{"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/transformer/papers/121","list_of":"/method/transformer","method":"Transformer","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":121,"pages_in_order":140,"rows_per_page":100,"rows":[12001,12100],"of":13999,"counts":{"archive_papers_tagged":13999,"with_a_code_link":6572,"where_syntology_ran_a_sample":2248,"not_listed_spam_title":0,"listed":13999,"listed_where_code_ran":2248,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1919,"every_run_a_failure_of_syntologys_instrument":329,"listed_with_a_run_with_no_instrument_failure":1919,"listed_every_run_a_failure_of_syntologys_instrument":329,"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/transformer","prev":"/method/transformer/papers/120","next":"/method/transformer/papers/122","papers":[{"paper":"/paper/video-super-resolution-transformer","slug":"video-super-resolution-transformer","title":"Video Super-Resolution Transformer","date":"2021-06-12","arxiv_id":"2106.06847","n_code_links":1,"syntology":null},{"paper":"/paper/break-it-fix-it-unsupervised-learning-for","slug":"break-it-fix-it-unsupervised-learning-for","title":"Break-It-Fix-It: Unsupervised Learning for Program Repair","date":"2021-06-11","arxiv_id":"2106.06600","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["michiyasunaga/bifi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/graph-transformer-networks-learning-meta-path","slug":"graph-transformer-networks-learning-meta-path","title":"Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNs","date":"2021-06-11","arxiv_id":"2106.06218","n_code_links":1,"syntology":null},{"paper":"/paper/isolated-sign-recognition-from-rgb-video","slug":"isolated-sign-recognition-from-rgb-video","title":"Isolated Sign Recognition from RGB Video using Pose Flow and Self-Attention","date":"2021-06-11","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/mltr-multi-label-classification-with","slug":"mltr-multi-label-classification-with","title":"MlTr: Multi-label Classification with Transformer","date":"2021-06-11","arxiv_id":"2106.06195","n_code_links":1,"syntology":null},{"paper":"/paper/modeling-sequences-as-distributions-with","slug":"modeling-sequences-as-distributions-with","title":"Modeling Sequences as Distributions with Uncertainty for Sequential Recommendation","date":"2021-06-11","arxiv_id":"2106.06165","n_code_links":1,"syntology":null},{"paper":"/paper/neural-symbolic-regression-that-scales","slug":"neural-symbolic-regression-that-scales","title":"Neural Symbolic Regression that Scales","date":"2021-06-11","arxiv_id":"2106.06427","n_code_links":2,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"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) · 3 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["SymposiumOrganization/NeuralSymbolicRegressionThatScales"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"vit-inception-gan-for-image-colourising","title":"ViT-Inception-GAN for Image Colourising","date":"2021-06-11","arxiv_id":"2106.06321","n_code_links":0,"syntology":null},{"paper":"/paper/cat-cross-attention-in-vision-transformer","slug":"cat-cross-attention-in-vision-transformer","title":"CAT: Cross Attention in Vision Transformer","date":"2021-06-10","arxiv_id":"2106.05786","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["linhezheng19/CAT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/convolutions-and-self-attention-re","slug":"convolutions-and-self-attention-re","title":"Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models","date":"2021-06-10","arxiv_id":"2106.05505","n_code_links":1,"syntology":null},{"paper":null,"slug":"groupbert-enhanced-transformer-architecture","title":"GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures","date":"2021-06-10","arxiv_id":"2106.05822","n_code_links":0,"syntology":null},{"paper":null,"slug":"mst-masked-self-supervised-transformer-for","title":"MST: Masked Self-Supervised Transformer for Visual Representation","date":"2021-06-10","arxiv_id":"2106.05656","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-vision-with-sparse-mixture-of-experts","slug":"scaling-vision-with-sparse-mixture-of-experts","title":"Scaling Vision with Sparse Mixture of Experts","date":"2021-06-10","arxiv_id":"2106.05974","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/vmoe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/space-time-mixing-attention-for-video","slug":"space-time-mixing-attention-for-video","title":"Space-time Mixing Attention for Video Transformer","date":"2021-06-10","arxiv_id":"2106.05968","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["1adrianb/video-transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/task-aware-multi-task-learning-for-speech-to","slug":"task-aware-multi-task-learning-for-speech-to","title":"TASK AWARE MULTI-TASK LEARNING FOR SPEECH TO TEXT TASKS","date":"2021-06-10","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/do-transformers-really-perform-bad-for-graph","slug":"do-transformers-really-perform-bad-for-graph","title":"Do Transformers Really Perform Bad for Graph Representation?","date":"2021-06-09","arxiv_id":"2106.05234","n_code_links":5,"syntology":null},{"paper":"/paper/instantaneous-grammatical-error-correction","slug":"instantaneous-grammatical-error-correction","title":"Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding","date":"2021-06-09","arxiv_id":"2106.04970","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":5,"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) · 2 unverified","official":{"repos":["AutoTemp/Shallow-Aggressive-Decoding"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"realtrans-end-to-end-simultaneous-speech","title":"RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer","date":"2021-06-09","arxiv_id":"2106.04833","n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-3d-hand-object-poses","slug":"semi-supervised-3d-hand-object-poses","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","date":"2021-06-09","arxiv_id":"2106.05266","n_code_links":1,"syntology":null},{"paper":"/paper/a-survey-of-transformers","slug":"a-survey-of-transformers","title":"A Survey of Transformers","date":"2021-06-08","arxiv_id":"2106.04554","n_code_links":2,"syntology":null},{"paper":"/paper/demystifying-local-vision-transformer-sparse","slug":"demystifying-local-vision-transformer-sparse","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","date":"2021-06-08","arxiv_id":"2106.04263","n_code_links":1,"syntology":{"ran":11,"of":16,"n_ran_checked":11,"n_instrument":0,"unverified":5,"pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["atten4vis/demystifylocalvit"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/detreg-unsupervised-pretraining-with-region","slug":"detreg-unsupervised-pretraining-with-region","title":"DETReg: Unsupervised Pretraining with Region Priors for Object Detection","date":"2021-06-08","arxiv_id":"2106.04550","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["amirbar/detreg"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/diverse-part-discovery-occluded-person-re","slug":"diverse-part-discovery-occluded-person-re","title":"Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer","date":"2021-06-08","arxiv_id":"2106.04095","n_code_links":0,"syntology":null},{"paper":"/paper/fully-transformer-networks-for-semantic","slug":"fully-transformer-networks-for-semantic","title":"Fully Transformer Networks for Semantic Image Segmentation","date":"2021-06-08","arxiv_id":"2106.04108","n_code_links":1,"syntology":null},{"paper":null,"slug":"hash-layers-for-large-sparse-models","title":"Hash Layers For Large Sparse Models","date":"2021-06-08","arxiv_id":"2106.04426","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-lack-of-robust-interpretability-of","title":"On the Lack of Robust Interpretability of Neural Text Classifiers","date":"2021-06-08","arxiv_id":"2106.04631","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-vision-transformers","slug":"scaling-vision-transformers","title":"Scaling Vision Transformers","date":"2021-06-08","arxiv_id":"2106.04560","n_code_links":1,"syntology":null},{"paper":null,"slug":"speech-bert-embedding-for-improving-prosody","title":"Speech BERT Embedding For Improving Prosody in Neural TTS","date":"2021-06-08","arxiv_id":"2106.04312","n_code_links":0,"syntology":null},{"paper":"/paper/staircase-attention-for-recurrent-processing","slug":"staircase-attention-for-recurrent-processing","title":"Staircase Attention for Recurrent Processing of Sequences","date":"2021-06-08","arxiv_id":"2106.04279","n_code_links":1,"syntology":null},{"paper":"/paper/attention-temperature-matters-in-abstractive","slug":"attention-temperature-matters-in-abstractive","title":"Attention Temperature Matters in Abstractive Summarization Distillation","date":"2021-06-07","arxiv_id":"2106.03441","n_code_links":1,"syntology":null},{"paper":"/paper/person-re-identification-with-a-locally-aware","slug":"person-re-identification-with-a-locally-aware","title":"Person Re-Identification with a Locally Aware Transformer","date":"2021-06-07","arxiv_id":"2106.03720","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":["SiddhantKapil/LA-Transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"progressive-open-domain-response-generation","title":"Progressive Open-Domain Response Generation with Multiple Controllable Attributes","date":"2021-06-07","arxiv_id":"2106.14614","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-graph-transformers-with-spectral","slug":"rethinking-graph-transformers-with-spectral","title":"Rethinking Graph Transformers with Spectral Attention","date":"2021-06-07","arxiv_id":"2106.03893","n_code_links":1,"syntology":null},{"paper":null,"slug":"reveal-of-vision-transformers-robustness","title":"Reveal of Vision Transformers Robustness against Adversarial Attacks","date":"2021-06-07","arxiv_id":"2106.03734","n_code_links":0,"syntology":null},{"paper":"/paper/shuffle-transformer-rethinking-spatial","slug":"shuffle-transformer-rethinking-spatial","title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","date":"2021-06-07","arxiv_id":"2106.03650","n_code_links":4,"syntology":{"ran":10,"of":12,"n_ran_checked":8,"n_instrument":2,"unverified":2,"pointer_only":6,"phrase":"10 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; 2 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/visual-transformer-for-task-aware-active","slug":"visual-transformer-for-task-aware-active","title":"Visual Transformer for Task-aware Active Learning","date":"2021-06-07","arxiv_id":"2106.03801","n_code_links":1,"syntology":null},{"paper":"/paper/vitae-vision-transformer-advanced-by","slug":"vitae-vision-transformer-advanced-by","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","date":"2021-06-07","arxiv_id":"2106.03348","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Annbless/ViTAE"],"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":["unlocated"]}}},{"paper":"/paper/attend-and-select-a-segment-attention-based","slug":"attend-and-select-a-segment-attention-based","title":"Attend and select: A segment selective transformer for microblog hashtag generation","date":"2021-06-06","arxiv_id":"2106.03151","n_code_links":1,"syntology":null},{"paper":"/paper/cape-encoding-relative-positions-with","slug":"cape-encoding-relative-positions-with","title":"CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings","date":"2021-06-06","arxiv_id":"2106.03143","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-source-channel-coding-for-sentence","title":"Deep Source-Channel Coding for Sentence Semantic Transmission with HARQ","date":"2021-06-06","arxiv_id":"2106.03009","n_code_links":0,"syntology":null},{"paper":null,"slug":"oriented-object-detection-with-transformer","title":"Oriented Object Detection with Transformer","date":"2021-06-06","arxiv_id":"2106.03146","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-training-from-scratch-for-object","slug":"rethinking-training-from-scratch-for-object","title":"Rethinking Training from Scratch for Object Detection","date":"2021-06-06","arxiv_id":"2106.03112","n_code_links":1,"syntology":null},{"paper":"/paper/uformer-a-general-u-shaped-transformer-for","slug":"uformer-a-general-u-shaped-transformer-for","title":"Uformer: A General U-Shaped Transformer for Image Restoration","date":"2021-06-06","arxiv_id":"2106.03106","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ZhendongWang6/Uformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/learnable-fourier-features-for-multi","slug":"learnable-fourier-features-for-multi","title":"Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding","date":"2021-06-05","arxiv_id":"2106.02795","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 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":null}},{"paper":"/paper/associating-objects-with-transformers-for","slug":"associating-objects-with-transformers-for","title":"Associating Objects with Transformers for Video Object Segmentation","date":"2021-06-04","arxiv_id":"2106.02638","n_code_links":2,"syntology":null},{"paper":"/paper/few-shot-segmentation-via-cycle-consistent","slug":"few-shot-segmentation-via-cycle-consistent","title":"Few-Shot Segmentation via Cycle-Consistent Transformer","date":"2021-06-04","arxiv_id":"2106.02320","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["GengDavid/CyCTR"],"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/glance-and-gaze-vision-transformer","slug":"glance-and-gaze-vision-transformer","title":"Glance-and-Gaze Vision Transformer","date":"2021-06-04","arxiv_id":"2106.02277","n_code_links":1,"syntology":null},{"paper":null,"slug":"scalable-transformers-for-neural-machine-1","title":"Scalable Transformers for Neural Machine Translation","date":"2021-06-04","arxiv_id":"2106.02242","n_code_links":0,"syntology":null},{"paper":"/paper/the-image-local-autoregressive-transformer","slug":"the-image-local-autoregressive-transformer","title":"The Image Local Autoregressive Transformer","date":"2021-06-04","arxiv_id":"2106.02514","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comparison-for-anti-noise-robustness-of","title":"A Comparison for Anti-noise Robustness of Deep Learning Classification Methods on a Tiny Object Image Dataset: from Convolutional Neural Network to Visual Transformer and Performer","date":"2021-06-03","arxiv_id":"2106.01927","n_code_links":0,"syntology":null},{"paper":"/paper/an-improved-model-for-voicing-silent-speech","slug":"an-improved-model-for-voicing-silent-speech","title":"An Improved Model for Voicing Silent Speech","date":"2021-06-03","arxiv_id":"2106.01933","n_code_links":1,"syntology":null},{"paper":"/paper/anticipative-video-transformer","slug":"anticipative-video-transformer","title":"Anticipative Video Transformer","date":"2021-06-03","arxiv_id":"2106.02036","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/AVT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"defending-democracy-using-deep-learning-to","title":"Defending Democracy: Using Deep Learning to Identify and Prevent Misinformation","date":"2021-06-03","arxiv_id":"2106.02607","n_code_links":0,"syntology":null},{"paper":null,"slug":"e2e-vlp-end-to-end-vision-language-pre","title":"E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning","date":"2021-06-03","arxiv_id":"2106.01804","n_code_links":0,"syntology":null},{"paper":"/paper/protores-proto-residual-architecture-for-deep","slug":"protores-proto-residual-architecture-for-deep","title":"ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics","date":"2021-06-03","arxiv_id":"2106.01981","n_code_links":1,"syntology":null},{"paper":"/paper/reinforcement-learning-as-one-big-sequence","slug":"reinforcement-learning-as-one-big-sequence","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","date":"2021-06-03","arxiv_id":"2106.02039","n_code_links":2,"syntology":{"ran":23,"of":28,"n_ran_checked":22,"n_instrument":1,"unverified":5,"pointer_only":1,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["JannerM/trajectory-transformer"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/tail-to-tail-non-autoregressive-sequence","slug":"tail-to-tail-non-autoregressive-sequence","title":"Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction","date":"2021-06-03","arxiv_id":"2106.01609","n_code_links":1,"syntology":null},{"paper":"/paper/container-context-aggregation-network","slug":"container-context-aggregation-network","title":"Container: Context Aggregation Network","date":"2021-06-02","arxiv_id":"2106.01401","n_code_links":4,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["allenai/container","gaopengcuhk/Container"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/decision-transformer-reinforcement-learning","slug":"decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","arxiv_id":"2106.01345","n_code_links":20,"syntology":{"ran":17,"of":26,"n_ran_checked":13,"n_instrument":4,"unverified":9,"pointer_only":8,"phrase":"17 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified","official":{"repos":["kzl/decision-transformer"],"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/enriching-transformers-with-structured-tensor","slug":"enriching-transformers-with-structured-tensor","title":"Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization","date":"2021-06-02","arxiv_id":"2106.01317","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jiangycTarheel/TPT-Summ"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hi-transformer-hierarchical-interactive","title":"Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling","date":"2021-06-02","arxiv_id":"2106.01040","n_code_links":0,"syntology":null},{"paper":"/paper/irene-interpretable-energy-prediction-for","slug":"irene-interpretable-energy-prediction-for","title":"IrEne: Interpretable Energy Prediction for Transformers","date":"2021-06-02","arxiv_id":"2106.01199","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 2 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":["StonyBrookNLP/irene"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"solving-arithmetic-word-problems-with","title":"Solving Arithmetic Word Problems with Transformers and Preprocessing of Problem Text","date":"2021-06-02","arxiv_id":"2106.00893","n_code_links":0,"syntology":null},{"paper":"/paper/sygns-a-systematic-generalization-testbed","slug":"sygns-a-systematic-generalization-testbed","title":"SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics","date":"2021-06-02","arxiv_id":"2106.01077","n_code_links":1,"syntology":null},{"paper":"/paper/topic-driven-and-knowledge-aware-transformer","slug":"topic-driven-and-knowledge-aware-transformer","title":"Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection","date":"2021-06-02","arxiv_id":"2106.01071","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-are-deep-infinite-dimensional-1","title":"Transformers are Deep Infinite-Dimensional Non-Mercer Binary Kernel Machines","date":"2021-06-02","arxiv_id":"2106.01506","n_code_links":0,"syntology":null},{"paper":"/paper/transmil-transformer-based-correlated","slug":"transmil-transformer-based-correlated","title":"TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification","date":"2021-06-02","arxiv_id":"2106.00908","n_code_links":3,"syntology":null},{"paper":null,"slug":"ad-headline-generation-using-self-critical","title":"Ad Headline Generation using Self-Critical Masked Language Model","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-test-sets-with-item-response-theory","title":"Comparing Test Sets with Item Response Theory","date":"2021-06-01","arxiv_id":"2106.00840","n_code_links":0,"syntology":null},{"paper":null,"slug":"contextual-domain-classification-with","title":"Contextual Domain Classification with Temporal Representations","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cooperative-multi-agent-transfer-learning","title":"Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment","date":"2021-06-01","arxiv_id":"2106.00517","n_code_links":0,"syntology":null},{"paper":"/paper/cultural-and-geographical-influences-on-image","slug":"cultural-and-geographical-influences-on-image","title":"Cultural and Geographical Influences on Image Translatability of Words across Languages","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/efficiently-summarizing-text-and-graph","slug":"efficiently-summarizing-text-and-graph","title":"Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-hop-transformer-for-document-level","title":"Multi-Hop Transformer for Document-Level Machine Translation","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-vehicles-trajectories-in-urban","title":"Predicting Vehicles Trajectories in Urban Scenarios with Transformer Networks and Augmented Information","date":"2021-06-01","arxiv_id":"2106.00559","n_code_links":0,"syntology":null},{"paper":"/paper/supervised-neural-clustering-via-latent","slug":"supervised-neural-clustering-via-latent","title":"Supervised Neural Clustering via Latent Structured Output Learning: Application to Question Intents","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"thg-transformer-with-hyperbolic-geometry","title":"THG: Transformer with Hyperbolic Geometry","date":"2021-06-01","arxiv_id":"2106.07350","n_code_links":0,"syntology":null},{"paper":"/paper/too-much-in-common-shifting-of-embeddings-in","slug":"too-much-in-common-shifting-of-embeddings-in","title":"Too Much in Common: Shifting of Embeddings in Transformer Language Models and its Implications","date":"2021-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-modeling-the-style-of-translators-in","title":"Towards Modeling the Style of Translators in Neural Machine Translation","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/you-only-look-at-one-sequence-rethinking","slug":"you-only-look-at-one-sequence-rethinking","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","date":"2021-06-01","arxiv_id":"2106.00666","n_code_links":2,"syntology":{"ran":5,"of":10,"n_ran_checked":2,"n_instrument":3,"unverified":5,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["hustvl/YOLOS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/analogous-to-evolutionary-algorithm-designing","slug":"analogous-to-evolutionary-algorithm-designing","title":"Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model","date":"2021-05-31","arxiv_id":"2105.15089","n_code_links":1,"syntology":null},{"paper":"/paper/beyond-noise-mitigating-the-impact-of-fine","slug":"beyond-noise-mitigating-the-impact-of-fine","title":"Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translation","date":"2021-05-31","arxiv_id":"2105.15087","n_code_links":2,"syntology":null},{"paper":"/paper/cascaded-head-colliding-attention","slug":"cascaded-head-colliding-attention","title":"Cascaded Head-colliding Attention","date":"2021-05-31","arxiv_id":"2105.14850","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":5,"n_instrument":4,"unverified":1,"pointer_only":5,"phrase":"9 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["LZhengisme/CODA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official","unlocated"]}}},{"paper":"/paper/choose-a-transformer-fourier-or-galerkin","slug":"choose-a-transformer-fourier-or-galerkin","title":"Choose a Transformer: Fourier or Galerkin","date":"2021-05-31","arxiv_id":"2105.14995","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":["scaomath/galerkin-transformer"],"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":"exploring-sparse-expert-models-and-beyond","title":"M6-T: Exploring Sparse Expert Models and Beyond","date":"2021-05-31","arxiv_id":"2105.15082","n_code_links":0,"syntology":null},{"paper":"/paper/g-transformer-for-document-level-machine","slug":"g-transformer-for-document-level-machine","title":"G-Transformer for Document-level Machine Translation","date":"2021-05-31","arxiv_id":"2105.14761","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["baoguangsheng/g-transformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/not-all-images-are-worth-16x16-words-dynamic","slug":"not-all-images-are-worth-16x16-words-dynamic","title":"Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition","date":"2021-05-31","arxiv_id":"2105.15075","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["blackfeather-wang/Dynamic-Vision-Transformer","blackfeather-wang/dynamic-vision-transformer-mindspore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/segformer-simple-and-efficient-design-for","slug":"segformer-simple-and-efficient-design-for","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","date":"2021-05-31","arxiv_id":"2105.15203","n_code_links":28,"syntology":{"ran":66,"of":86,"n_ran_checked":62,"n_instrument":4,"unverified":20,"pointer_only":20,"phrase":"66 ran (of which 22 constructed an object rather than computing a result; 62 with no instrument failure: 0 honoured, 1 violated, 61 with no contract checked; 4 where Syntology's instrument failed) · 20 unverified","official":{"repos":["NVlabs/SegFormer"],"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":["community","listed","unlocated"]}}},{"paper":null,"slug":"neural-models-for-offensive-language","title":"Neural Models for Offensive Language Detection","date":"2021-05-30","arxiv_id":"2106.14609","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-deep-image-matching-for","slug":"transformer-based-deep-image-matching-for","title":"TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification","date":"2021-05-30","arxiv_id":"2105.14432","n_code_links":2,"syntology":{"ran":13,"of":21,"n_ran_checked":9,"n_instrument":4,"unverified":8,"pointer_only":1,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","official":{"repos":["shengcailiao/QAConv","ShengcaiLiao/TransMatcher"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["found_in_text","official","unlocated"]}}},{"paper":"/paper/unsupervised-joint-learning-of-depth-optical","slug":"unsupervised-joint-learning-of-depth-optical","title":"Unsupervised Joint Learning of Depth, Optical Flow, Ego-motion from Video","date":"2021-05-30","arxiv_id":"2105.14520","n_code_links":1,"syntology":null},{"paper":null,"slug":"foveater-foveated-transformer-for-image","title":"FoveaTer: Foveated Transformer for Image Classification","date":"2021-05-29","arxiv_id":"2105.14173","n_code_links":0,"syntology":null},{"paper":"/paper/korean-english-machine-translation-with","slug":"korean-english-machine-translation-with","title":"Korean-English Machine Translation with Multiple Tokenization Strategy","date":"2021-05-29","arxiv_id":"2105.14274","n_code_links":1,"syntology":null},{"paper":"/paper/less-is-more-pay-less-attention-in-vision","slug":"less-is-more-pay-less-attention-in-vision","title":"Less is More: Pay Less Attention in Vision Transformers","date":"2021-05-29","arxiv_id":"2105.14217","n_code_links":2,"syntology":null},{"paper":null,"slug":"ufc-bert-unifying-multi-modal-controls-for","title":"M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers","date":"2021-05-29","arxiv_id":"2105.14211","n_code_links":0,"syntology":null},{"paper":"/paper/an-attention-free-transformer-1","slug":"an-attention-free-transformer-1","title":"An Attention Free Transformer","date":"2021-05-28","arxiv_id":"2105.14103","n_code_links":11,"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":null}},{"paper":"/paper/byt5-towards-a-token-free-future-with-pre","slug":"byt5-towards-a-token-free-future-with-pre","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","date":"2021-05-28","arxiv_id":"2105.13626","n_code_links":5,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google-research/byt5"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/compositionally-restricted-attention-based","slug":"compositionally-restricted-attention-based","title":"Compositionally restricted attention-based network for materials property predictions","date":"2021-05-28","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/hierarchical-transformer-encoders-for","slug":"hierarchical-transformer-encoders-for","title":"Hierarchical Transformer Encoders for Vietnamese Spelling Correction","date":"2021-05-28","arxiv_id":"2105.13578","n_code_links":1,"syntology":null},{"paper":"/paper/ptnet-a-high-resolution-infant-mri","slug":"ptnet-a-high-resolution-infant-mri","title":"PTNet: A High-Resolution Infant MRI Synthesizer Based on Transformer","date":"2021-05-28","arxiv_id":"2105.13993","n_code_links":1,"syntology":null}],"record_sha256":"2c918b35726c6a1aefd5c4bc6896ca02af676acdb2726bc59827658fad6c4603","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}