark Corpus for the Detection of Automatically Generated Text in Academic Publications","date":"2022-02-04","arxiv_id":"2202.02013","n_code_links":1,"syntology":null},{"paper":"/paper/co-training-improves-prompt-based-learning","slug":"co-training-improves-prompt-based-learning","title":"Co-training Improves Prompt-based Learning for Large Language Models","date":"2022-02-02","arxiv_id":"2202.00828","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["clinicalml/cotrain-prompting"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/l3cube-mahacorpus-and-mahabert-marathi","slug":"l3cube-mahacorpus-and-mahabert-marathi","title":"L3Cube-MahaCorpus and MahaBERT: Marathi Monolingual Corpus, Marathi BERT Language Models, and Resources","date":"2022-02-02","arxiv_id":"2202.01159","n_code_links":1,"syntology":null},{"paper":null,"slug":"vc-gpt-visual-conditioned-gpt-for-end-to-end","title":"A Frustratingly Simple Approach for End-to-End Image Captioning","date":"2022-01-30","arxiv_id":"2201.12723","n_code_links":0,"syntology":null},{"paper":"/paper/chain-of-thought-prompting-elicits-reasoning","slug":"chain-of-thought-prompting-elicits-reasoning","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","date":"2022-01-28","arxiv_id":"2201.11903","n_code_links":19,"syntology":{"ran":5,"of":7,"n_ran_checked":4,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"self-paced-learning-to-improve-text-row","title":"Self-paced learning to improve text row detection in historical documents with missing labels","date":"2022-01-28","arxiv_id":"2201.12216","n_code_links":0,"syntology":null},{"paper":"/paper/summarizing-differences-between-text","slug":"summarizing-differences-between-text","title":"Describing Differences between Text Distributions with Natural Language","date":"2022-01-28","arxiv_id":"2201.12323","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ruiqi-zhong/describedistributionaldifferences"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dnnfuser-generative-pre-trained-transformer","title":"DNNFuser: Generative Pre-Trained Transformer as a Generalized Mapper for Layer Fusion in DNN Accelerators","date":"2022-01-26","arxiv_id":"2201.11218","n_code_links":0,"syntology":null},{"paper":"/paper/synchromesh-reliable-code-generation-from-pre-1","slug":"synchromesh-reliable-code-generation-from-pre-1","title":"Synchromesh: Reliable code generation from pre-trained language models","date":"2022-01-26","arxiv_id":"2201.11227","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"pre-trained-language-transformers-are","title":"Pre-Trained Language Transformers are Universal Image Classifiers","date":"2022-01-25","arxiv_id":"2201.10182","n_code_links":0,"syntology":null},{"paper":null,"slug":"whose-language-counts-as-high-quality","title":"Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection","date":"2022-01-25","arxiv_id":"2201.10474","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthetic-books","title":"Synthetic Books","date":"2022-01-24","arxiv_id":"2201.09518","n_code_links":0,"syntology":null},{"paper":"/paper/black-box-prompt-learning-for-pre-trained","slug":"black-box-prompt-learning-for-pre-trained","title":"Black-box Prompt Learning for Pre-trained Language Models","date":"2022-01-21","arxiv_id":"2201.08531","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shizhediao/black-box-prompt-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/coauthor-designing-a-human-ai-collaborative","slug":"coauthor-designing-a-human-ai-collaborative","title":"CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities","date":"2022-01-18","arxiv_id":"2201.06796","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-study-of-pre-trained-language-models-for","title":"A Study of Pre-trained Language Models for Analogy Generation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"auto-regressive-text-generation-with-pre","title":"Auto-regressive Text Generation with Pre-Trained Language Models: An Empirical Study on Question-type Short Text Generation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-hierarchical-domain-adaptation-for-1","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"elastic-weight-consolidation-for-reduction-of","title":"Elastic Weight Consolidation for Reduction of Catastrophic Forgetting in GPT-2","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"few-shot-semantic-parsing-with-language-1","title":"Few-Shot Semantic Parsing with Language Models Trained On Code","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-transformers-are-more-efficient-1","title":"Hierarchical Transformers Are More Efficient Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"jointly-reinforced-user-simulator-and-task","title":"Jointly Reinforced User Simulator and Task-oriented Dialog System with Simplified Generative Architecture","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/memory-assisted-prompt-editing-to-improve-gpt","slug":"memory-assisted-prompt-editing-to-improve-gpt","title":"Memory-assisted prompt editing to improve GPT-3 after deployment","date":"2022-01-16","arxiv_id":"2201.06009","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["madaan/memprompt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"penguins-dont-fly-reasoning-about-generics","title":"Penguins Don’t Fly: Reasoning about Generics through Instantiations and Exceptions","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"polling-latent-opinions-a-method-for","title":"Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"provably-confidential-language-modelling","title":"Provably Confidential Language Modelling","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"re2g-retrieve-rerank-generate","title":"Re2G: Retrieve, Rerank, Generate","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"reframing-human-ai-collaboration-for-1","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"representation-learning-for-conversational-1","title":"Representation Learning for Conversational Data using Discourse Mutual Information Maximization","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/unifiedskg-unifying-and-multi-tasking","slug":"unifiedskg-unifying-and-multi-tasking","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","date":"2022-01-16","arxiv_id":"2201.05966","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":1,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["hkunlp/unifiedskg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/wanli-worker-and-ai-collaboration-for-natural","slug":"wanli-worker-and-ai-collaboration-for-natural","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","date":"2022-01-16","arxiv_id":"2201.05955","n_code_links":1,"syntology":null},{"paper":null,"slug":"when-a-sentence-does-not-introduce-a","title":"When a sentence does not introduce a discourse entity, Transformer-based models still often refer to it","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"why-does-surprisal-from-smaller-gpt-2-models","title":"Why Does Surprisal From Smaller GPT-2 Models Provide Better Fit to Human Reading Times?","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"commonsenseqa-2-0-exposing-the-limits-of-ai","title":"CommonsenseQA 2.0: Exposing the Limits of AI through Gamification","date":"2022-01-14","arxiv_id":"2201.05320","n_code_links":0,"syntology":null},{"paper":"/paper/assemble-foundation-models-for-automatic-code","slug":"assemble-foundation-models-for-automatic-code","title":"Assemble Foundation Models for Automatic Code Summarization","date":"2022-01-13","arxiv_id":"2201.05222","n_code_links":1,"syntology":null},{"paper":"/paper/black-box-tuning-for-language-model-as-a","slug":"black-box-tuning-for-language-model-as-a","title":"Black-Box Tuning for Language-Model-as-a-Service","date":"2022-01-10","arxiv_id":"2201.03514","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["txsun1997/black-box-tuning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/image-based-automatic-dial-meter-reading-in","slug":"image-based-automatic-dial-meter-reading-in","title":"Image-based Automatic Dial Meter Reading in Unconstrained Scenarios","date":"2022-01-08","arxiv_id":"2201.02850","n_code_links":1,"syntology":null},{"paper":null,"slug":"computational-lens-on-cognition-study-of","title":"Imagined versus Remembered Stories: Quantifying Differences in Narrative Flow","date":"2022-01-07","arxiv_id":"2201.02662","n_code_links":0,"syntology":null},{"paper":"/paper/flow-guided-sparse-transformer-for-video","slug":"flow-guided-sparse-transformer-for-video","title":"Flow-Guided Sparse Transformer for Video Deblurring","date":"2022-01-06","arxiv_id":"2201.01893","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["linjing7/VR-Baseline"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"submix-practical-private-prediction-for-large-1","title":"Submix: Practical Private Prediction for Large-Scale Language Models","date":"2022-01-04","arxiv_id":"2201.00971","n_code_links":0,"syntology":null},{"paper":"/paper/a-neural-network-solves-and-generates","slug":"a-neural-network-solves-and-generates","title":"A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level","date":"2021-12-31","arxiv_id":"2112.15594","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["idrori/mathq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/dense-to-sparse-gate-for-mixture-of-experts-1","slug":"dense-to-sparse-gate-for-mixture-of-experts-1","title":"EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate","date":"2021-12-29","arxiv_id":"2112.14397","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["codecaution/evomoe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ernie-3-0-titan-exploring-larger-scale","slug":"ernie-3-0-titan-exploring-larger-scale","title":"ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","date":"2021-12-23","arxiv_id":"2112.12731","n_code_links":3,"syntology":null},{"paper":"/paper/few-shot-learning-with-multilingual-language","slug":"few-shot-learning-with-multilingual-language","title":"Few-shot Learning with Multilingual Language Models","date":"2021-12-20","arxiv_id":"2112.10668","n_code_links":2,"syntology":null},{"paper":null,"slug":"analysis-and-mitigation-of-dataset-artifacts","title":"Analysis and Mitigation of Dataset Artifacts in OpenAI GPT-3","date":"2021-12-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/webgpt-browser-assisted-question-answering","slug":"webgpt-browser-assisted-question-answering","title":"WebGPT: Browser-assisted question-answering with human feedback","date":"2021-12-17","arxiv_id":"2112.09332","n_code_links":2,"syntology":null},{"paper":"/paper/call-for-customized-conversation-customized","slug":"call-for-customized-conversation-customized","title":"Call for Customized Conversation: Customized Conversation Grounding Persona and Knowledge","date":"2021-12-16","arxiv_id":"2112.08619","n_code_links":3,"syntology":null},{"paper":"/paper/efficient-hierarchical-domain-adaptation-for","slug":"efficient-hierarchical-domain-adaptation-for","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","date":"2021-12-16","arxiv_id":"2112.08786","n_code_links":1,"syntology":null},{"paper":null,"slug":"few-shot-semantic-parsing-with-language","title":"Few-Shot Semantic Parsing with Language Models Trained On Code","date":"2021-12-16","arxiv_id":"2112.08696","n_code_links":0,"syntology":null},{"paper":null,"slug":"reconsidering-the-past-optimizing-hidden-1","title":"Reconsidering the Past: Optimizing Hidden States in Language Models","date":"2021-12-16","arxiv_id":"2112.08653","n_code_links":0,"syntology":null},{"paper":"/paper/reframing-human-ai-collaboration-for","slug":"reframing-human-ai-collaboration-for","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","date":"2021-12-16","arxiv_id":"2112.08674","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/few_shot_explanations"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/embracing-single-stride-3d-object-detector","slug":"embracing-single-stride-3d-object-detector","title":"Embracing Single Stride 3D Object Detector with Sparse Transformer","date":"2021-12-13","arxiv_id":"2112.06375","n_code_links":2,"syntology":null},{"paper":"/paper/glam-efficient-scaling-of-language-models","slug":"glam-efficient-scaling-of-language-models","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","date":"2021-12-13","arxiv_id":"2112.06905","n_code_links":0,"syntology":null},{"paper":"/paper/wechsel-effective-initialization-of-subword-1","slug":"wechsel-effective-initialization-of-subword-1","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","date":"2021-12-13","arxiv_id":"2112.06598","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cpjku/wechsel"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improving-logical-level-natural-language","title":"Improving Logical-Level Natural Language Generation with Topic-Conditioned Data Augmentation and Logical Form Generation","date":"2021-12-12","arxiv_id":"2112.06240","n_code_links":0,"syntology":null},{"paper":"/paper/improving-language-models-by-retrieving-from","slug":"improving-language-models-by-retrieving-from","title":"Improving language models by retrieving from trillions of tokens","date":"2021-12-08","arxiv_id":"2112.04426","n_code_links":2,"syntology":{"ran":16,"of":23,"n_ran_checked":14,"n_instrument":2,"unverified":7,"pointer_only":3,"phrase":"16 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 3 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","official":null}},{"paper":null,"slug":"gaudi-conversational-interactions-with-deep","title":"Gaudí: Conversational Interactions with Deep Representations to Generate Image Collections","date":"2021-12-05","arxiv_id":"2112.04404","n_code_links":0,"syntology":null},{"paper":null,"slug":"representation-learning-for-conversational","title":"Representation Learning for Conversational Data using Discourse Mutual Information Maximization","date":"2021-12-04","arxiv_id":"2112.05787","n_code_links":0,"syntology":null},{"paper":null,"slug":"probabilistic-approach-for-road-users","title":"Probabilistic Approach for Road-Users Detection","date":"2021-12-02","arxiv_id":"2112.01360","n_code_links":0,"syntology":null},{"paper":null,"slug":"searching-for-efficient-transformers-for","title":"Searching for Efficient Transformers for Language Modeling","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/think-big-teach-small-do-language-models","slug":"think-big-teach-small-do-language-models","title":"Think Big, Teach Small: Do Language Models Distil Occam’s Razor?","date":"2021-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/tuning-large-neural-networks-via-zero-shot","slug":"tuning-large-neural-networks-via-zero-shot","title":"Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","date":"2021-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-transformers-on-word","title":"A Comparative Study of Transformers on Word Sense Disambiguation","date":"2021-11-30","arxiv_id":"2111.15417","n_code_links":0,"syntology":null},{"paper":null,"slug":"chemical-identification-and-indexing-in","title":"Chemical Identification and Indexing in PubMed Articles via BERT and Text-to-Text Approaches","date":"2021-11-30","arxiv_id":"2111.15622","n_code_links":0,"syntology":null},{"paper":"/paper/pixelated-butterfly-simple-and-efficient-1","slug":"pixelated-butterfly-simple-and-efficient-1","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","date":"2021-11-30","arxiv_id":"2112.00029","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":5,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["HazyResearch/pixelfly"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["found_in_text"]}}},{"paper":null,"slug":"context-matters-in-semantically-controlled","title":"Context Matters in Semantically Controlled Language Generation for Task-oriented Dialogue Systems","date":"2021-11-28","arxiv_id":"2111.14119","n_code_links":0,"syntology":null},{"paper":"/paper/amortized-prompt-lightweight-fine-tuning-for","slug":"amortized-prompt-lightweight-fine-tuning-for","title":"Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains","date":"2021-11-25","arxiv_id":"2111.12853","n_code_links":1,"syntology":{"ran":12,"of":17,"n_ran_checked":8,"n_instrument":4,"unverified":5,"pointer_only":17,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["shogi880/DPLCLIP"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transformer-based-korean-pretrained-language","title":"Transformer-based Korean Pretrained Language Models: A Survey on Three Years of Progress","date":"2021-11-25","arxiv_id":"2112.03014","n_code_links":0,"syntology":null},{"paper":"/paper/clipcap-clip-prefix-for-image-captioning","slug":"clipcap-clip-prefix-for-image-captioning","title":"ClipCap: CLIP Prefix for Image Captioning","date":"2021-11-18","arxiv_id":"2111.09734","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rmokady/clip_prefix_caption"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"how-much-do-language-models-copy-from-their","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","date":"2021-11-18","arxiv_id":"2111.09509","n_code_links":0,"syntology":null},{"paper":null,"slug":"guiding-generative-language-models-for-data","title":"Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification","date":"2021-11-17","arxiv_id":"2111.09064","n_code_links":0,"syntology":null},{"paper":null,"slug":"active-dialogue-simulation-in-conversational","title":"Active Dialogue Simulation in Conversational Systems","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"an-information-theoretic-measurement-of","title":"An Information Theoretic Measurement of Topical Relevance in Learner Essays","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/building-chinese-biomedical-language-models-1","slug":"building-chinese-biomedical-language-models-1","title":"Building Chinese Biomedical Language Models via Multi-Level Text Discrimination","date":"2021-11-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"create-a-benchmark-for-chinese-short-video","title":"CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"data-augmentation-for-intent-classification","title":"Data Augmentation for Intent Classification with Generic Large Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"eliteplm-an-empirical-study-on-general","title":"ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"56c2dfb44c7c09e61644d2189d3c11fced2e03c1da321464537cfd6d9a418e4a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}