{"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/linear-layer/papers/194","list_of":"/method/linear-layer","method":"Linear Layer","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":194,"pages_in_order":255,"rows_per_page":100,"rows":[19301,19400],"of":25421,"counts":{"archive_papers_tagged":25421,"with_a_code_link":11479,"where_syntology_ran_a_sample":3523,"not_listed_spam_title":0,"listed":25421,"listed_where_code_ran":3523,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2976,"every_run_a_failure_of_syntologys_instrument":547,"listed_with_a_run_with_no_instrument_failure":2976,"listed_every_run_a_failure_of_syntologys_instrument":547,"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/linear-layer","prev":"/method/linear-layer/papers/193","next":"/method/linear-layer/papers/195","papers":[{"paper":"/paper/an-empirical-study-of-training-end-to-end","slug":"an-empirical-study-of-training-end-to-end","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","date":"2021-11-03","arxiv_id":"2111.02387","n_code_links":3,"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":["zdou0830/meter"],"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/an-explanation-of-in-context-learning-as-1","slug":"an-explanation-of-in-context-learning-as-1","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","date":"2021-11-03","arxiv_id":"2111.02080","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["p-lambda/incontext-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bert-dre-bert-with-deep-recursive-encoder-for","title":"BERT-DRE: BERT with Deep Recursive Encoder for Natural Language Sentence Matching","date":"2021-11-03","arxiv_id":"2111.02188","n_code_links":0,"syntology":null},{"paper":null,"slug":"prostformer-pre-trained-progressive-space","title":"ProSTformer: Pre-trained Progressive Space-Time Self-attention Model for Traffic Flow Forecasting","date":"2021-11-03","arxiv_id":"2111.03459","n_code_links":0,"syntology":null},{"paper":null,"slug":"theeyecorpus-experiments-in-reducing-nlp-bias","title":"TheEyeCorpus: Experiments in Reducing NLP Bias and Identifiability for Large LMs","date":"2021-11-03","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/transms-transformers-for-super-resolution","slug":"transms-transformers-for-super-resolution","title":"TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging","date":"2021-11-03","arxiv_id":"2111.02163","n_code_links":2,"syntology":null},{"paper":"/paper/vlmo-unified-vision-language-pre-training","slug":"vlmo-unified-vision-language-pre-training","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","date":"2021-11-03","arxiv_id":"2111.02358","n_code_links":2,"syntology":null},{"paper":null,"slug":"can-vision-transformers-perform-convolution-1","title":"Can Vision Transformers Perform Convolution?","date":"2021-11-02","arxiv_id":"2111.01353","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-of-hate-speech-using-bert-and-hate","title":"Detection of Hate Speech using BERT and Hate Speech Word Embedding with Deep Model","date":"2021-11-02","arxiv_id":"2111.01515","n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-documents-relevance-to-search","title":"Explaining Documents' Relevance to Search Queries","date":"2021-11-02","arxiv_id":"2111.01314","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-split-vision-transformer-for-covid","title":"Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training","date":"2021-11-02","arxiv_id":"2111.01338","n_code_links":0,"syntology":null},{"paper":"/paper/relational-self-attention-what-s-missing-in","slug":"relational-self-attention-what-s-missing-in","title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","date":"2021-11-02","arxiv_id":"2111.01673","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["KimManjin/RSA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/revisiting-spatio-temporal-layouts-for","slug":"revisiting-spatio-temporal-layouts-for","title":"Revisiting spatio-temporal layouts for compositional action recognition","date":"2021-11-02","arxiv_id":"2111.01936","n_code_links":1,"syntology":null},{"paper":"/paper/sentence-encoding-for-dialogue-act","slug":"sentence-encoding-for-dialogue-act","title":"Sentence encoding for Dialogue Act classification","date":"2021-11-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/uquad1-0-development-of-an-urdu-question","slug":"uquad1-0-development-of-an-urdu-question","title":"UQuAD1.0: Development of an Urdu Question Answering Training Data for Machine Reading Comprehension","date":"2021-11-02","arxiv_id":"2111.01543","n_code_links":0,"syntology":null},{"paper":null,"slug":"accounting-for-dependencies-in-deep-learning","title":"Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imaging","date":"2021-11-01","arxiv_id":"2111.01556","n_code_links":0,"syntology":null},{"paper":"/paper/arch-net-model-distillation-for-architecture","slug":"arch-net-model-distillation-for-architecture","title":"Arch-Net: Model Distillation for Architecture Agnostic Model Deployment","date":"2021-11-01","arxiv_id":"2111.01135","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparative-study-of-long-document","title":"Comparative Study of Long Document Classification","date":"2021-11-01","arxiv_id":"2111.00702","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-hate-speech-detection-using","title":"Cross-lingual Hate Speech Detection using Transformer Models","date":"2021-11-01","arxiv_id":"2111.00981","n_code_links":0,"syntology":null},{"paper":"/paper/identifying-causal-associations-in-tweets","slug":"identifying-causal-associations-in-tweets","title":"Identifying causal relations in tweets using deep learning: Use case on diabetes-related tweets from 2017-2021","date":"2021-11-01","arxiv_id":"2111.01225","n_code_links":1,"syntology":null},{"paper":"/paper/itacotron-2-transfering-english-speech","slug":"itacotron-2-transfering-english-speech","title":"ITAcotron 2: Transfering English Speech Synthesis Architectures and Speech Features to Italian","date":"2021-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-generate-piano-music-with-sustain","slug":"learning-to-generate-piano-music-with-sustain","title":"Learning To Generate Piano Music With Sustain Pedals","date":"2021-11-01","arxiv_id":"2111.01216","n_code_links":1,"syntology":null},{"paper":"/paper/maple-masking-words-to-generate-blackout","slug":"maple-masking-words-to-generate-blackout","title":"MAPLE – MAsking words to generate blackout Poetry using sequence-to-sequence LEarning","date":"2021-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"recent-advances-in-natural-language","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","date":"2021-11-01","arxiv_id":"2111.01243","n_code_links":0,"syntology":null},{"paper":"/paper/rmnet-equivalently-removing-residual-1","slug":"rmnet-equivalently-removing-residual-1","title":"RMNet: Equivalently Removing Residual Connection from Networks","date":"2021-11-01","arxiv_id":"2111.00687","n_code_links":1,"syntology":null},{"paper":null,"slug":"vsec-transformer-based-model-for-vietnamese","title":"VSEC: Transformer-based Model for Vietnamese Spelling Correction","date":"2021-11-01","arxiv_id":"2111.00640","n_code_links":0,"syntology":null},{"paper":"/paper/wino-x-multilingual-winograd-schemas-for","slug":"wino-x-multilingual-winograd-schemas-for","title":"Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution","date":"2021-11-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/fineas-financial-embedding-analysis-of","slug":"fineas-financial-embedding-analysis-of","title":"FinEAS: Financial Embedding Analysis of Sentiment","date":"2021-10-31","arxiv_id":"2111.00526","n_code_links":1,"syntology":null},{"paper":"/paper/backdoor-pre-trained-models-can-transfer-to","slug":"backdoor-pre-trained-models-can-transfer-to","title":"Backdoor Pre-trained Models Can Transfer to All","date":"2021-10-30","arxiv_id":"2111.00197","n_code_links":1,"syntology":null},{"paper":"/paper/cross-modality-fusion-transformer-for","slug":"cross-modality-fusion-transformer-for","title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","date":"2021-10-30","arxiv_id":"2111.00273","n_code_links":1,"syntology":null},{"paper":"/paper/dsee-dually-sparsity-embedded-efficient-1","slug":"dsee-dually-sparsity-embedded-efficient-1","title":"DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models","date":"2021-10-30","arxiv_id":"2111.00160","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":8,"n_instrument":2,"unverified":3,"pointer_only":10,"phrase":"10 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["vita-group/dsee"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"magic-pyramid-accelerating-inference-with","title":"Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning","date":"2021-10-30","arxiv_id":"2111.00230","n_code_links":0,"syntology":null},{"paper":"/paper/patchformer-a-versatile-3d-transformer-based","slug":"patchformer-a-versatile-3d-transformer-based","title":"PatchFormer: An Efficient Point Transformer with Patch Attention","date":"2021-10-30","arxiv_id":"2111.00207","n_code_links":0,"syntology":null},{"paper":"/paper/amendable-generation-for-dialogue-state","slug":"amendable-generation-for-dialogue-state","title":"Amendable Generation for Dialogue State Tracking","date":"2021-10-29","arxiv_id":"2110.15659","n_code_links":1,"syntology":null},{"paper":"/paper/delayed-propagation-transformer-a-universal","slug":"delayed-propagation-transformer-a-universal","title":"Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems","date":"2021-10-29","arxiv_id":"2110.15926","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":6,"phrase":"5 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["vita-group/dept"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/rebel-relation-extraction-by-end-to-end","slug":"rebel-relation-extraction-by-end-to-end","title":"REBEL: Relation Extraction By End-to-end Language generation","date":"2021-10-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/structure-aware-fine-tuning-of-sequence-to","slug":"structure-aware-fine-tuning-of-sequence-to","title":"Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing","date":"2021-10-29","arxiv_id":"2110.15534","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-golden-rule-as-a-heuristic-to-measure-the","title":"The Golden Rule as a Heuristic to Measure the Fairness of Texts Using Machine Learning","date":"2021-10-29","arxiv_id":"2111.00107","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-sequence-tagging-framework-for","title":"ICDM 2020 Knowledge Graph Contest: Consumer Event-Cause Extraction","date":"2021-10-28","arxiv_id":"2110.15722","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sequence-to-sequence-model-for-extracting","title":"A Sequence to Sequence Model for Extracting Multiple Product Name Entities from Dialog","date":"2021-10-28","arxiv_id":"2110.14843","n_code_links":0,"syntology":null},{"paper":null,"slug":"blending-anti-aliasing-into-vision","title":"Blending Anti-Aliasing into Vision Transformer","date":"2021-10-28","arxiv_id":"2110.15156","n_code_links":0,"syntology":null},{"paper":"/paper/bridge-the-gap-between-cv-and-nlp-a-gradient","slug":"bridge-the-gap-between-cv-and-nlp-a-gradient","title":"Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework","date":"2021-10-28","arxiv_id":"2110.15317","n_code_links":1,"syntology":null},{"paper":"/paper/colossal-ai-a-unified-deep-learning-system","slug":"colossal-ai-a-unified-deep-learning-system","title":"Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training","date":"2021-10-28","arxiv_id":"2110.14883","n_code_links":1,"syntology":null},{"paper":null,"slug":"dispensed-transformer-network-for","title":"Dispensed Transformer Network for Unsupervised Domain Adaptation","date":"2021-10-28","arxiv_id":"2110.14944","n_code_links":0,"syntology":null},{"paper":null,"slug":"nxmtransformer-semi-structured-sparsification","title":"NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM","date":"2021-10-28","arxiv_id":"2110.15766","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-attention-heads-of-transformer-models","title":"Pruning Attention Heads of Transformer Models Using A* Search: A Novel Approach to Compress Big NLP Architectures","date":"2021-10-28","arxiv_id":"2110.15225","n_code_links":0,"syntology":null},{"paper":"/paper/scatterbrain-unifying-sparse-and-low-rank","slug":"scatterbrain-unifying-sparse-and-low-rank","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","date":"2021-10-28","arxiv_id":"2110.15343","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":["hazyresearch/scatterbrain"],"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/self-supervised-representation-learning-on-1","slug":"self-supervised-representation-learning-on-1","title":"Hyper-Representations: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction","date":"2021-10-28","arxiv_id":"2110.15288","n_code_links":1,"syntology":{"ran":9,"of":15,"n_ran_checked":9,"n_instrument":0,"unverified":6,"pointer_only":15,"phrase":"9 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["hsg-aiml/neurips_2021-weight_space_learning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/semi-siamese-bi-encoder-neural-ranking-model","slug":"semi-siamese-bi-encoder-neural-ranking-model","title":"Semi-Siamese Bi-encoder Neural Ranking Model Using Lightweight Fine-Tuning","date":"2021-10-28","arxiv_id":"2110.14943","n_code_links":1,"syntology":null},{"paper":null,"slug":"anomaly-injected-deep-support-vector-data","title":"Anomaly-Injected Deep Support Vector Data Description for Text Outlier Detection","date":"2021-10-27","arxiv_id":"2110.14729","n_code_links":0,"syntology":null},{"paper":"/paper/ask-me-in-your-own-words-paraphrasing-for","slug":"ask-me-in-your-own-words-paraphrasing-for","title":"Ask me in your own words: paraphrasing for multitask question answering","date":"2021-10-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"detecting-dementia-from-speech-and","title":"Detecting Dementia from Speech and Transcripts using Transformers","date":"2021-10-27","arxiv_id":"2110.14769","n_code_links":0,"syntology":null},{"paper":"/paper/discovering-non-monotonic-autoregressive","slug":"discovering-non-monotonic-autoregressive","title":"Discovering Non-monotonic Autoregressive Orderings with Variational Inference","date":"2021-10-27","arxiv_id":"2110.15797","n_code_links":1,"syntology":{"ran":1,"of":7,"n_ran_checked":1,"n_instrument":0,"unverified":6,"pointer_only":0,"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) · 6 unverified","official":{"repos":["xuanlinli17/autoregressive_inference"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transfer-learning-with-causal-counterfactual","title":"Transfer learning with causal counterfactual reasoning in Decision Transformers","date":"2021-10-27","arxiv_id":"2110.14355","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-generalize-deepsets-and-can-be","slug":"transformers-generalize-deepsets-and-can-be","title":"Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs","date":"2021-10-27","arxiv_id":"2110.14416","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["jw9730/hot"],"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":"vision-transformer-for-classification-of","title":"Vision Transformer for Classification of Breast Ultrasound Images","date":"2021-10-27","arxiv_id":"2110.14731","n_code_links":0,"syntology":null},{"paper":null,"slug":"bioie-biomedical-information-extraction-with","title":"BioIE: Biomedical Information Extraction with Multi-head Attention Enhanced Graph Convolutional Network","date":"2021-10-26","arxiv_id":"2110.13683","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-t-fool-me-adversarially-robust","title":"Can't Fool Me: Adversarially Robust Transformer for Video Understanding","date":"2021-10-26","arxiv_id":"2110.13950","n_code_links":0,"syntology":null},{"paper":null,"slug":"clauserec-a-clause-recommendation-framework","title":"CLAUSEREC: A Clause Recommendation Framework for AI-aided Contract Authoring","date":"2021-10-26","arxiv_id":"2110.15794","n_code_links":0,"syntology":null},{"paper":"/paper/geometric-transformer-for-end-to-end-molecule","slug":"geometric-transformer-for-end-to-end-molecule","title":"Geometric Transformer for End-to-End Molecule Properties Prediction","date":"2021-10-26","arxiv_id":"2110.13721","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["yoniLc/GeometricTransformerMolecule"],"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/hierarchical-transformers-are-more-efficient","slug":"hierarchical-transformers-are-more-efficient","title":"Hierarchical Transformers Are More Efficient Language Models","date":"2021-10-26","arxiv_id":"2110.13711","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google/trax"],"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","unlocated"]}}},{"paper":null,"slug":"leveraging-local-temporal-information-for","title":"Leveraging Local Temporal Information for Multimodal Scene Classification","date":"2021-10-26","arxiv_id":"2110.13992","n_code_links":0,"syntology":null},{"paper":"/paper/post-processing-for-individual-fairness","slug":"post-processing-for-individual-fairness","title":"Post-processing for Individual Fairness","date":"2021-10-26","arxiv_id":"2110.13796","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":["felix-petersen/fairness-post-processing"],"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/s2s-ft-fine-tuning-pretrained-transformer","slug":"s2s-ft-fine-tuning-pretrained-transformer","title":"s2s-ft: Fine-Tuning Pretrained Transformer Encoders for Sequence-to-Sequence Learning","date":"2021-10-26","arxiv_id":"2110.13640","n_code_links":1,"syntology":null},{"paper":"/paper/tribert-full-body-human-centric-audio-visual","slug":"tribert-full-body-human-centric-audio-visual","title":"TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation","date":"2021-10-26","arxiv_id":"2110.13412","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["ubc-vision/tribert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/wavlm-large-scale-self-supervised-pre","slug":"wavlm-large-scale-self-supervised-pre","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","date":"2021-10-26","arxiv_id":"2110.13900","n_code_links":9,"syntology":null},{"paper":"/paper/actions-speak-louder-than-listening","slug":"actions-speak-louder-than-listening","title":"Actions Speak Louder than Listening: Evaluating Music Style Transfer based on Editing Experience","date":"2021-10-25","arxiv_id":"2110.12855","n_code_links":1,"syntology":null},{"paper":"/paper/doctr-document-image-transformer-for","slug":"doctr-document-image-transformer-for","title":"DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction","date":"2021-10-25","arxiv_id":"2110.12942","n_code_links":2,"syntology":null},{"paper":"/paper/fine-tuning-of-pre-trained-transformers-for","slug":"fine-tuning-of-pre-trained-transformers-for","title":"Fine-tuning of Pre-trained Transformers for Hate, Offensive, and Profane Content Detection in English and Marathi","date":"2021-10-25","arxiv_id":"2110.12687","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-artificial-texts-as-substitution","title":"Generating artificial texts as substitution or complement of training data","date":"2021-10-25","arxiv_id":"2110.13016","n_code_links":0,"syntology":null},{"paper":null,"slug":"gophormer-ego-graph-transformer-for-node","title":"Gophormer: Ego-Graph Transformer for Node Classification","date":"2021-10-25","arxiv_id":"2110.13094","n_code_links":0,"syntology":null},{"paper":"/paper/history-aware-multimodal-transformer-for","slug":"history-aware-multimodal-transformer-for","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","date":"2021-10-25","arxiv_id":"2110.13309","n_code_links":1,"syntology":{"ran":7,"of":15,"n_ran_checked":7,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"7 ran (of which 3 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) · 8 unverified","official":null}},{"paper":"/paper/iconqa-a-new-benchmark-for-abstract-diagram","slug":"iconqa-a-new-benchmark-for-abstract-diagram","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","date":"2021-10-25","arxiv_id":"2110.13214","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":10,"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) · 2 unverified","official":{"repos":["lupantech/iconqa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/mvt-multi-view-vision-transformer-for-3d","slug":"mvt-multi-view-vision-transformer-for-3d","title":"MVT: Multi-view Vision Transformer for 3D Object Recognition","date":"2021-10-25","arxiv_id":"2110.13083","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shanshuo/MVT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"revisiting-cnn-for-highly-inflected-bengali","title":"Paradigm Shift in Language Modeling: Revisiting CNN for Modeling Sanskrit Originated Bengali and Hindi Language","date":"2021-10-25","arxiv_id":"2110.13032","n_code_links":0,"syntology":null},{"paper":null,"slug":"stransgan-an-empirical-study-on-transformer-1","title":"The Nuts and Bolts of Adopting Transformer in GANs","date":"2021-10-25","arxiv_id":"2110.13107","n_code_links":0,"syntology":null},{"paper":"/paper/cvt-assd-convolutional-vision-transformer","slug":"cvt-assd-convolutional-vision-transformer","title":"CvT-ASSD: Convolutional vision-Transformer Based Attentive Single Shot MultiBox Detector","date":"2021-10-24","arxiv_id":"2110.12364","n_code_links":1,"syntology":null},{"paper":null,"slug":"hate-and-offensive-speech-detection-in-hindi","title":"Hate and Offensive Speech Detection in Hindi and Marathi","date":"2021-10-23","arxiv_id":"2110.12200","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-countable-armed-bandit-with-vanishing","title":"Bandits with Dynamic Arm-acquisition Costs","date":"2021-10-23","arxiv_id":"2110.12118","n_code_links":0,"syntology":null},{"paper":"/paper/double-trouble-how-to-not-explain-a-text","slug":"double-trouble-how-to-not-explain-a-text","title":"Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?","date":"2021-10-22","arxiv_id":"2110.11929","n_code_links":1,"syntology":null},{"paper":"/paper/learning-text-image-joint-embedding-for","slug":"learning-text-image-joint-embedding-for","title":"Learning Text-Image Joint Embedding for Efficient Cross-Modal Retrieval with Deep Feature Engineering","date":"2021-10-22","arxiv_id":"2110.11592","n_code_links":1,"syntology":null},{"paper":null,"slug":"mhattnsurv-multi-head-attention-for-survival","title":"MHAttnSurv: Multi-Head Attention for Survival Prediction Using Whole-Slide Pathology Images","date":"2021-10-22","arxiv_id":"2110.11558","n_code_links":0,"syntology":null},{"paper":null,"slug":"signature-graph-networks","title":"Signature-Graph Networks","date":"2021-10-22","arxiv_id":"2110.11551","n_code_links":0,"syntology":null},{"paper":"/paper/3d-anas-v2-grafting-transformer-module-on","slug":"3d-anas-v2-grafting-transformer-module-on","title":"Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image Classification","date":"2021-10-21","arxiv_id":"2110.11084","n_code_links":1,"syntology":null},{"paper":"/paper/cloob-modern-hopfield-networks-with-infoloob-1","slug":"cloob-modern-hopfield-networks-with-infoloob-1","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","date":"2021-10-21","arxiv_id":"2110.11316","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":1,"n_instrument":6,"unverified":4,"pointer_only":4,"phrase":"7 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; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ml-jku/cloob"],"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":["community","official"]}}},{"paper":"/paper/fast-model-editing-at-scale-1","slug":"fast-model-editing-at-scale-1","title":"Fast Model Editing at Scale","date":"2021-10-21","arxiv_id":"2110.11309","n_code_links":3,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["eric-mitchell/mend"],"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":null,"slug":"modeling-performance-in-open-domain-dialogue","title":"Modeling Performance in Open-Domain Dialogue with PARADISE","date":"2021-10-21","arxiv_id":"2110.11164","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-acceleration-with-dynamic-sparse","title":"Transformer Acceleration with Dynamic Sparse Attention","date":"2021-10-21","arxiv_id":"2110.11299","n_code_links":0,"syntology":null},{"paper":null,"slug":"vis-top-visual-transformer-overlay-processor","title":"Vis-TOP: Visual Transformer Overlay Processor","date":"2021-10-21","arxiv_id":"2110.10957","n_code_links":0,"syntology":null},{"paper":null,"slug":"after-unet-axial-fusion-transformer-unet-for","title":"AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentation","date":"2021-10-20","arxiv_id":"2110.10403","n_code_links":0,"syntology":null},{"paper":"/paper/aniformer-data-driven-3d-animation-with","slug":"aniformer-data-driven-3d-animation-with","title":"AniFormer: Data-driven 3D Animation with Transformer","date":"2021-10-20","arxiv_id":"2110.10533","n_code_links":1,"syntology":null},{"paper":null,"slug":"continual-learning-in-multilingual-nmt-via","title":"Continual Learning in Multilingual NMT via Language-Specific Embeddings","date":"2021-10-20","arxiv_id":"2110.10478","n_code_links":0,"syntology":null},{"paper":"/paper/distributionally-robust-classifiers-in","slug":"distributionally-robust-classifiers-in","title":"Distributionally Robust Classifiers in Sentiment Analysis","date":"2021-10-20","arxiv_id":"2110.10372","n_code_links":1,"syntology":null},{"paper":null,"slug":"esod-edge-based-task-scheduling-for-object","title":"ESOD:Edge-based Task Scheduling for Object Detection","date":"2021-10-20","arxiv_id":"2110.11342","n_code_links":0,"syntology":null},{"paper":"/paper/few-shot-temporal-action-localization-with","slug":"few-shot-temporal-action-localization-with","title":"Few-Shot Temporal Action Localization with Query Adaptive Transformer","date":"2021-10-20","arxiv_id":"2110.10552","n_code_links":1,"syntology":null},{"paper":null,"slug":"sea-graph-shell-attention-in-graph-neural","title":"SEA: Graph Shell Attention in Graph Neural Networks","date":"2021-10-20","arxiv_id":"2110.10674","n_code_links":0,"syntology":null},{"paper":null,"slug":"slam-a-unified-encoder-for-speech-and","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","date":"2021-10-20","arxiv_id":"2110.10329","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-accurate-and-reliable-iris","title":"Toward Accurate and Reliable Iris Segmentation Using Uncertainty Learning","date":"2021-10-20","arxiv_id":"2110.10334","n_code_links":0,"syntology":null},{"paper":null,"slug":"vldeformer-learning-visual-semantic","title":"VLDeformer: Vision-Language Decomposed Transformer for Fast Cross-Modal Retrieval","date":"2021-10-20","arxiv_id":"2110.11338","n_code_links":0,"syntology":null},{"paper":"/paper/a-picture-is-worth-a-thousand-words-a-unified","slug":"a-picture-is-worth-a-thousand-words-a-unified","title":"A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation","date":"2021-10-19","arxiv_id":"2110.09756","n_code_links":1,"syntology":null}],"record_sha256":"6f3a8c7bfa822fb01ee4b05230f62ca859f171c30cbc875d4c43b77dd7a99e42","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}