{"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/212","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":212,"pages_in_order":250,"rows_per_page":100,"rows":[21101,21200],"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/211","next":"/method/layer-normalization/papers/213","papers":[{"paper":"/paper/russian-paraphrasers-paraphrase-with","slug":"russian-paraphrasers-paraphrase-with","title":"Russian Paraphrasers: Paraphrase with Transformers","date":"2021-04-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/spatial-temporal-graph-transformer-for","slug":"spatial-temporal-graph-transformer-for","title":"TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking","date":"2021-04-01","arxiv_id":"2104.00194","n_code_links":0,"syntology":null},{"paper":null,"slug":"through-the-looking-glass-learning-to","title":"Through the Looking Glass: Learning to Attribute Synthetic Text Generated by Language Models","date":"2021-04-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"wakavt-a-sequential-variational-transformer","title":"WakaVT: A Sequential Variational Transformer for Waka Generation","date":"2021-04-01","arxiv_id":"2104.00426","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-neighbourhood-framework-for-resource-lean","title":"A Neighbourhood Framework for Resource-Lean Content Flagging","date":"2021-03-31","arxiv_id":"2103.17055","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-attacks-and-defenses-for-speech","title":"Adversarial Attacks and Defenses for Speech Recognition Systems","date":"2021-03-31","arxiv_id":"2103.17122","n_code_links":0,"syntology":null},{"paper":"/paper/going-deeper-with-image-transformers","slug":"going-deeper-with-image-transformers","title":"Going deeper with Image Transformers","date":"2021-03-31","arxiv_id":"2103.17239","n_code_links":21,"syntology":{"ran":9,"of":11,"n_ran_checked":6,"n_instrument":3,"unverified":2,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["rwightman/pytorch-image-models","facebookresearch/deit"],"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","unlocated"]}}},{"paper":"/paper/identifying-co-adaptation-of-algorithmic-and","slug":"identifying-co-adaptation-of-algorithmic-and","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","date":"2021-03-31","arxiv_id":"2103.17258","n_code_links":1,"syntology":null},{"paper":"/paper/learning-spatio-temporal-transformer-for","slug":"learning-spatio-temporal-transformer-for","title":"Learning Spatio-Temporal Transformer for Visual Tracking","date":"2021-03-31","arxiv_id":"2103.17154","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 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":["researchmm/Stark"],"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":"/paper/an-in-depth-analysis-of-passage-level-label","slug":"an-in-depth-analysis-of-passage-level-label","title":"An In-depth Analysis of Passage-Level Label Transfer for Contextual Document Ranking","date":"2021-03-30","arxiv_id":"2103.16669","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-graph-partitioning-for-very-large","title":"Automatic Graph Partitioning for Very Large-scale Deep Learning","date":"2021-03-30","arxiv_id":"2103.16063","n_code_links":0,"syntology":null},{"paper":"/paper/grounding-dialogue-systems-via-knowledge","slug":"grounding-dialogue-systems-via-knowledge","title":"Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers","date":"2021-03-30","arxiv_id":"2103.16289","n_code_links":1,"syntology":null},{"paper":"/paper/kaleido-bert-vision-language-pre-training-on","slug":"kaleido-bert-vision-language-pre-training-on","title":"Kaleido-BERT: Vision-Language Pre-training on Fashion Domain","date":"2021-03-30","arxiv_id":"2103.16110","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: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mczhuge/Kaleido-BERT"],"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":null,"slug":"read-and-attend-temporal-localisation-in-sign","title":"Read and Attend: Temporal Localisation in Sign Language Videos","date":"2021-03-30","arxiv_id":"2103.16481","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-spatial-dimensions-of-vision","slug":"rethinking-spatial-dimensions-of-vision","title":"Rethinking Spatial Dimensions of Vision Transformers","date":"2021-03-30","arxiv_id":"2103.16302","n_code_links":12,"syntology":{"ran":10,"of":20,"n_ran_checked":10,"n_instrument":0,"unverified":10,"pointer_only":0,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","official":{"repos":["naver-ai/pit"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"spatiotemporal-transformer-for-video-based","title":"Spatiotemporal Transformer for Video-based Person Re-identification","date":"2021-03-30","arxiv_id":"2103.16469","n_code_links":0,"syntology":null},{"paper":"/paper/xrjl-hkust-at-semeval-2021-task-4-wordnet","slug":"xrjl-hkust-at-semeval-2021-task-4-wordnet","title":"XRJL-HKUST at SemEval-2021 Task 4: WordNet-Enhanced Dual Multi-head Co-Attention for Reading Comprehension of Abstract Meaning","date":"2021-03-30","arxiv_id":"2103.16102","n_code_links":1,"syntology":null},{"paper":"/paper/2103-15358","slug":"2103-15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","date":"2021-03-29","arxiv_id":"2103.15358","n_code_links":3,"syntology":{"ran":8,"of":10,"n_ran_checked":5,"n_instrument":3,"unverified":2,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/vision-longformer"],"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":["listed","official"]}}},{"paper":"/paper/2103-15436","slug":"2103-15436","title":"Transformer Tracking","date":"2021-03-29","arxiv_id":"2103.15436","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":3,"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) · 2 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["chenxin-dlut/TransT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"contextual-text-embeddings-for-twi","title":"Contextual Text Embeddings for Twi","date":"2021-03-29","arxiv_id":"2103.15963","n_code_links":0,"syntology":null},{"paper":"/paper/cvt-introducing-convolutions-to-vision","slug":"cvt-introducing-convolutions-to-vision","title":"CvT: Introducing Convolutions to Vision Transformers","date":"2021-03-29","arxiv_id":"2103.15808","n_code_links":16,"syntology":{"ran":39,"of":47,"n_ran_checked":36,"n_instrument":3,"unverified":8,"pointer_only":8,"phrase":"39 ran (of which 19 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","official":{"repos":["microsoft/CvT"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["listed","named_in_paper","official","unlocated"]}}},{"paper":null,"slug":"retraining-distilbert-for-a-voice-shopping","title":"Retraining DistilBERT for a Voice Shopping Assistant by Using Universal Dependencies","date":"2021-03-29","arxiv_id":"2103.15737","n_code_links":0,"syntology":null},{"paper":"/paper/whitening-sentence-representations-for-better","slug":"whitening-sentence-representations-for-better","title":"Whitening Sentence Representations for Better Semantics and Faster Retrieval","date":"2021-03-29","arxiv_id":"2103.15316","n_code_links":3,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["bojone/BERT-whitening"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"hit-hierarchical-transformer-with-momentum","title":"HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval","date":"2021-03-28","arxiv_id":"2103.15049","n_code_links":0,"syntology":null},{"paper":"/paper/penelopie-enabling-open-information","slug":"penelopie-enabling-open-information","title":"PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation","date":"2021-03-28","arxiv_id":"2103.15075","n_code_links":1,"syntology":null},{"paper":null,"slug":"png-bert-augmented-bert-on-phonemes-and","title":"PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS","date":"2021-03-28","arxiv_id":"2103.15060","n_code_links":0,"syntology":null},{"paper":"/paper/2103-14803","slug":"2103-14803","title":"Face Transformer for Recognition","date":"2021-03-27","arxiv_id":"2103.14803","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":8,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zhongyy/Face-Transformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/2103-14899","slug":"2103-14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","date":"2021-03-27","arxiv_id":"2103.14899","n_code_links":15,"syntology":{"ran":17,"of":26,"n_ran_checked":17,"n_instrument":0,"unverified":9,"pointer_only":0,"phrase":"17 ran (of which 10 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 1 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","official":{"repos":["IBM/CrossViT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"machine-learning-meets-natural-language","title":"Machine Learning Meets Natural Language Processing -- The story so far","date":"2021-03-27","arxiv_id":"2104.10213","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-self-training-for-sentiment","title":"Unsupervised Self-Training for Sentiment Analysis of Code-Switched Data","date":"2021-03-27","arxiv_id":"2103.14797","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-practical-survey-on-faster-and-lighter","title":"A Practical Survey on Faster and Lighter Transformers","date":"2021-03-26","arxiv_id":"2103.14636","n_code_links":0,"syntology":null},{"paper":"/paper/automated-radiology-report-generation-using","slug":"automated-radiology-report-generation-using","title":"Automated radiology report generation using conditioned transformers","date":"2021-03-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"bart-based-semantic-correction-for-mandarin","title":"BART based semantic correction for Mandarin automatic speech recognition system","date":"2021-03-26","arxiv_id":"2104.05507","n_code_links":0,"syntology":null},{"paper":"/paper/gated-transformer-networks-for-multivariate","slug":"gated-transformer-networks-for-multivariate","title":"Gated Transformer Networks for Multivariate Time Series Classification","date":"2021-03-26","arxiv_id":"2103.14438","n_code_links":2,"syntology":null},{"paper":"/paper/leveraging-neural-representations-for","slug":"leveraging-neural-representations-for","title":"Leveraging pre-trained representations to improve access to untranscribed speech from endangered languages","date":"2021-03-26","arxiv_id":"2103.14583","n_code_links":1,"syntology":null},{"paper":"/paper/lifting-transformer-for-3d-human-pose","slug":"lifting-transformer-for-3d-human-pose","title":"Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation","date":"2021-03-26","arxiv_id":"2103.14304","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":1,"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":["Vegetebird/StridedTransformer-Pose3D"],"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":null,"slug":"understanding-robustness-of-transformers-for","title":"Understanding Robustness of Transformers for Image Classification","date":"2021-03-26","arxiv_id":"2103.14586","n_code_links":0,"syntology":null},{"paper":null,"slug":"abstracting-the-sampling-behaviour-of","title":"Abstracting the Sampling Behaviour of Stochastic Linear Periodic Event-Triggered Control Systems","date":"2021-03-25","arxiv_id":"2103.13839","n_code_links":0,"syntology":null},{"paper":"/paper/agentformer-agent-aware-transformers-for","slug":"agentformer-agent-aware-transformers-for","title":"AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting","date":"2021-03-25","arxiv_id":"2103.14023","n_code_links":2,"syntology":{"ran":14,"of":17,"n_ran_checked":12,"n_instrument":2,"unverified":3,"pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Khrylx/AgentFormer"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bert4so-neural-sentence-ordering-by-fine","title":"BERT4SO: Neural Sentence Ordering by Fine-tuning BERT","date":"2021-03-25","arxiv_id":"2103.13584","n_code_links":0,"syntology":null},{"paper":null,"slug":"bertinho-galician-bert-representations","title":"Bertinho: Galician BERT Representations","date":"2021-03-25","arxiv_id":"2103.13799","n_code_links":0,"syntology":null},{"paper":null,"slug":"k-xlnet-a-general-method-for-combining","title":"K-XLNet: A General Method for Combining Explicit Knowledge with Language Model Pretraining","date":"2021-03-25","arxiv_id":"2104.10649","n_code_links":0,"syntology":null},{"paper":"/paper/mask-attention-networks-rethinking-and","slug":"mask-attention-networks-rethinking-and","title":"Mask Attention Networks: Rethinking and Strengthen Transformer","date":"2021-03-25","arxiv_id":"2103.13597","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":null}},{"paper":"/paper/predicting-directionality-in-causal-relations","slug":"predicting-directionality-in-causal-relations","title":"Predicting Directionality in Causal Relations in Text","date":"2021-03-25","arxiv_id":"2103.13606","n_code_links":2,"syntology":null},{"paper":"/paper/swin-transformer-hierarchical-vision","slug":"swin-transformer-hierarchical-vision","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","date":"2021-03-25","arxiv_id":"2103.14030","n_code_links":80,"syntology":{"ran":123,"of":207,"n_ran_checked":82,"n_instrument":41,"unverified":84,"pointer_only":45,"phrase":"123 ran (of which 45 constructed an object rather than computing a result; 82 with no instrument failure: 5 honoured, 2 violated, 75 with no contract checked; 41 where Syntology's instrument failed) · 84 unverified","official":{"repos":["microsoft/Swin-Transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"visual-grounding-strategies-for-text-only","title":"Visual Grounding Strategies for Text-Only Natural Language Processing","date":"2021-03-25","arxiv_id":"2103.13942","n_code_links":0,"syntology":null},{"paper":"/paper/czert-czech-bert-like-model-for-language","slug":"czert-czech-bert-like-model-for-language","title":"Czert -- Czech BERT-like Model for Language Representation","date":"2021-03-24","arxiv_id":"2103.13031","n_code_links":1,"syntology":null},{"paper":"/paper/fastmoe-a-fast-mixture-of-expert-training","slug":"fastmoe-a-fast-mixture-of-expert-training","title":"FastMoE: A Fast Mixture-of-Expert Training System","date":"2021-03-24","arxiv_id":"2103.13262","n_code_links":3,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["davidmrau/mixture-of-experts","laekov/fastmoe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"low-resource-machine-translation-for-low","title":"Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages","date":"2021-03-24","arxiv_id":"2103.13272","n_code_links":0,"syntology":null},{"paper":"/paper/multi-view-3d-reconstruction-with-transformer","slug":"multi-view-3d-reconstruction-with-transformer","title":"Multi-view 3D Reconstruction with Transformer","date":"2021-03-24","arxiv_id":"2103.12957","n_code_links":0,"syntology":null},{"paper":"/paper/revamping-cross-modal-recipe-retrieval-with","slug":"revamping-cross-modal-recipe-retrieval-with","title":"Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning","date":"2021-03-24","arxiv_id":"2103.13061","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 3 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; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["amzn/image-to-recipe-transformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"thinking-aloud-dynamic-context-generation","title":"Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2","date":"2021-03-24","arxiv_id":"2103.13033","n_code_links":0,"syntology":null},{"paper":"/paper/vision-transformers-for-dense-prediction","slug":"vision-transformers-for-dense-prediction","title":"Vision Transformers for Dense Prediction","date":"2021-03-24","arxiv_id":"2103.13413","n_code_links":15,"syntology":{"ran":65,"of":116,"n_ran_checked":32,"n_instrument":33,"unverified":51,"pointer_only":15,"phrase":"65 ran (of which 19 constructed an object rather than computing a result; 32 with no instrument failure: 0 honoured, 0 violated, 32 with no contract checked; 33 where Syntology's instrument failed) · 51 unverified","official":null}},{"paper":"/paper/are-neural-language-models-good-plagiarists-a","slug":"are-neural-language-models-good-plagiarists-a","title":"Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection","date":"2021-03-23","arxiv_id":"2103.12450","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-hate-speech-with-gpt-3","slug":"detecting-hate-speech-with-gpt-3","title":"Detecting Hate Speech with GPT-3","date":"2021-03-23","arxiv_id":"2103.12407","n_code_links":2,"syntology":null},{"paper":null,"slug":"global-correlation-network-end-to-end-joint","title":"Global Correlation Network: End-to-End Joint Multi-Object Detection and Tracking","date":"2021-03-23","arxiv_id":"2103.12511","n_code_links":0,"syntology":null},{"paper":null,"slug":"repairing-pronouns-in-translation-with-bert","title":"Repairing Pronouns in Translation with BERT-Based Post-Editing","date":"2021-03-23","arxiv_id":"2103.12838","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-nlp-cookbook-modern-recipes-for","title":"The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures","date":"2021-03-23","arxiv_id":"2104.10640","n_code_links":0,"syntology":null},{"paper":null,"slug":"tmr-evaluating-ner-recall-on-tough-mentions","title":"TMR: Evaluating NER Recall on Tough Mentions","date":"2021-03-23","arxiv_id":"2103.12312","n_code_links":0,"syntology":null},{"paper":null,"slug":"variable-name-recovery-in-decompiled-binary","title":"Variable Name Recovery in Decompiled Binary Code using Constrained Masked Language Modeling","date":"2021-03-23","arxiv_id":"2103.12801","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-a-review-of-applications-in-natural","title":"BERT: A Review of Applications in Natural Language Processing and Understanding","date":"2021-03-22","arxiv_id":"2103.11943","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-the-gap-between-supervised","title":"Bridging the gap between supervised classification and unsupervised topic modelling for social-media assisted crisis management","date":"2021-03-22","arxiv_id":"2103.11835","n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-trainable-multi-instance-pose","slug":"end-to-end-trainable-multi-instance-pose","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","date":"2021-03-22","arxiv_id":"2103.12115","n_code_links":2,"syntology":{"ran":15,"of":18,"n_ran_checked":13,"n_instrument":2,"unverified":3,"pointer_only":8,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["amathislab/poet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/hybrid-model-for-patent-classification-using","slug":"hybrid-model-for-patent-classification-using","title":"PatentSBERTa: A Deep NLP based Hybrid Model for Patent Distance and Classification using Augmented SBERT","date":"2021-03-22","arxiv_id":"2103.11933","n_code_links":2,"syntology":null},{"paper":"/paper/identifying-machine-paraphrased-plagiarism","slug":"identifying-machine-paraphrased-plagiarism","title":"Identifying Machine-Paraphrased Plagiarism","date":"2021-03-22","arxiv_id":"2103.11909","n_code_links":2,"syntology":null},{"paper":"/paper/incorporating-convolution-designs-into-visual","slug":"incorporating-convolution-designs-into-visual","title":"Incorporating Convolution Designs into Visual Transformers","date":"2021-03-22","arxiv_id":"2103.11816","n_code_links":3,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"9 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 9 samples that ran constructed an object rather than computing a result","official":{"repos":["coeusguo/ceit"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/meta-detr-few-shot-object-detection-via","slug":"meta-detr-few-shot-object-detection-via","title":"Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation","date":"2021-03-22","arxiv_id":"2103.11731","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":2,"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":["ZhangGongjie/Meta-DETR"],"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/open-domain-question-answering-over-tables","slug":"open-domain-question-answering-over-tables","title":"Open Domain Question Answering over Tables via Dense Retrieval","date":"2021-03-22","arxiv_id":"2103.12011","n_code_links":1,"syntology":null},{"paper":"/paper/tiny-transformers-for-environmental-sound","slug":"tiny-transformers-for-environmental-sound","title":"Tiny Transformers for Environmental Sound Classification at the Edge","date":"2021-03-22","arxiv_id":"2103.12157","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-unsupervised-sampling-approach-for-image","title":"An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information","date":"2021-03-21","arxiv_id":"2104.02605","n_code_links":0,"syntology":null},{"paper":null,"slug":"maast-map-attention-with-semantic","title":"MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation","date":"2021-03-21","arxiv_id":"2103.11374","n_code_links":0,"syntology":null},{"paper":null,"slug":"namerec-highly-accurate-and-fine-grained","title":"NameRec*: Highly Accurate and Fine-grained Person Name Recognition","date":"2021-03-21","arxiv_id":"2103.11360","n_code_links":0,"syntology":null},{"paper":"/paper/non-autoregressive-translation-by-learning","slug":"non-autoregressive-translation-by-learning","title":"Non-Autoregressive Translation by Learning Target Categorical Codes","date":"2021-03-21","arxiv_id":"2103.11405","n_code_links":1,"syntology":null},{"paper":null,"slug":"paying-attention-to-activation-maps-in-camera","title":"Paying Attention to Activation Maps in Camera Pose Regression","date":"2021-03-21","arxiv_id":"2103.11477","n_code_links":0,"syntology":null},{"paper":"/paper/rosita-refined-bert-compression-with","slug":"rosita-refined-bert-compression-with","title":"ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques","date":"2021-03-21","arxiv_id":"2103.11367","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["llyx97/Rosita"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/paying-attention-to-multiscale-feature-maps","slug":"paying-attention-to-multiscale-feature-maps","title":"Attention-Based Multimodal Image Matching","date":"2021-03-20","arxiv_id":"2103.11247","n_code_links":1,"syntology":null},{"paper":null,"slug":"api2com-on-the-improvement-of-automatically","title":"API2Com: On the Improvement of Automatically Generated Code Comments Using API Documentations","date":"2021-03-19","arxiv_id":"2103.10668","n_code_links":0,"syntology":null},{"paper":"/paper/convit-improving-vision-transformers-with","slug":"convit-improving-vision-transformers-with","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","date":"2021-03-19","arxiv_id":"2103.10697","n_code_links":9,"syntology":null},{"paper":null,"slug":"cost-effective-deployment-of-bert-models-in","title":"Cost-effective Deployment of BERT Models in Serverless Environment","date":"2021-03-19","arxiv_id":"2103.10673","n_code_links":0,"syntology":null},{"paper":"/paper/hopper-multi-hop-transformer-for-1","slug":"hopper-multi-hop-transformer-for-1","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","date":"2021-03-19","arxiv_id":"2103.10574","n_code_links":1,"syntology":null},{"paper":"/paper/let-your-heart-speak-in-its-mother-tongue","slug":"let-your-heart-speak-in-its-mother-tongue","title":"Let Your Heart Speak in its Mother Tongue: Multilingual Captioning of Cardiac Signals","date":"2021-03-19","arxiv_id":"2103.11011","n_code_links":1,"syntology":null},{"paper":"/paper/muril-multilingual-representations-for-indian","slug":"muril-multilingual-representations-for-indian","title":"MuRIL: Multilingual Representations for Indian Languages","date":"2021-03-19","arxiv_id":"2103.10730","n_code_links":1,"syntology":null},{"paper":null,"slug":"play-the-shannon-game-with-language-models-a","title":"Play the Shannon Game With Language Models: A Human-Free Approach to Summary Evaluation","date":"2021-03-19","arxiv_id":"2103.10918","n_code_links":0,"syntology":null},{"paper":null,"slug":"transferable-model-for-shape-optimization","title":"Transferable Model for Shape Optimization subject to Physical Constraints","date":"2021-03-19","arxiv_id":"2103.10805","n_code_links":0,"syntology":null},{"paper":"/paper/all-nlp-tasks-are-generation-tasks-a-general","slug":"all-nlp-tasks-are-generation-tasks-a-general","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-03-18","arxiv_id":"2103.10360","n_code_links":8,"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":["THUDM/GLM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"contextual-biasing-of-language-models-for","title":"Contextual Biasing of Language Models for Speech Recognition in Goal-Oriented Conversational Agents","date":"2021-03-18","arxiv_id":"2103.10325","n_code_links":0,"syntology":null},{"paper":"/paper/danish-fungi-2020-not-just-another-image","slug":"danish-fungi-2020-not-just-another-image","title":"Danish Fungi 2020 -- Not Just Another Image Recognition Dataset","date":"2021-03-18","arxiv_id":"2103.10107","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-transformer-for-video-understanding","title":"Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training","date":"2021-03-18","arxiv_id":"2103.10043","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-understands-too","slug":"gpt-understands-too","title":"GPT Understands, Too","date":"2021-03-18","arxiv_id":"2103.10385","n_code_links":10,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["THUDM/P-tuning"],"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":["listed","official"]}}},{"paper":"/paper/model-extraction-and-adversarial","slug":"model-extraction-and-adversarial","title":"Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!","date":"2021-03-18","arxiv_id":"2103.10013","n_code_links":1,"syntology":null},{"paper":null,"slug":"spices-survey-papers-as-interactive","title":"SPICES: SURVEY PAPERS AS INTERACTIVE CHEATSHEET EMBEDDINGS","date":"2021-03-18","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"code-word-detection-in-fraud-investigations","title":"Code Word Detection in Fraud Investigations using a Deep-Learning Approach","date":"2021-03-17","arxiv_id":"2103.09606","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-role-of-images-for-analyzing-claims-in","slug":"on-the-role-of-images-for-analyzing-claims-in","title":"On the Role of Images for Analyzing Claims in Social Media","date":"2021-03-17","arxiv_id":"2103.09602","n_code_links":1,"syntology":null},{"paper":null,"slug":"sml-a-new-semantic-embedding-alignment","title":"SILT: Efficient transformer training for inter-lingual inference","date":"2021-03-17","arxiv_id":"2103.09635","n_code_links":0,"syntology":null},{"paper":"/paper/trans-svnet-accurate-phase-recognition-from","slug":"trans-svnet-accurate-phase-recognition-from","title":"Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer","date":"2021-03-17","arxiv_id":"2103.09712","n_code_links":1,"syntology":null},{"paper":"/paper/uniparma-semeval-2021-task-5-toxic-spans","slug":"uniparma-semeval-2021-task-5-toxic-spans","title":"UniParma at SemEval-2021 Task 5: Toxic Spans Detection Using CharacterBERT and Bag-of-Words Model","date":"2021-03-17","arxiv_id":"2103.09645","n_code_links":1,"syntology":null},{"paper":"/paper/you-only-look-one-level-feature","slug":"you-only-look-one-level-feature","title":"You Only Look One-level Feature","date":"2021-03-17","arxiv_id":"2103.09460","n_code_links":6,"syntology":null},{"paper":"/paper/dense-interaction-learning-for-video-based","slug":"dense-interaction-learning-for-video-based","title":"Dense Interaction Learning for Video-based Person Re-identification","date":"2021-03-16","arxiv_id":"2103.09013","n_code_links":0,"syntology":null},{"paper":null,"slug":"kgsynnet-a-novel-entity-synonyms-discovery","title":"KGSynNet: A Novel Entity Synonyms Discovery Framework with Knowledge Graph","date":"2021-03-16","arxiv_id":"2103.08893","n_code_links":0,"syntology":null},{"paper":"/paper/lightningdot-pre-training-visual-semantic","slug":"lightningdot-pre-training-visual-semantic","title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","date":"2021-03-16","arxiv_id":"2103.08784","n_code_links":2,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["intersun/LightningDOT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"record_sha256":"bc8976b6dd61d62ed40dd270155b7a867daed8439c7e69a79ebbd97d4e29ee8c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}