{"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/absolute-position-encodings/papers/120","list_of":"/method/absolute-position-encodings","method":"Absolute Position Encodings","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":120,"pages_in_order":140,"rows_per_page":100,"rows":[11901,12000],"of":13942,"counts":{"archive_papers_tagged":13942,"with_a_code_link":6505,"where_syntology_ran_a_sample":2224,"not_listed_spam_title":0,"listed":13942,"listed_where_code_ran":2224,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1897,"every_run_a_failure_of_syntologys_instrument":327,"listed_with_a_run_with_no_instrument_failure":1897,"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/absolute-position-encodings","prev":"/method/absolute-position-encodings/papers/119","next":"/method/absolute-position-encodings/papers/121","papers":[{"paper":"/paper/revisiting-deep-learning-models-for-tabular","slug":"revisiting-deep-learning-models-for-tabular","title":"Revisiting Deep Learning Models for Tabular Data","date":"2021-06-22","arxiv_id":"2106.11959","n_code_links":11,"syntology":{"ran":18,"of":22,"n_ran_checked":15,"n_instrument":3,"unverified":4,"pointer_only":1,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 1 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yandex-research/tabular-dl-revisiting-models","Yura52/tabular-dl-revisiting-models"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"hi-behrt-hierarchical-transformer-based-model","title":"Hi-BEHRT: Hierarchical Transformer-based model for accurate prediction of clinical events using multimodal longitudinal electronic health records","date":"2021-06-21","arxiv_id":"2106.11360","n_code_links":0,"syntology":null},{"paper":null,"slug":"modetr-moving-object-detection-with","title":"MODETR: Moving Object Detection with Transformers","date":"2021-06-21","arxiv_id":"2106.11422","n_code_links":0,"syntology":null},{"paper":null,"slug":"tcic-theme-concepts-learning-cross-language","title":"TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning","date":"2021-06-21","arxiv_id":"2106.10936","n_code_links":0,"syntology":null},{"paper":"/paper/cpm-2-large-scale-cost-effective-pre-trained","slug":"cpm-2-large-scale-cost-effective-pre-trained","title":"CPM-2: Large-scale Cost-effective Pre-trained Language Models","date":"2021-06-20","arxiv_id":"2106.10715","n_code_links":2,"syntology":null},{"paper":"/paper/solution-for-large-scale-long-tailed","slug":"solution-for-large-scale-long-tailed","title":"Solution for Large-scale Long-tailed Recognition with Noisy Labels","date":"2021-06-20","arxiv_id":"2106.10683","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-image-transformer-for-one-shot","title":"Adaptive Image Transformer for One-Shot Object Detection","date":"2021-06-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/clusformer-a-transformer-based-clustering","slug":"clusformer-a-transformer-based-clustering","title":"Clusformer: A Transformer Based Clustering Approach to Unsupervised Large-Scale Face and Visual Landmark Recognition","date":"2021-06-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/exploring-vision-transformers-for-fine","slug":"exploring-vision-transformers-for-fine","title":"Exploring Vision Transformers for Fine-grained Classification","date":"2021-06-19","arxiv_id":"2106.10587","n_code_links":1,"syntology":null},{"paper":null,"slug":"gaussian-context-transformer","title":"Gaussian Context Transformer","date":"2021-06-19","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-compositional-generalization-in-1","title":"Improving Compositional Generalization in Classification Tasks via Structure Annotations","date":"2021-06-19","arxiv_id":"2106.10434","n_code_links":0,"syntology":null},{"paper":"/paper/jointgt-graph-text-joint-representation","slug":"jointgt-graph-text-joint-representation","title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","date":"2021-06-19","arxiv_id":"2106.10502","n_code_links":1,"syntology":null},{"paper":"/paper/point-4d-transformer-networks-for-spatio","slug":"point-4d-transformer-networks-for-spatio","title":"Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos","date":"2021-06-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/rstnet-captioning-with-adaptive-attention-on","slug":"rstnet-captioning-with-adaptive-attention-on","title":"RSTNet: Captioning With Adaptive Attention on Visual and Non-Visual Words","date":"2021-06-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/all-you-can-embed-natural-language-based","slug":"all-you-can-embed-natural-language-based","title":"All You Can Embed: Natural Language based Vehicle Retrieval with Spatio-Temporal Transformers","date":"2021-06-18","arxiv_id":"2106.10153","n_code_links":1,"syntology":null},{"paper":"/paper/anomaly-detection-in-dynamic-graphs-via","slug":"anomaly-detection-in-dynamic-graphs-via","title":"Anomaly Detection in Dynamic Graphs via Transformer","date":"2021-06-18","arxiv_id":"2106.09876","n_code_links":1,"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":null}},{"paper":"/paper/end-to-end-temporal-action-detection-with","slug":"end-to-end-temporal-action-detection-with","title":"End-to-end Temporal Action Detection with Transformer","date":"2021-06-18","arxiv_id":"2106.10271","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["xlliu7/TadTR"],"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":null,"slug":"recurrent-stacking-of-layers-in-neural","title":"Recurrent Stacking of Layers in Neural Networks: An Application to Neural Machine Translation","date":"2021-06-18","arxiv_id":"2106.10002","n_code_links":0,"syntology":null},{"paper":"/paper/dual-view-molecule-pre-training","slug":"dual-view-molecule-pre-training","title":"Dual-view Molecule Pre-training","date":"2021-06-17","arxiv_id":"2106.10234","n_code_links":1,"syntology":null},{"paper":null,"slug":"long-short-temporal-contrastive-learning-of","title":"Long-Short Temporal Contrastive Learning of Video Transformers","date":"2021-06-17","arxiv_id":"2106.09212","n_code_links":0,"syntology":null},{"paper":"/paper/lora-low-rank-adaptation-of-large-language","slug":"lora-low-rank-adaptation-of-large-language","title":"LoRA: Low-Rank Adaptation of Large Language Models","date":"2021-06-17","arxiv_id":"2106.09685","n_code_links":74,"syntology":{"ran":51,"of":84,"n_ran_checked":44,"n_instrument":7,"unverified":33,"pointer_only":30,"phrase":"51 ran (of which 19 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 7 where Syntology's instrument failed) · 33 unverified","official":{"repos":["microsoft/LoRA"],"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/multi-head-or-single-head-an-empirical","slug":"multi-head-or-single-head-an-empirical","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training","date":"2021-06-17","arxiv_id":"2106.09650","n_code_links":1,"syntology":null},{"paper":"/paper/semi-autoregressive-transformer-for-image","slug":"semi-autoregressive-transformer-for-image","title":"Semi-Autoregressive Transformer for Image Captioning","date":"2021-06-17","arxiv_id":"2106.09436","n_code_links":1,"syntology":null},{"paper":"/paper/time-series-is-a-special-sequence-forecasting","slug":"time-series-is-a-special-sequence-forecasting","title":"SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction","date":"2021-06-17","arxiv_id":"2106.09305","n_code_links":6,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["WenjieDu/PyPOTS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","named_in_paper"]}}},{"paper":"/paper/end-to-end-semi-supervised-object-detection","slug":"end-to-end-semi-supervised-object-detection","title":"End-to-End Semi-Supervised Object Detection with Soft Teacher","date":"2021-06-16","arxiv_id":"2106.09018","n_code_links":8,"syntology":null},{"paper":"/paper/grounding-spatio-temporal-language-with","slug":"grounding-spatio-temporal-language-with","title":"Grounding Spatio-Temporal Language with Transformers","date":"2021-06-16","arxiv_id":"2106.08858","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-evaluation-and-improvement-of-tail-label","title":"On Evaluation and Improvement of Tail Label Performance for Multi-label Text Classification","date":"2021-06-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"shuffle-transformer-with-feature-alignment","title":"Shuffle Transformer with Feature Alignment for Video Face Parsing","date":"2021-06-16","arxiv_id":"2106.08650","n_code_links":0,"syntology":null},{"paper":null,"slug":"simultaneous-training-of-partially-masked","title":"Masked Training of Neural Networks with Partial Gradients","date":"2021-06-16","arxiv_id":"2106.08895","n_code_links":0,"syntology":null},{"paper":"/paper/beit-bert-pre-training-of-image-transformers","slug":"beit-bert-pre-training-of-image-transformers","title":"BEiT: BERT Pre-Training of Image Transformers","date":"2021-06-15","arxiv_id":"2106.08254","n_code_links":14,"syntology":{"ran":6,"of":11,"n_ran_checked":4,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["microsoft/unilm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"pairconnect-a-compute-efficient-mlp","title":"PairConnect: A Compute-Efficient MLP Alternative to Attention","date":"2021-06-15","arxiv_id":"2106.08235","n_code_links":0,"syntology":null},{"paper":"/paper/scene-transformer-a-unified-multi-task-model","slug":"scene-transformer-a-unified-multi-task-model","title":"Scene Transformer: A unified architecture for predicting multiple agent trajectories","date":"2021-06-15","arxiv_id":"2106.08417","n_code_links":4,"syntology":{"ran":2,"of":6,"n_ran_checked":1,"n_instrument":1,"unverified":4,"pointer_only":6,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":null}},{"paper":null,"slug":"end-to-end-neural-diarization-from","title":"End-to-end Neural Diarization: From Transformer to Conformer","date":"2021-06-14","arxiv_id":"2106.07167","n_code_links":0,"syntology":null},{"paper":"/paper/improved-transformer-for-high-resolution-gans","slug":"improved-transformer-for-high-resolution-gans","title":"Improved Transformer for High-Resolution GANs","date":"2021-06-14","arxiv_id":"2106.07631","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["google-research/hit-gan"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/ng-a-multi-step-matrix-product-natural","slug":"ng-a-multi-step-matrix-product-natural","title":"NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learning","date":"2021-06-14","arxiv_id":"2106.07454","n_code_links":1,"syntology":null},{"paper":"/paper/s-2-mlp-spatial-shift-mlp-architecture-for","slug":"s-2-mlp-spatial-shift-mlp-architecture-for","title":"S$^2$-MLP: Spatial-Shift MLP Architecture for Vision","date":"2021-06-14","arxiv_id":"2106.07477","n_code_links":1,"syntology":null},{"paper":null,"slug":"why-can-you-lay-off-heads-investigating-how","title":"Why Can You Lay Off Heads? Investigating How BERT Heads Transfer","date":"2021-06-14","arxiv_id":"2106.07137","n_code_links":0,"syntology":null},{"paper":null,"slug":"infobehavior-self-supervised-representation","title":"InfoBehavior: Self-supervised Representation Learning for Ultra-long Behavior Sequence via Hierarchical Grouping","date":"2021-06-13","arxiv_id":"2106.06905","n_code_links":0,"syntology":null},{"paper":"/paper/reinforcement-learning-as-one-big-sequence-1","slug":"reinforcement-learning-as-one-big-sequence-1","title":"Reinforcement Learning as One Big Sequence Modeling Problem","date":"2021-06-13","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/the-deformer-an-order-agnostic-distribution","slug":"the-deformer-an-order-agnostic-distribution","title":"The DEformer: An Order-Agnostic Distribution Estimating Transformer","date":"2021-06-13","arxiv_id":"2106.06989","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":5,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["airalcorn2/deformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/thinking-like-transformers-1","slug":"thinking-like-transformers-1","title":"Thinking Like Transformers","date":"2021-06-13","arxiv_id":"2106.06981","n_code_links":5,"syntology":{"ran":11,"of":18,"n_ran_checked":7,"n_instrument":4,"unverified":7,"pointer_only":5,"phrase":"11 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","official":{"repos":["tech-srl/RASP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"curriculum-pre-training-heterogeneous","title":"Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-$N$ Recommendation","date":"2021-06-12","arxiv_id":"2106.06722","n_code_links":0,"syntology":null},{"paper":"/paper/ds-transunet-dual-swin-transformer-u-net-for","slug":"ds-transunet-dual-swin-transformer-u-net-for","title":"DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation","date":"2021-06-12","arxiv_id":"2106.06716","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["TianBaoGe/DS-TransUNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/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}],"record_sha256":"8a05c50c21a2a8f3923946b512c31f6b6480b4def0b15726f7a977fc69b9c5e1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}