{"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/attention/papers/237","list_of":"/method/attention","method":"Attention","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":237,"pages_in_order":316,"rows_per_page":100,"rows":[23601,23700],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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/attention","prev":"/method/attention/papers/236","next":"/method/attention/papers/238","papers":[{"paper":"/paper/modeling-image-composition-for-complex-scene","slug":"modeling-image-composition-for-complex-scene","title":"Modeling Image Composition for Complex Scene Generation","date":"2022-06-02","arxiv_id":"2206.00923","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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["johndreamer/twfa"],"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/optimizing-relevance-maps-of-vision","slug":"optimizing-relevance-maps-of-vision","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","date":"2022-06-02","arxiv_id":"2206.01161","n_code_links":1,"syntology":null},{"paper":null,"slug":"transforming-medical-imaging-with","title":"Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives","date":"2022-06-02","arxiv_id":"2206.01136","n_code_links":0,"syntology":null},{"paper":null,"slug":"vl-beit-generative-vision-language","title":"VL-BEiT: Generative Vision-Language Pretraining","date":"2022-06-02","arxiv_id":"2206.01127","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-between-vision","title":"A comparative study between vision transformers and CNNs in digital pathology","date":"2022-06-01","arxiv_id":"2206.00389","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-group-level-gender-bias-in","title":"Assessing Group-level Gender Bias in Professional Evaluations: The Case of Medical Student End-of-Shift Feedback","date":"2022-06-01","arxiv_id":"2206.00234","n_code_links":0,"syntology":null},{"paper":"/paper/bert-sort-a-zero-shot-mlm-semantic-encoder-on","slug":"bert-sort-a-zero-shot-mlm-semantic-encoder-on","title":"BERT-Sort: A Zero-shot MLM Semantic Encoder on Ordinal Features for AutoML","date":"2022-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/clip4idc-clip-for-image-difference-captioning","slug":"clip4idc-clip-for-image-difference-captioning","title":"CLIP4IDC: CLIP for Image Difference Captioning","date":"2022-06-01","arxiv_id":"2206.00629","n_code_links":1,"syntology":null},{"paper":null,"slug":"cross-domain-detection-transformer-based-on","title":"Cross-domain Detection Transformer based on Spatial-aware and Semantic-aware Token Alignment","date":"2022-06-01","arxiv_id":"2206.00222","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-self-supervised-vision-pretraining","slug":"efficient-self-supervised-vision-pretraining","title":"Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction","date":"2022-06-01","arxiv_id":"2206.00790","n_code_links":1,"syntology":null},{"paper":"/paper/entity-resolution-with-hierarchical-graph","slug":"entity-resolution-with-hierarchical-graph","title":"Entity Resolution with Hierarchical Graph Attention Networks","date":"2022-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"extreme-floorplan-reconstruction-by-structure","title":"Floorplan Restoration by Structure Hallucinating Transformer Cascades","date":"2022-06-01","arxiv_id":"2206.00645","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-sequential-contexts-using","title":"Learning Sequential Contexts using Transformer for 3D Hand Pose Estimation","date":"2022-06-01","arxiv_id":"2206.00171","n_code_links":0,"syntology":null},{"paper":null,"slug":"order-sensitive-shapley-values-for-evaluating","title":"Order-sensitive Shapley Values for Evaluating Conceptual Soundness of NLP Models","date":"2022-06-01","arxiv_id":"2206.00192","n_code_links":0,"syntology":null},{"paper":null,"slug":"romantic-computing","title":"Romantic-Computing","date":"2022-06-01","arxiv_id":"2206.11864","n_code_links":0,"syntology":null},{"paper":"/paper/stargazer-a-transformer-based-driver-action","slug":"stargazer-a-transformer-based-driver-action","title":"Stargazer: A transformer-based driver action detection system for intelligent transportation","date":"2022-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/the-fully-convolutional-transformer-for","slug":"the-fully-convolutional-transformer-for","title":"The Fully Convolutional Transformer for Medical Image Segmentation","date":"2022-06-01","arxiv_id":"2206.00566","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-unified-framework-for-emotion","title":"A Unified Framework for Emotion Identification and Generation in Dialogues","date":"2022-05-31","arxiv_id":"2205.15513","n_code_links":0,"syntology":null},{"paper":"/paper/codeattack-code-based-adversarial-attacks-for","slug":"codeattack-code-based-adversarial-attacks-for","title":"CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models","date":"2022-05-31","arxiv_id":"2206.00052","n_code_links":2,"syntology":null},{"paper":"/paper/decomposing-nerf-for-editing-via-feature","slug":"decomposing-nerf-for-editing-via-feature","title":"Decomposing NeRF for Editing via Feature Field Distillation","date":"2022-05-31","arxiv_id":"2205.15585","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/gatenlp-ushef-at-semeval-2022-task-8-entity","slug":"gatenlp-ushef-at-semeval-2022-task-8-entity","title":"GateNLP-UShef at SemEval-2022 Task 8: Entity-Enriched Siamese Transformer for Multilingual News Article Similarity","date":"2022-05-31","arxiv_id":"2205.15812","n_code_links":1,"syntology":null},{"paper":null,"slug":"inferring-3d-change-detection-from-bitemporal","title":"Inferring 3D change detection from bitemporal optical images","date":"2022-05-31","arxiv_id":"2205.15903","n_code_links":0,"syntology":null},{"paper":"/paper/joint-spatial-temporal-and-appearance","slug":"joint-spatial-temporal-and-appearance","title":"Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking","date":"2022-05-31","arxiv_id":"2205.15495","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-graph-deep-learning-a-case-study-in","title":"Knowledge Graph - Deep Learning: A Case Study in Question Answering in Aviation Safety Domain","date":"2022-05-31","arxiv_id":"2205.15952","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-represent-programs-with-code","title":"HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representations","date":"2022-05-31","arxiv_id":"2205.15479","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-transformers-for-product","title":"Multilingual Transformers for Product Matching -- Experiments and a New Benchmark in Polish","date":"2022-05-31","arxiv_id":"2205.15712","n_code_links":0,"syntology":null},{"paper":"/paper/surface-analysis-with-vision-transformers","slug":"surface-analysis-with-vision-transformers","title":"Surface Analysis with Vision Transformers","date":"2022-05-31","arxiv_id":"2205.15836","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 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":["metrics-lab/surface-vision-transformers"],"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"]}}},{"paper":null,"slug":"you-can-t-count-on-luck-why-decision","title":"You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments","date":"2022-05-31","arxiv_id":"2205.15967","n_code_links":0,"syntology":null},{"paper":"/paper/attention-flows-for-general-transformers","slug":"attention-flows-for-general-transformers","title":"Attention Flows for General Transformers","date":"2022-05-30","arxiv_id":"2205.15389","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-short-math-answer-grading-via-in","slug":"automatic-short-math-answer-grading-via-in","title":"Automatic Short Math Answer Grading via In-context Meta-learning","date":"2022-05-30","arxiv_id":"2205.15219","n_code_links":1,"syntology":null},{"paper":"/paper/billions-of-parameters-are-worth-more-than-in","slug":"billions-of-parameters-are-worth-more-than-in","title":"Billions of Parameters Are Worth More Than In-domain Training Data: A case study in the Legal Case Entailment Task","date":"2022-05-30","arxiv_id":"2205.15172","n_code_links":1,"syntology":null},{"paper":"/paper/can-transformer-be-too-compositional-1","slug":"can-transformer-be-too-compositional-1","title":"Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation","date":"2022-05-30","arxiv_id":"2205.15301","n_code_links":1,"syntology":null},{"paper":"/paper/e2s2-encoding-enhanced-sequence-to-sequence","slug":"e2s2-encoding-enhanced-sequence-to-sequence","title":"E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation","date":"2022-05-30","arxiv_id":"2205.14912","n_code_links":1,"syntology":null},{"paper":"/paper/few-shot-diffusion-models","slug":"few-shot-diffusion-models","title":"Few-Shot Diffusion Models","date":"2022-05-30","arxiv_id":"2205.15463","n_code_links":1,"syntology":null},{"paper":"/paper/hivit-hierarchical-vision-transformer-meets","slug":"hivit-hierarchical-vision-transformer-meets","title":"HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling","date":"2022-05-30","arxiv_id":"2205.14949","n_code_links":1,"syntology":null},{"paper":"/paper/illumination-adaptive-transformer","slug":"illumination-adaptive-transformer","title":"You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction","date":"2022-05-30","arxiv_id":"2205.14871","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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) · 0 unverified","official":{"repos":["cuiziteng/illumination-adaptive-transformer"],"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"]}}},{"paper":"/paper/multi-agent-reinforcement-learning-is-a","slug":"multi-agent-reinforcement-learning-is-a","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","date":"2022-05-30","arxiv_id":"2205.14953","n_code_links":1,"syntology":null},{"paper":"/paper/multi-game-decision-transformers","slug":"multi-game-decision-transformers","title":"Multi-Game Decision Transformers","date":"2022-05-30","arxiv_id":"2205.15241","n_code_links":1,"syntology":null},{"paper":"/paper/prompting-electra-few-shot-learning-with","slug":"prompting-electra-few-shot-learning-with","title":"Prompting ELECTRA: Few-Shot Learning with Discriminative Pre-Trained Models","date":"2022-05-30","arxiv_id":"2205.15223","n_code_links":1,"syntology":null},{"paper":"/paper/temporal-latent-bottleneck-synthesis-of-fast","slug":"temporal-latent-bottleneck-synthesis-of-fast","title":"Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning","date":"2022-05-30","arxiv_id":"2205.14794","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":null}},{"paper":"/paper/transformer-with-tree-order-encoding-for","slug":"transformer-with-tree-order-encoding-for","title":"Transformer with Tree-order Encoding for Neural Program Generation","date":"2022-05-30","arxiv_id":"2206.13354","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-and-few-shot-learning-for-lung","title":"Zero-Shot and Few-Shot Learning for Lung Cancer Multi-Label Classification using Vision Transformer","date":"2022-05-30","arxiv_id":"2205.15290","n_code_links":0,"syntology":null},{"paper":null,"slug":"covid-19-literature-mining-and-retrieval","title":"COVID-19 Literature Mining and Retrieval using Text Mining Approaches","date":"2022-05-29","arxiv_id":"2205.14781","n_code_links":0,"syntology":null},{"paper":"/paper/cped-a-large-scale-chinese-personalized-and-1","slug":"cped-a-large-scale-chinese-personalized-and-1","title":"CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI","date":"2022-05-29","arxiv_id":"2205.14727","n_code_links":1,"syntology":null},{"paper":"/paper/efficientvit-enhanced-linear-attention-for","slug":"efficientvit-enhanced-linear-attention-for","title":"EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction","date":"2022-05-29","arxiv_id":"2205.14756","n_code_links":6,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mit-han-lab/efficientvit","rwightman/pytorch-image-models"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-locality-and-isotropy-in-dialogue","slug":"learning-locality-and-isotropy-in-dialogue","title":"Learning Locality and Isotropy in Dialogue Modeling","date":"2022-05-29","arxiv_id":"2205.14583","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":["hahahawu/simdrc"],"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":"micro-expression-recognition-based-on","title":"Micro-Expression Recognition Based on Attribute Information Embedding and Cross-modal Contrastive Learning","date":"2022-05-29","arxiv_id":"2205.14643","n_code_links":0,"syntology":null},{"paper":null,"slug":"sfe-ai-at-semeval-2022-task-11-low-resource","title":"SFE-AI at SemEval-2022 Task 11: Low-Resource Named Entity Recognition using Large Pre-trained Language Models","date":"2022-05-29","arxiv_id":"2205.14660","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformap-transformer-for-memory-access","title":"TransforMAP: Transformer for Memory Access Prediction","date":"2022-05-29","arxiv_id":"2205.14778","n_code_links":0,"syntology":null},{"paper":null,"slug":"urdu-news-article-recommendation-model-using","title":"Urdu News Article Recommendation Model using Natural Language Processing Techniques","date":"2022-05-29","arxiv_id":"2206.11862","n_code_links":0,"syntology":null},{"paper":null,"slug":"approximate-conditional-coverage-via-neural","title":"Approximate Conditional Coverage & Calibration via Neural Model Approximations","date":"2022-05-28","arxiv_id":"2205.14310","n_code_links":0,"syntology":null},{"paper":"/paper/learning-non-autoregressive-models-from-2","slug":"learning-non-autoregressive-models-from-2","title":"Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization","date":"2022-05-28","arxiv_id":"2205.14521","n_code_links":1,"syntology":null},{"paper":"/paper/mdmlp-image-classification-from-scratch-on","slug":"mdmlp-image-classification-from-scratch-on","title":"MDMLP: Image Classification from Scratch on Small Datasets with MLP","date":"2022-05-28","arxiv_id":"2205.14477","n_code_links":2,"syntology":null},{"paper":"/paper/multi-task-learning-with-multi-query","slug":"multi-task-learning-with-multi-query","title":"Multi-Task Learning with Multi-Query Transformer for Dense Prediction","date":"2022-05-28","arxiv_id":"2205.14354","n_code_links":1,"syntology":null},{"paper":"/paper/non-stationary-transformers-rethinking-the","slug":"non-stationary-transformers-rethinking-the","title":"Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting","date":"2022-05-28","arxiv_id":"2205.14415","n_code_links":2,"syntology":null},{"paper":"/paper/teaching-models-to-express-their-uncertainty","slug":"teaching-models-to-express-their-uncertainty","title":"Teaching Models to Express Their Uncertainty in Words","date":"2022-05-28","arxiv_id":"2205.14334","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sylinrl/calibratedmath"],"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/variational-transformer-a-framework-beyond","slug":"variational-transformer-a-framework-beyond","title":"Variational Transformer: A Framework Beyond the Trade-off between Accuracy and Diversity for Image Captioning","date":"2022-05-28","arxiv_id":"2205.14458","n_code_links":1,"syntology":null},{"paper":null,"slug":"wt-mvsnet-window-based-transformers-for-multi","title":"WT-MVSNet: Window-based Transformers for Multi-view Stereo","date":"2022-05-28","arxiv_id":"2205.14319","n_code_links":0,"syntology":null},{"paper":"/paper/architecture-agnostic-masked-image-modeling","slug":"architecture-agnostic-masked-image-modeling","title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","date":"2022-05-27","arxiv_id":"2205.13943","n_code_links":3,"syntology":null},{"paper":"/paper/fedformer-contextual-federation-with","slug":"fedformer-contextual-federation-with","title":"FedFormer: Contextual Federation with Attention in Reinforcement Learning","date":"2022-05-27","arxiv_id":"2205.13697","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 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) · 0 unverified","official":{"repos":["liamhebert/FedFormer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/flashattention-fast-and-memory-efficient","slug":"flashattention-fast-and-memory-efficient","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","date":"2022-05-27","arxiv_id":"2205.14135","n_code_links":13,"syntology":{"ran":24,"of":30,"n_ran_checked":18,"n_instrument":6,"unverified":6,"pointer_only":1,"phrase":"24 ran (of which 2 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","official":{"repos":["dao-ailab/flash-attention"],"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":["found_in_text","listed"]}}},{"paper":"/paper/future-transformer-for-long-term-action","slug":"future-transformer-for-long-term-action","title":"Future Transformer for Long-term Action Anticipation","date":"2022-05-27","arxiv_id":"2205.14022","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":8,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/git-a-generative-image-to-text-transformer","slug":"git-a-generative-image-to-text-transformer","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","date":"2022-05-27","arxiv_id":"2205.14100","n_code_links":1,"syntology":{"ran":14,"of":21,"n_ran_checked":14,"n_instrument":0,"unverified":7,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["microsoft/GenerativeImage2Text"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/momentum-stiefel-optimizer-with-applications","slug":"momentum-stiefel-optimizer-with-applications","title":"Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport","date":"2022-05-27","arxiv_id":"2205.14173","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["konglk1203/variationalstiefeloptimizer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/multimodal-masked-autoencoders-learn","slug":"multimodal-masked-autoencoders-learn","title":"Multimodal Masked Autoencoders Learn Transferable Representations","date":"2022-05-27","arxiv_id":"2205.14204","n_code_links":3,"syntology":{"ran":12,"of":12,"n_ran_checked":9,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["young-geng/m3ae_public"],"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"]}}},{"paper":"/paper/nearest-neighbor-zero-shot-inference","slug":"nearest-neighbor-zero-shot-inference","title":"kNN-Prompt: Nearest Neighbor Zero-Shot Inference","date":"2022-05-27","arxiv_id":"2205.13792","n_code_links":1,"syntology":null},{"paper":null,"slug":"nlu-for-game-based-learning-in-real-initial","title":"NLU for Game-based Learning in Real: Initial Evaluations","date":"2022-05-27","arxiv_id":"2205.13754","n_code_links":0,"syntology":null},{"paper":"/paper/patching-leaks-in-the-charformer-for-1","slug":"patching-leaks-in-the-charformer-for-1","title":"Patching Leaks in the Charformer for Efficient Character-Level Generation","date":"2022-05-27","arxiv_id":"2205.14086","n_code_links":1,"syntology":null},{"paper":"/paper/probabilistic-transformer-modelling","slug":"probabilistic-transformer-modelling","title":"Probabilistic Transformer: Modelling Ambiguities and Distributions for RNA Folding and Molecule Design","date":"2022-05-27","arxiv_id":"2205.13927","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-from-an-optimization-perspective","slug":"transformers-from-an-optimization-perspective","title":"Transformers from an Optimization Perspective","date":"2022-05-27","arxiv_id":"2205.13891","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["fftyyy/transformers-from-optimization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/turjuman-a-public-toolkit-for-neural-arabic","slug":"turjuman-a-public-toolkit-for-neural-arabic","title":"TURJUMAN: A Public Toolkit for Neural Arabic Machine Translation","date":"2022-05-27","arxiv_id":"2206.03933","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-long-programming-languages-with","slug":"understanding-long-programming-languages-with","title":"Understanding Long Programming Languages with Structure-Aware Sparse Attention","date":"2022-05-27","arxiv_id":"2205.13730","n_code_links":1,"syntology":null},{"paper":"/paper/what-dense-graph-do-you-need-for-self","slug":"what-dense-graph-do-you-need-for-self","title":"What Dense Graph Do You Need for Self-Attention?","date":"2022-05-27","arxiv_id":"2205.14014","n_code_links":1,"syntology":null},{"paper":"/paper/adaptformer-adapting-vision-transformers-for","slug":"adaptformer-adapting-vision-transformers-for","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","date":"2022-05-26","arxiv_id":"2205.13535","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ShoufaChen/AdaptFormer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/are-transformers-effective-for-time-series","slug":"are-transformers-effective-for-time-series","title":"Are Transformers Effective for Time Series Forecasting?","date":"2022-05-26","arxiv_id":"2205.13504","n_code_links":10,"syntology":{"ran":13,"of":19,"n_ran_checked":13,"n_instrument":0,"unverified":6,"pointer_only":13,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 6 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":null,"slug":"benchmarking-of-deep-learning-models-on-2d","title":"Benchmarking of Deep Learning models on 2D Laminar Flow behind Cylinder","date":"2022-05-26","arxiv_id":"2205.13485","n_code_links":0,"syntology":null},{"paper":null,"slug":"clinical-dialogue-transcription-error","title":"Clinical Dialogue Transcription Error Correction using Seq2Seq Models","date":"2022-05-26","arxiv_id":"2205.13572","n_code_links":0,"syntology":null},{"paper":null,"slug":"dt-sv-a-transformer-based-time-domain","title":"DT-SV: A Transformer-based Time-domain Approach for Speaker Verification","date":"2022-05-26","arxiv_id":"2205.13249","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-u-transformer-with-boundary-aware","slug":"efficient-u-transformer-with-boundary-aware","title":"Do we really need temporal convolutions in action segmentation?","date":"2022-05-26","arxiv_id":"2205.13425","n_code_links":1,"syntology":null},{"paper":null,"slug":"embed-to-control-partially-observed-systems","title":"Embed to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency","date":"2022-05-26","arxiv_id":"2205.13476","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-split-bert-for-heterogeneous-text","title":"Federated Split BERT for Heterogeneous Text Classification","date":"2022-05-26","arxiv_id":"2205.13299","n_code_links":0,"syntology":null},{"paper":"/paper/green-hierarchical-vision-transformer-for","slug":"green-hierarchical-vision-transformer-for","title":"Green Hierarchical Vision Transformer for Masked Image Modeling","date":"2022-05-26","arxiv_id":"2205.13515","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["layneh/greenmim"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-dialogue-representations-from","slug":"learning-dialogue-representations-from","title":"Learning Dialogue Representations from Consecutive Utterances","date":"2022-05-26","arxiv_id":"2205.13568","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-dependency-grammar-for-fine","slug":"leveraging-dependency-grammar-for-fine","title":"Leveraging Dependency Grammar for Fine-Grained Offensive Language Detection using Graph Convolutional Networks","date":"2022-05-26","arxiv_id":"2205.13164","n_code_links":1,"syntology":null},{"paper":"/paper/mixmim-mixed-and-masked-image-modeling-for","slug":"mixmim-mixed-and-masked-image-modeling-for","title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers","date":"2022-05-26","arxiv_id":"2205.13137","n_code_links":1,"syntology":null},{"paper":"/paper/semaffinet-semantic-affine-transformation-for","slug":"semaffinet-semantic-affine-transformation-for","title":"SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation","date":"2022-05-26","arxiv_id":"2205.13490","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":11,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wangzy22/SemAffiNet"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-document-vectors-using-cosine-similarity-1","slug":"the-document-vectors-using-cosine-similarity-1","title":"The Document Vectors Using Cosine Similarity Revisited","date":"2022-05-26","arxiv_id":"2205.13357","n_code_links":1,"syntology":null},{"paper":"/paper/towards-learning-universal-hyperparameter","slug":"towards-learning-universal-hyperparameter","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","date":"2022-05-26","arxiv_id":"2205.13320","n_code_links":1,"syntology":null},{"paper":"/paper/training-and-inference-on-any-order","slug":"training-and-inference-on-any-order","title":"Training and Inference on Any-Order Autoregressive Models the Right Way","date":"2022-05-26","arxiv_id":"2205.13554","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-for-partial-differential","slug":"transformer-for-partial-differential","title":"Transformer for Partial Differential Equations' Operator Learning","date":"2022-05-26","arxiv_id":"2205.13671","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":12,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["BaratiLab/OFormer"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vidi-a-video-dataset-of-incidents","slug":"vidi-a-video-dataset-of-incidents","title":"VIDI: A Video Dataset of Incidents","date":"2022-05-26","arxiv_id":"2205.13277","n_code_links":1,"syntology":null},{"paper":"/paper/your-transformer-may-not-be-as-powerful-as","slug":"your-transformer-may-not-be-as-powerful-as","title":"Your Transformer May Not be as Powerful as You Expect","date":"2022-05-26","arxiv_id":"2205.13401","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lsj2408/urpe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/bit-robustly-binarized-multi-distilled","slug":"bit-robustly-binarized-multi-distilled","title":"BiT: Robustly Binarized Multi-distilled Transformer","date":"2022-05-25","arxiv_id":"2205.13016","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"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) · 0 unverified","official":{"repos":["facebookresearch/bit"],"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":["listed","official"]}}},{"paper":null,"slug":"conditional-set-generation-using-seq2seq-1","title":"Conditional set generation using Seq2seq models","date":"2022-05-25","arxiv_id":"2205.12485","n_code_links":0,"syntology":null},{"paper":null,"slug":"eye-gaze-guided-vision-transformer-for","title":"Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning","date":"2022-05-25","arxiv_id":"2205.12466","n_code_links":0,"syntology":null},{"paper":"/paper/factorizing-content-and-budget-decisions-in","slug":"factorizing-content-and-budget-decisions-in","title":"Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents","date":"2022-05-25","arxiv_id":"2205.12486","n_code_links":1,"syntology":null},{"paper":"/paper/inception-transformer","slug":"inception-transformer","title":"Inception Transformer","date":"2022-05-25","arxiv_id":"2205.12956","n_code_links":4,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["sail-sg/iformer"],"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":"large-language-models-are-zero-shot-clinical","title":"Large Language Models are Few-Shot Clinical Information Extractors","date":"2022-05-25","arxiv_id":"2205.12689","n_code_links":0,"syntology":null},{"paper":null,"slug":"lifelong-learning-natural-language-processing","title":"Lifelong Learning Natural Language Processing Approach for Multilingual Data Classification","date":"2022-05-25","arxiv_id":"2206.11867","n_code_links":0,"syntology":null},{"paper":"/paper/mocovit-mobile-convolutional-vision","slug":"mocovit-mobile-convolutional-vision","title":"MoCoViT: Mobile Convolutional Vision Transformer","date":"2022-05-25","arxiv_id":"2205.12635","n_code_links":1,"syntology":null}],"record_sha256":"7000a48bdd67e165be6dfc72aaff1fb0b97630ce2c98eb8c0d710a7b4d3449f2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}