{"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/layer-normalization/papers/172","list_of":"/method/layer-normalization","method":"Layer Normalization","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":172,"pages_in_order":250,"rows_per_page":100,"rows":[17101,17200],"of":24980,"counts":{"archive_papers_tagged":24980,"with_a_code_link":11273,"where_syntology_ran_a_sample":3471,"not_listed_spam_title":0,"listed":24980,"listed_where_code_ran":3471,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2923,"every_run_a_failure_of_syntologys_instrument":548,"listed_with_a_run_with_no_instrument_failure":2923,"listed_every_run_a_failure_of_syntologys_instrument":548,"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/layer-normalization","prev":"/method/layer-normalization/papers/171","next":"/method/layer-normalization/papers/173","papers":[{"paper":"/paper/multimodal-masked-autoencoders-learn","slug":"multimodal-masked-autoencoders-learn","title":"Multimodal Masked Autoencoders Learn Transferable Representations","date":"2022-05-27","arxiv_id":"2205.14204","n_code_links":3,"syntology":{"ran":12,"of":12,"n_ran_checked":9,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["young-geng/m3ae_public"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/nearest-neighbor-zero-shot-inference","slug":"nearest-neighbor-zero-shot-inference","title":"kNN-Prompt: Nearest Neighbor Zero-Shot Inference","date":"2022-05-27","arxiv_id":"2205.13792","n_code_links":1,"syntology":null},{"paper":null,"slug":"nlu-for-game-based-learning-in-real-initial","title":"NLU for Game-based Learning in Real: Initial Evaluations","date":"2022-05-27","arxiv_id":"2205.13754","n_code_links":0,"syntology":null},{"paper":"/paper/patching-leaks-in-the-charformer-for-1","slug":"patching-leaks-in-the-charformer-for-1","title":"Patching Leaks in the Charformer for Efficient Character-Level Generation","date":"2022-05-27","arxiv_id":"2205.14086","n_code_links":1,"syntology":null},{"paper":"/paper/probabilistic-transformer-modelling","slug":"probabilistic-transformer-modelling","title":"Probabilistic Transformer: Modelling Ambiguities and Distributions for RNA Folding and Molecule Design","date":"2022-05-27","arxiv_id":"2205.13927","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-from-an-optimization-perspective","slug":"transformers-from-an-optimization-perspective","title":"Transformers from an Optimization Perspective","date":"2022-05-27","arxiv_id":"2205.13891","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["fftyyy/transformers-from-optimization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/turjuman-a-public-toolkit-for-neural-arabic","slug":"turjuman-a-public-toolkit-for-neural-arabic","title":"TURJUMAN: A Public Toolkit for Neural Arabic Machine Translation","date":"2022-05-27","arxiv_id":"2206.03933","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-long-programming-languages-with","slug":"understanding-long-programming-languages-with","title":"Understanding Long Programming Languages with Structure-Aware Sparse Attention","date":"2022-05-27","arxiv_id":"2205.13730","n_code_links":1,"syntology":null},{"paper":"/paper/what-dense-graph-do-you-need-for-self","slug":"what-dense-graph-do-you-need-for-self","title":"What Dense Graph Do You Need for Self-Attention?","date":"2022-05-27","arxiv_id":"2205.14014","n_code_links":1,"syntology":null},{"paper":"/paper/adaptformer-adapting-vision-transformers-for","slug":"adaptformer-adapting-vision-transformers-for","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","date":"2022-05-26","arxiv_id":"2205.13535","n_code_links":2,"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":["ShoufaChen/AdaptFormer"],"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":"/paper/are-transformers-effective-for-time-series","slug":"are-transformers-effective-for-time-series","title":"Are Transformers Effective for Time Series Forecasting?","date":"2022-05-26","arxiv_id":"2205.13504","n_code_links":10,"syntology":{"ran":13,"of":19,"n_ran_checked":13,"n_instrument":0,"unverified":6,"pointer_only":13,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["WenjieDu/PyPOTS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","named_in_paper"]}}},{"paper":null,"slug":"benchmarking-of-deep-learning-models-on-2d","title":"Benchmarking of Deep Learning models on 2D Laminar Flow behind Cylinder","date":"2022-05-26","arxiv_id":"2205.13485","n_code_links":0,"syntology":null},{"paper":null,"slug":"clinical-dialogue-transcription-error","title":"Clinical Dialogue Transcription Error Correction using Seq2Seq Models","date":"2022-05-26","arxiv_id":"2205.13572","n_code_links":0,"syntology":null},{"paper":null,"slug":"dt-sv-a-transformer-based-time-domain","title":"DT-SV: A Transformer-based Time-domain Approach for Speaker Verification","date":"2022-05-26","arxiv_id":"2205.13249","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-u-transformer-with-boundary-aware","slug":"efficient-u-transformer-with-boundary-aware","title":"Do we really need temporal convolutions in action segmentation?","date":"2022-05-26","arxiv_id":"2205.13425","n_code_links":1,"syntology":null},{"paper":null,"slug":"embed-to-control-partially-observed-systems","title":"Embed to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency","date":"2022-05-26","arxiv_id":"2205.13476","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-split-bert-for-heterogeneous-text","title":"Federated Split BERT for Heterogeneous Text Classification","date":"2022-05-26","arxiv_id":"2205.13299","n_code_links":0,"syntology":null},{"paper":"/paper/green-hierarchical-vision-transformer-for","slug":"green-hierarchical-vision-transformer-for","title":"Green Hierarchical Vision Transformer for Masked Image Modeling","date":"2022-05-26","arxiv_id":"2205.13515","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["layneh/greenmim"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-dialogue-representations-from","slug":"learning-dialogue-representations-from","title":"Learning Dialogue Representations from Consecutive Utterances","date":"2022-05-26","arxiv_id":"2205.13568","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-dependency-grammar-for-fine","slug":"leveraging-dependency-grammar-for-fine","title":"Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks","date":"2022-05-26","arxiv_id":"2205.13164","n_code_links":1,"syntology":null},{"paper":"/paper/mixmim-mixed-and-masked-image-modeling-for","slug":"mixmim-mixed-and-masked-image-modeling-for","title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers","date":"2022-05-26","arxiv_id":"2205.13137","n_code_links":1,"syntology":null},{"paper":"/paper/semaffinet-semantic-affine-transformation-for","slug":"semaffinet-semantic-affine-transformation-for","title":"SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation","date":"2022-05-26","arxiv_id":"2205.13490","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":11,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wangzy22/SemAffiNet"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-document-vectors-using-cosine-similarity-1","slug":"the-document-vectors-using-cosine-similarity-1","title":"The Document Vectors Using Cosine Similarity Revisited","date":"2022-05-26","arxiv_id":"2205.13357","n_code_links":1,"syntology":null},{"paper":"/paper/towards-learning-universal-hyperparameter","slug":"towards-learning-universal-hyperparameter","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","date":"2022-05-26","arxiv_id":"2205.13320","n_code_links":1,"syntology":null},{"paper":"/paper/training-and-inference-on-any-order","slug":"training-and-inference-on-any-order","title":"Training and Inference on Any-Order Autoregressive Models the Right Way","date":"2022-05-26","arxiv_id":"2205.13554","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-for-partial-differential","slug":"transformer-for-partial-differential","title":"Transformer for Partial Differential Equations' Operator Learning","date":"2022-05-26","arxiv_id":"2205.13671","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":12,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["BaratiLab/OFormer"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vidi-a-video-dataset-of-incidents","slug":"vidi-a-video-dataset-of-incidents","title":"VIDI: A Video Dataset of Incidents","date":"2022-05-26","arxiv_id":"2205.13277","n_code_links":1,"syntology":null},{"paper":"/paper/your-transformer-may-not-be-as-powerful-as","slug":"your-transformer-may-not-be-as-powerful-as","title":"Your Transformer May Not be as Powerful as You Expect","date":"2022-05-26","arxiv_id":"2205.13401","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":["lsj2408/urpe"],"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":"/paper/bit-robustly-binarized-multi-distilled","slug":"bit-robustly-binarized-multi-distilled","title":"BiT: Robustly Binarized Multi-distilled Transformer","date":"2022-05-25","arxiv_id":"2205.13016","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"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) · 0 unverified","official":{"repos":["facebookresearch/bit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"conditional-set-generation-using-seq2seq-1","title":"Conditional set generation using Seq2seq models","date":"2022-05-25","arxiv_id":"2205.12485","n_code_links":0,"syntology":null},{"paper":null,"slug":"eye-gaze-guided-vision-transformer-for","title":"Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning","date":"2022-05-25","arxiv_id":"2205.12466","n_code_links":0,"syntology":null},{"paper":"/paper/factorizing-content-and-budget-decisions-in","slug":"factorizing-content-and-budget-decisions-in","title":"Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents","date":"2022-05-25","arxiv_id":"2205.12486","n_code_links":1,"syntology":null},{"paper":"/paper/inception-transformer","slug":"inception-transformer","title":"Inception Transformer","date":"2022-05-25","arxiv_id":"2205.12956","n_code_links":4,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["sail-sg/iformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"large-language-models-are-zero-shot-clinical","title":"Large Language Models are Few-Shot Clinical Information Extractors","date":"2022-05-25","arxiv_id":"2205.12689","n_code_links":0,"syntology":null},{"paper":null,"slug":"lifelong-learning-natural-language-processing","title":"Lifelong Learning Natural Language Processing Approach for Multilingual Data Classification","date":"2022-05-25","arxiv_id":"2206.11867","n_code_links":0,"syntology":null},{"paper":"/paper/mocovit-mobile-convolutional-vision","slug":"mocovit-mobile-convolutional-vision","title":"MoCoViT: Mobile Convolutional Vision Transformer","date":"2022-05-25","arxiv_id":"2205.12635","n_code_links":1,"syntology":null},{"paper":"/paper/naturalprover-grounded-mathematical-proof","slug":"naturalprover-grounded-mathematical-proof","title":"NaturalProver: Grounded Mathematical Proof Generation with Language Models","date":"2022-05-25","arxiv_id":"2205.12910","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":["wellecks/naturalprover"],"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":"orca-interpreting-prompted-language-models","title":"ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data","date":"2022-05-25","arxiv_id":"2205.12600","n_code_links":0,"syntology":null},{"paper":"/paper/robustlr-evaluating-robustness-to-logical","slug":"robustlr-evaluating-robustness-to-logical","title":"RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoning","date":"2022-05-25","arxiv_id":"2205.12598","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["ink-usc/robustlr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/tacube-pre-computing-data-cubes-for-answering","slug":"tacube-pre-computing-data-cubes-for-answering","title":"TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data","date":"2022-05-25","arxiv_id":"2205.12682","n_code_links":1,"syntology":null},{"paper":null,"slug":"text-to-face-generation-with-stylegan2","title":"Text-to-Face Generation with StyleGAN2","date":"2022-05-25","arxiv_id":"2205.12512","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-understanding-label-regularization","title":"Do we need Label Regularization to Fine-tune Pre-trained Language Models?","date":"2022-05-25","arxiv_id":"2205.12428","n_code_links":0,"syntology":null},{"paper":null,"slug":"train-flat-then-compress-sharpness-aware","title":"Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models","date":"2022-05-25","arxiv_id":"2205.12694","n_code_links":0,"syntology":null},{"paper":"/paper/transcormer-transformer-for-sentence-scoring","slug":"transcormer-transformer-for-sentence-scoring","title":"Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling","date":"2022-05-25","arxiv_id":"2205.12986","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/vtp-volumetric-transformer-for-multi-view","slug":"vtp-volumetric-transformer-for-multi-view","title":"VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation","date":"2022-05-25","arxiv_id":"2205.12602","n_code_links":0,"syntology":null},{"paper":"/paper/vulberta-simplified-source-code-pre-training","slug":"vulberta-simplified-source-code-pre-training","title":"VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection","date":"2022-05-25","arxiv_id":"2205.12424","n_code_links":1,"syntology":null},{"paper":"/paper/adamix-mixture-of-adapter-for-parameter","slug":"adamix-mixture-of-adapter-for-parameter","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","date":"2022-05-24","arxiv_id":"2205.12410","n_code_links":1,"syntology":null},{"paper":null,"slug":"edit5-semi-autoregressive-text-editing-with","title":"EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start","date":"2022-05-24","arxiv_id":"2205.12209","n_code_links":0,"syntology":null},{"paper":"/paper/flute-figurative-language-understanding-and","slug":"flute-figurative-language-understanding-and","title":"FLUTE: Figurative Language Understanding through Textual Explanations","date":"2022-05-24","arxiv_id":"2205.12404","n_code_links":1,"syntology":null},{"paper":"/paper/formulating-few-shot-fine-tuning-towards","slug":"formulating-few-shot-fine-tuning-towards","title":"Formulating Few-shot Fine-tuning Towards Language Model Pre-training: A Pilot Study on Named Entity Recognition","date":"2022-05-24","arxiv_id":"2205.11799","n_code_links":1,"syntology":null},{"paper":"/paper/garden-path-traversal-within-gpt-2","slug":"garden-path-traversal-within-gpt-2","title":"Garden-Path Traversal in GPT-2","date":"2022-05-24","arxiv_id":"2205.12302","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wjurayj/garden-path-gpt2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/geomlama-geo-diverse-commonsense-probing-on","slug":"geomlama-geo-diverse-commonsense-probing-on","title":"GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models","date":"2022-05-24","arxiv_id":"2205.12247","n_code_links":1,"syntology":null},{"paper":"/paper/history-compression-via-language-models-in","slug":"history-compression-via-language-models-in","title":"History Compression via Language Models in Reinforcement Learning","date":"2022-05-24","arxiv_id":"2205.12258","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":6,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ml-jku/helm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-human-is-human-evaluation-improving-the","title":"The Authenticity Gap in Human Evaluation","date":"2022-05-24","arxiv_id":"2205.11930","n_code_links":0,"syntology":null},{"paper":"/paper/k-12bert-bert-for-k-12-education","slug":"k-12bert-bert-for-k-12-education","title":"K-12BERT: BERT for K-12 education","date":"2022-05-24","arxiv_id":"2205.12335","n_code_links":1,"syntology":null},{"paper":null,"slug":"medical-scientific-table-to-text-generation","title":"Medical Scientific Table-to-Text Generation with Human-in-the-Loop under the Data Sparsity Constraint","date":"2022-05-24","arxiv_id":"2205.12368","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-level-modeling-units-for-end-to-end","title":"Multi-Level Modeling Units for End-to-End Mandarin Speech Recognition","date":"2022-05-24","arxiv_id":"2205.11998","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-role-of-bidirectionality-in-language","title":"On the Role of Bidirectionality in Language Model Pre-Training","date":"2022-05-24","arxiv_id":"2205.11726","n_code_links":0,"syntology":null},{"paper":"/paper/partial-input-baselines-show-that-nli-models","slug":"partial-input-baselines-show-that-nli-models","title":"Partial-input baselines show that NLI models can ignore context, but they don't","date":"2022-05-24","arxiv_id":"2205.12181","n_code_links":1,"syntology":null},{"paper":null,"slug":"privacy-preserving-image-classification-using-1","title":"Privacy-Preserving Image Classification Using Vision Transformer","date":"2022-05-24","arxiv_id":"2205.12041","n_code_links":0,"syntology":null},{"paper":"/paper/retromae-pre-training-retrieval-oriented","slug":"retromae-pre-training-retrieval-oriented","title":"RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder","date":"2022-05-24","arxiv_id":"2205.12035","n_code_links":1,"syntology":null},{"paper":"/paper/sparse-mixers-combining-moe-and-mixing-to","slug":"sparse-mixers-combining-moe-and-mixing-to","title":"Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT","date":"2022-05-24","arxiv_id":"2205.12399","n_code_links":1,"syntology":null},{"paper":null,"slug":"symbolic-expression-transformer-a-computer","title":"Symbolic Expression Transformer: A Computer Vision Approach for Symbolic Regression","date":"2022-05-24","arxiv_id":"2205.11798","n_code_links":0,"syntology":null},{"paper":null,"slug":"umsnet-an-universal-multi-sensor-network-for","title":"UMSNet: An Universal Multi-sensor Network for Human Activity Recognition","date":"2022-05-24","arxiv_id":"2205.11756","n_code_links":0,"syntology":null},{"paper":null,"slug":"word-order-typology-in-multilingual-bert-a","title":"Word-order typology in Multilingual BERT: A case study in subordinate-clause detection","date":"2022-05-24","arxiv_id":"2205.11987","n_code_links":0,"syntology":null},{"paper":"/paper/workflow-discovery-from-dialogues-in-the-low","slug":"workflow-discovery-from-dialogues-in-the-low","title":"Workflow Discovery from Dialogues in the Low Data Regime","date":"2022-05-24","arxiv_id":"2205.11690","n_code_links":1,"syntology":null},{"paper":"/paper/a-question-answer-driven-approach-to-reveal","slug":"a-question-answer-driven-approach-to-reveal","title":"A Question-Answer Driven Approach to Reveal Affirmative Interpretations from Verbal Negations","date":"2022-05-23","arxiv_id":"2205.11467","n_code_links":1,"syntology":null},{"paper":"/paper/accurate-and-resource-efficient-lipreading","slug":"accurate-and-resource-efficient-lipreading","title":"Accurate and Resource-Efficient Lipreading with Efficientnetv2 and Transformers","date":"2022-05-23","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/artificial-intelligence-for-topic-modelling","slug":"artificial-intelligence-for-topic-modelling","title":"Artificial intelligence for topic modelling in Hindu philosophy: mapping themes between the Upanishads and the Bhagavad Gita","date":"2022-05-23","arxiv_id":"2205.11020","n_code_links":1,"syntology":null},{"paper":"/paper/banglanlg-benchmarks-and-resources-for","slug":"banglanlg-benchmarks-and-resources-for","title":"BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla","date":"2022-05-23","arxiv_id":"2205.11081","n_code_links":2,"syntology":null},{"paper":"/paper/bolt-fused-window-transformers-for-fmri-time","slug":"bolt-fused-window-transformers-for-fmri-time","title":"BolT: Fused Window Transformers for fMRI Time Series Analysis","date":"2022-05-23","arxiv_id":"2205.11578","n_code_links":1,"syntology":null},{"paper":null,"slug":"distilcamembert-a-distillation-of-the-french","title":"DistilCamemBERT: a distillation of the French model CamemBERT","date":"2022-05-23","arxiv_id":"2205.11111","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-short-text-classification-with","title":"Improving Short Text Classification With Augmented Data Using GPT-3","date":"2022-05-23","arxiv_id":"2205.10981","n_code_links":0,"syntology":null},{"paper":"/paper/kold-korean-offensive-language-dataset","slug":"kold-korean-offensive-language-dataset","title":"KOLD: Korean Offensive Language Dataset","date":"2022-05-23","arxiv_id":"2205.11315","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-ignore-adversarial-attacks-1","title":"Learning to Ignore Adversarial Attacks","date":"2022-05-23","arxiv_id":"2205.11551","n_code_links":0,"syntology":null},{"paper":"/paper/looking-for-a-handsome-carpenter-debiasing","slug":"looking-for-a-handsome-carpenter-debiasing","title":"Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements","date":"2022-05-23","arxiv_id":"2205.11374","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-paradox-of-learning-to-reason-from","slug":"on-the-paradox-of-learning-to-reason-from","title":"On the Paradox of Learning to Reason from Data","date":"2022-05-23","arxiv_id":"2205.11502","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["joshuacnf/paradox-learning2reason"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/outliers-dimensions-that-disrupt-transformers","slug":"outliers-dimensions-that-disrupt-transformers","title":"Outliers Dimensions that Disrupt Transformers Are Driven by Frequency","date":"2022-05-23","arxiv_id":"2205.11380","n_code_links":1,"syntology":{"ran":8,"of":16,"n_ran_checked":8,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["gpucce/outliersvsfreq"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/parameter-efficient-sparsity-for-large","slug":"parameter-efficient-sparsity-for-large","title":"Parameter-Efficient Sparsity for Large Language Models Fine-Tuning","date":"2022-05-23","arxiv_id":"2205.11005","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 2 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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["alibaba/AliceMind","yuchaoli/pst"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"penguins-don-t-fly-reasoning-about-generics","title":"Penguins Don't Fly: Reasoning about Generics through Instantiations and Exceptions","date":"2022-05-23","arxiv_id":"2205.11658","n_code_links":0,"syntology":null},{"paper":"/paper/prompt-tuning-for-discriminative-pre-trained-1","slug":"prompt-tuning-for-discriminative-pre-trained-1","title":"Prompt Tuning for Discriminative Pre-trained Language Models","date":"2022-05-23","arxiv_id":"2205.11166","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":5,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["thunlp/dpt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"rl-with-kl-penalties-is-better-viewed-as","title":"RL with KL penalties is better viewed as Bayesian inference","date":"2022-05-23","arxiv_id":"2205.11275","n_code_links":0,"syntology":null},{"paper":null,"slug":"scholarbert-bigger-is-not-always-better","title":"The Diminishing Returns of Masked Language Models to Science","date":"2022-05-23","arxiv_id":"2205.11342","n_code_links":0,"syntology":null},{"paper":"/paper/selfreformer-self-refined-network-with","slug":"selfreformer-self-refined-network-with","title":"SelfReformer: Self-Refined Network with Transformer for Salient Object Detection","date":"2022-05-23","arxiv_id":"2205.11283","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["BarCodeReader/SelfReformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"simple-recurrence-improves-masked-language","title":"Simple Recurrence Improves Masked Language Models","date":"2022-05-23","arxiv_id":"2205.11588","n_code_links":0,"syntology":null},{"paper":"/paper/super-vision-transformer","slug":"super-vision-transformer","title":"Super Vision Transformer","date":"2022-05-23","arxiv_id":"2205.11397","n_code_links":1,"syntology":null},{"paper":"/paper/templm-distilling-language-models-into","slug":"templm-distilling-language-models-into","title":"TempLM: Distilling Language Models into Template-Based Generators","date":"2022-05-23","arxiv_id":"2205.11055","n_code_links":1,"syntology":null},{"paper":"/paper/time-series-transformer-generative","slug":"time-series-transformer-generative","title":"Time-series Transformer Generative Adversarial Networks","date":"2022-05-23","arxiv_id":"2205.11164","n_code_links":5,"syntology":null},{"paper":null,"slug":"use-of-transformer-based-models-for-word","title":"Use of Transformer-Based Models for Word-Level Transliteration of the Book of the Dean of Lismore","date":"2022-05-23","arxiv_id":"2205.11370","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-graph-enhanced-bert-model-for-event-2","title":"A Graph Enhanced BERT Model for Event Prediction","date":"2022-05-22","arxiv_id":"2205.10822","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-query-selection-for-fast-visual","title":"Dynamic Query Selection for Fast Visual Perceiver","date":"2022-05-22","arxiv_id":"2205.10873","n_code_links":0,"syntology":null},{"paper":"/paper/graphmae-self-supervised-masked-graph","slug":"graphmae-self-supervised-masked-graph","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","date":"2022-05-22","arxiv_id":"2205.10803","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["thudm/graphmae"],"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/instruction-induction-from-few-examples-to","slug":"instruction-induction-from-few-examples-to","title":"Instruction Induction: From Few Examples to Natural Language Task Descriptions","date":"2022-05-22","arxiv_id":"2205.10782","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":["orhonovich/instruction-induction"],"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/relphormer-relational-graph-transformer-for","slug":"relphormer-relational-graph-transformer-for","title":"Relphormer: Relational Graph Transformer for Knowledge Graph Representations","date":"2022-05-22","arxiv_id":"2205.10852","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zjunlp/relphormer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/deeper-vs-wider-a-revisit-of-transformer","slug":"deeper-vs-wider-a-revisit-of-transformer","title":"A Study on Transformer Configuration and Training Objective","date":"2022-05-21","arxiv_id":"2205.10505","n_code_links":0,"syntology":null},{"paper":"/paper/dproq-a-gated-graph-transformer-for-protein","slug":"dproq-a-gated-graph-transformer-for-protein","title":"DProQ: A Gated-Graph Transformer for Protein Complex Structure Assessment","date":"2022-05-21","arxiv_id":"2205.10627","n_code_links":1,"syntology":null},{"paper":"/paper/hlatr-enhance-multi-stage-text-retrieval-with","slug":"hlatr-enhance-multi-stage-text-retrieval-with","title":"HLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer Reranking","date":"2022-05-21","arxiv_id":"2205.10569","n_code_links":1,"syntology":null},{"paper":"/paper/least-to-most-prompting-enables-complex","slug":"least-to-most-prompting-enables-complex","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","date":"2022-05-21","arxiv_id":"2205.10625","n_code_links":1,"syntology":null},{"paper":"/paper/life-after-bert-what-do-other-muppets-2","slug":"life-after-bert-what-do-other-muppets-2","title":"Life after BERT: What do Other Muppets Understand about Language?","date":"2022-05-21","arxiv_id":"2205.10696","n_code_links":1,"syntology":null},{"paper":"/paper/pre-training-data-quality-and-quantity-for-a","slug":"pre-training-data-quality-and-quantity-for-a","title":"Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese","date":"2022-05-21","arxiv_id":"2205.10517","n_code_links":1,"syntology":null}],"record_sha256":"6be0d1a198c913d81eb2e81bc109a27d1f4f2c0c1a17d91010c54e10050324b0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}