{"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/position-wise-feed-forward-layer/papers/123","list_of":"/method/position-wise-feed-forward-layer","method":"Position-Wise Feed-Forward 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":123,"pages_in_order":139,"rows_per_page":100,"rows":[12201,12300],"of":13895,"counts":{"archive_papers_tagged":13895,"with_a_code_link":6514,"where_syntology_ran_a_sample":2229,"not_listed_spam_title":0,"listed":13895,"listed_where_code_ran":2229,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1902,"every_run_a_failure_of_syntologys_instrument":327,"listed_with_a_run_with_no_instrument_failure":1902,"listed_every_run_a_failure_of_syntologys_instrument":327,"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/position-wise-feed-forward-layer","prev":"/method/position-wise-feed-forward-layer/papers/122","next":"/method/position-wise-feed-forward-layer/papers/124","papers":[{"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":"/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/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":"/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":"/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":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":"/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/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/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":"/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/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/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":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":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":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":"/paper/unetr-transformers-for-3d-medical-image","slug":"unetr-transformers-for-3d-medical-image","title":"UNETR: Transformers for 3D Medical Image Segmentation","date":"2021-03-18","arxiv_id":"2103.10504","n_code_links":10,"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/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":"/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"]}}},{"paper":null,"slug":"knowledge-driven-description-synthesis-for","title":"Knowledge driven Description Synthesis for Floor Plan Interpretation","date":"2021-03-15","arxiv_id":"2103.08298","n_code_links":0,"syntology":null},{"paper":"/paper/improving-code-summarization-with-block-wise","slug":"improving-code-summarization-with-block-wise","title":"Improving Code Summarization with Block-wise Abstract Syntax Tree Splitting","date":"2021-03-14","arxiv_id":"2103.07845","n_code_links":1,"syntology":null},{"paper":null,"slug":"semvlp-vision-language-pre-training-by-1","title":"SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels","date":"2021-03-14","arxiv_id":"2103.07829","n_code_links":0,"syntology":null},{"paper":null,"slug":"embedding-calibration-for-music-semantic","title":"Optimal Embedding Calibration for Symbolic Music Similarity","date":"2021-03-13","arxiv_id":"2103.07656","n_code_links":0,"syntology":null},{"paper":null,"slug":"bilingual-dictionary-based-language-model","title":"Bilingual Dictionary-based Language Model Pretraining for Neural Machine Translation","date":"2021-03-12","arxiv_id":"2103.07040","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-architecture-search-based-on-cartesian","title":"Neural Architecture Search based on Cartesian Genetic Programming Coding Method","date":"2021-03-12","arxiv_id":"2103.07173","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-the-behavior-of-dealers-in-over","title":"Predicting the Behavior of Dealers in Over-The-Counter Corporate Bond Markets","date":"2021-03-12","arxiv_id":"2103.09098","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequential-random-network-for-fine-grained","title":"Sequential Random Network for Fine-grained Image Classification","date":"2021-03-12","arxiv_id":"2103.07230","n_code_links":0,"syntology":null},{"paper":null,"slug":"severity-quantification-and-lesion","title":"Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer","date":"2021-03-12","arxiv_id":"2103.07062","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-transformer-for-covid-19-cxr-diagnosis","title":"Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus","date":"2021-03-12","arxiv_id":"2103.07055","n_code_links":0,"syntology":null},{"paper":"/paper/canine-pre-training-an-efficient-tokenization","slug":"canine-pre-training-an-efficient-tokenization","title":"CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation","date":"2021-03-11","arxiv_id":"2103.06874","n_code_links":6,"syntology":null},{"paper":null,"slug":"continuous-3d-multi-channel-sign-language","title":"Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks","date":"2021-03-11","arxiv_id":"2103.06982","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-improving-deep-learning-trace-analysis","title":"On Improving Deep Learning Trace Analysis with System Call Arguments","date":"2021-03-11","arxiv_id":"2103.06915","n_code_links":0,"syntology":null},{"paper":"/paper/unknown-object-segmentation-from-stereo","slug":"unknown-object-segmentation-from-stereo","title":"Unknown Object Segmentation from Stereo Images","date":"2021-03-11","arxiv_id":"2103.06796","n_code_links":2,"syntology":null},{"paper":"/paper/cuad-an-expert-annotated-nlp-dataset-for","slug":"cuad-an-expert-annotated-nlp-dataset-for","title":"CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review","date":"2021-03-10","arxiv_id":"2103.06268","n_code_links":2,"syntology":null},{"paper":"/paper/pretrained-transformers-as-universal","slug":"pretrained-transformers-as-universal","title":"Pretrained Transformers as Universal Computation Engines","date":"2021-03-09","arxiv_id":"2103.05247","n_code_links":4,"syntology":null},{"paper":"/paper/end-to-end-human-object-interaction-detection","slug":"end-to-end-human-object-interaction-detection","title":"End-to-End Human Object Interaction Detection with HOI Transformer","date":"2021-03-08","arxiv_id":"2103.04503","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["bbepoch/HoiTransformer"],"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":"mtlhealth-a-deep-learning-system-for","title":"MTLHealth: A Deep Learning System for Detecting Disturbing Content in Student Essays","date":"2021-03-07","arxiv_id":"2103.04290","n_code_links":0,"syntology":null},{"paper":"/paper/syntax-bert-improving-pre-trained","slug":"syntax-bert-improving-pre-trained","title":"Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees","date":"2021-03-07","arxiv_id":"2103.04350","n_code_links":1,"syntology":null},{"paper":"/paper/transbts-multimodal-brain-tumor-segmentation","slug":"transbts-multimodal-brain-tumor-segmentation","title":"TransBTS: Multimodal Brain Tumor Segmentation Using Transformer","date":"2021-03-07","arxiv_id":"2103.04430","n_code_links":3,"syntology":null},{"paper":"/paper/investigating-on-incorporating-pretrained-and","slug":"investigating-on-incorporating-pretrained-and","title":"Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech","date":"2021-03-06","arxiv_id":"2103.04088","n_code_links":1,"syntology":null},{"paper":"/paper/attention-is-not-all-you-need-pure-attention","slug":"attention-is-not-all-you-need-pure-attention","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","date":"2021-03-05","arxiv_id":"2103.03404","n_code_links":1,"syntology":null},{"paper":null,"slug":"hierarchical-transformer-for-multilingual","title":"Hierarchical Transformer for Multilingual Machine Translation","date":"2021-03-05","arxiv_id":"2103.03589","n_code_links":0,"syntology":null},{"paper":"/paper/iot-instance-wise-layer-reordering-for-1","slug":"iot-instance-wise-layer-reordering-for-1","title":"IOT: Instance-wise Layer Reordering for Transformer Structures","date":"2021-03-05","arxiv_id":"2103.03457","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["instance-wise-ordered-transformer/IOT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/measuring-mathematical-problem-solving-with","slug":"measuring-mathematical-problem-solving-with","title":"Measuring Mathematical Problem Solving With the MATH Dataset","date":"2021-03-05","arxiv_id":"2103.03874","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":1,"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":["hendrycks/math"],"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":["official","unlocated"]}}},{"paper":"/paper/spectr-spectral-transformer-for-hyperspectral","slug":"spectr-spectral-transformer-for-hyperspectral","title":"SpecTr: Spectral Transformer for Hyperspectral Pathology Image Segmentation","date":"2021-03-05","arxiv_id":"2103.03604","n_code_links":1,"syntology":null},{"paper":"/paper/cotr-efficiently-bridging-cnn-and-transformer","slug":"cotr-efficiently-bridging-cnn-and-transformer","title":"CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation","date":"2021-03-04","arxiv_id":"2103.03024","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-acoustic-modelling-for-phone","title":"End-to-end acoustic modelling for phone recognition of young readers","date":"2021-03-04","arxiv_id":"2103.02899","n_code_links":0,"syntology":null},{"paper":"/paper/the-transformer-network-for-the-traveling","slug":"the-transformer-network-for-the-traveling","title":"The Transformer Network for the Traveling Salesman Problem","date":"2021-03-04","arxiv_id":"2103.03012","n_code_links":1,"syntology":null},{"paper":null,"slug":"university-of-copenhagen-participation-in","title":"University of Copenhagen Participation in TREC Health Misinformation Track 2020","date":"2021-03-03","arxiv_id":"2103.02462","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hint-from-arithmetic-on-systematic","title":"A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics","date":"2021-03-02","arxiv_id":"2103.01403","n_code_links":0,"syntology":null},{"paper":null,"slug":"dual-reinforcement-based-specification","title":"Dual Reinforcement-Based Specification Generation for Image De-Rendering","date":"2021-03-02","arxiv_id":"2103.01867","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-product-description-generation-via","title":"Probing Product Description Generation via Posterior Distillation","date":"2021-03-02","arxiv_id":"2103.01594","n_code_links":0,"syntology":null},{"paper":null,"slug":"crossmap-transformer-a-crossmodal-masked-path","title":"CrossMap Transformer: A Crossmodal Masked Path Transformer Using Double Back-Translation for Vision-and-Language Navigation","date":"2021-03-01","arxiv_id":"2103.00852","n_code_links":0,"syntology":null},{"paper":"/paper/generative-chemical-transformer-attention","slug":"generative-chemical-transformer-attention","title":"Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention","date":"2021-02-27","arxiv_id":"2103.00213","n_code_links":2,"syntology":null},{"paper":"/paper/transformer-in-transformer","slug":"transformer-in-transformer","title":"Transformer in Transformer","date":"2021-02-27","arxiv_id":"2103.00112","n_code_links":12,"syntology":{"ran":16,"of":24,"n_ran_checked":15,"n_instrument":1,"unverified":8,"pointer_only":5,"phrase":"16 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["huawei-noah/CV-backbones"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"transformers-with-competitive-ensembles-of-1","title":"Transformers with Competitive Ensembles of Independent Mechanisms","date":"2021-02-27","arxiv_id":"2103.00336","n_code_links":0,"syntology":null},{"paper":null,"slug":"lazyformer-self-attention-with-lazy-update","title":"LazyFormer: Self Attention with Lazy Update","date":"2021-02-25","arxiv_id":"2102.12702","n_code_links":0,"syntology":null},{"paper":"/paper/let-linguistic-knowledge-enhanced-graph","slug":"let-linguistic-knowledge-enhanced-graph","title":"LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching","date":"2021-02-25","arxiv_id":"2102.12671","n_code_links":1,"syntology":null},{"paper":null,"slug":"mixspeech-data-augmentation-for-low-resource","title":"MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition","date":"2021-02-25","arxiv_id":"2102.12664","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-universal-language-model-to-downstream","title":"From Universal Language Model to Downstream Task: Improving RoBERTa-Based Vietnamese Hate Speech Detection","date":"2021-02-24","arxiv_id":"2102.12162","n_code_links":0,"syntology":null},{"paper":"/paper/pyramid-vision-transformer-a-versatile","slug":"pyramid-vision-transformer-a-versatile","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","date":"2021-02-24","arxiv_id":"2102.12122","n_code_links":11,"syntology":{"ran":22,"of":30,"n_ran_checked":18,"n_instrument":4,"unverified":8,"pointer_only":1,"phrase":"22 ran (of which 16 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 0 violated, 16 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","official":{"repos":["whai362/PVT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/when-attention-meets-fast-recurrence-training","slug":"when-attention-meets-fast-recurrence-training","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","date":"2021-02-24","arxiv_id":"2102.12459","n_code_links":1,"syntology":null},{"paper":"/paper/accurate-learning-of-graph-representations-1","slug":"accurate-learning-of-graph-representations-1","title":"Accurate Learning of Graph Representations with Graph Multiset Pooling","date":"2021-02-23","arxiv_id":"2102.11533","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["JinheonBaek/GMT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deep-deformation-detail-synthesis-for-thin","title":"Deep Deformation Detail Synthesis for Thin Shell Models","date":"2021-02-23","arxiv_id":"2102.11541","n_code_links":0,"syntology":null},{"paper":"/paper/do-transformer-modifications-transfer-across","slug":"do-transformer-modifications-transfer-across","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","date":"2021-02-23","arxiv_id":"2102.11972","n_code_links":1,"syntology":null},{"paper":"/paper/deepfake-video-detection-using-convolutional","slug":"deepfake-video-detection-using-convolutional","title":"Deepfake Video Detection Using Convolutional Vision Transformer","date":"2021-02-22","arxiv_id":"2102.11126","n_code_links":1,"syntology":null},{"paper":null,"slug":"determination-of-fault-location-in","title":"Determination of Fault Location in Transmission Lines with Image Processing and Artificial Neural Networks","date":"2021-02-22","arxiv_id":"2102.11073","n_code_links":0,"syntology":null},{"paper":"/paper/do-we-really-need-explicit-position-encodings","slug":"do-we-really-need-explicit-position-encodings","title":"Conditional Positional Encodings for Vision Transformers","date":"2021-02-22","arxiv_id":"2102.10882","n_code_links":2,"syntology":null},{"paper":null,"slug":"position-information-in-transformers-an","title":"Position Information in Transformers: An Overview","date":"2021-02-22","arxiv_id":"2102.11090","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-is-all-you-need-multimodal","slug":"transformer-is-all-you-need-multimodal","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","date":"2021-02-22","arxiv_id":"2102.10772","n_code_links":1,"syntology":null},{"paper":"/paper/medical-transformer-gated-axial-attention-for","slug":"medical-transformer-gated-axial-attention-for","title":"Medical Transformer: Gated Axial-Attention for Medical Image Segmentation","date":"2021-02-21","arxiv_id":"2102.10662","n_code_links":2,"syntology":null},{"paper":null,"slug":"multilingual-answer-sentence-reranking-via","title":"Multilingual Answer Sentence Reranking via Automatically Translated Data","date":"2021-02-20","arxiv_id":"2102.10250","n_code_links":0,"syntology":null},{"paper":"/paper/towards-accurate-and-compact-architectures","slug":"towards-accurate-and-compact-architectures","title":"Towards Accurate and Compact Architectures via Neural Architecture Transformer","date":"2021-02-20","arxiv_id":"2102.10301","n_code_links":2,"syntology":null},{"paper":null,"slug":"dialect-identification-in-nuanced-arabic","title":"Dialect Identification in Nuanced Arabic Tweets Using Farasa Segmentation and AraBERT","date":"2021-02-19","arxiv_id":"2102.09749","n_code_links":0,"syntology":null},{"paper":"/paper/latent-variable-nested-set-transformers","slug":"latent-variable-nested-set-transformers","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","date":"2021-02-19","arxiv_id":"2104.00563","n_code_links":2,"syntology":{"ran":11,"of":17,"n_ran_checked":10,"n_instrument":1,"unverified":6,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["roggirg/AutoBots"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/going-full-tilt-boogie-on-document","slug":"going-full-tilt-boogie-on-document","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","date":"2021-02-18","arxiv_id":"2102.09550","n_code_links":1,"syntology":null},{"paper":"/paper/quiz-style-question-generation-for-news","slug":"quiz-style-question-generation-for-news","title":"Quiz-Style Question Generation for News Stories","date":"2021-02-18","arxiv_id":"2102.09094","n_code_links":2,"syntology":null},{"paper":"/paper/beyond-fully-connected-layers-with","slug":"beyond-fully-connected-layers-with","title":"Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters","date":"2021-02-17","arxiv_id":"2102.08597","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["astonzhang/Parameterization-of-Hypercomplex-Multiplications"],"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/gradinit-learning-to-initialize-neural","slug":"gradinit-learning-to-initialize-neural","title":"GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training","date":"2021-02-16","arxiv_id":"2102.08098","n_code_links":2,"syntology":{"ran":7,"of":13,"n_ran_checked":4,"n_instrument":3,"unverified":6,"pointer_only":12,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","official":{"repos":["zhuchen03/gradinit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/revisiting-language-encoding-in-learning","slug":"revisiting-language-encoding-in-learning","title":"Revisiting Language Encoding in Learning Multilingual Representations","date":"2021-02-16","arxiv_id":"2102.08357","n_code_links":1,"syntology":null},{"paper":"/paper/translational-equivariance-in-kernelizable","slug":"translational-equivariance-in-kernelizable","title":"Translational Equivariance in Kernelizable Attention","date":"2021-02-15","arxiv_id":"2102.07680","n_code_links":1,"syntology":null},{"paper":null,"slug":"dancing-along-battery-enabling-transformer","title":"Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices","date":"2021-02-12","arxiv_id":"2102.06336","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-zero-shot-neural-machine","title":"Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders","date":"2021-02-12","arxiv_id":"2102.06578","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-inference-performance-of","title":"Optimizing Inference Performance of Transformers on CPUs","date":"2021-02-12","arxiv_id":"2102.06621","n_code_links":0,"syntology":null}],"record_sha256":"e745d44806ad4ffdbab353cc42c94f156195b48f35c82632ece5838a84b81c67","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}