{"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":"/task/hard-attention","name":"Hard Attention","slug":"hard-attention","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":100,"papers_with_code":41,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":100,"of":100,"of_with_code":41,"tagged_in_all":100,"counts":{"archive_papers_tagged":100,"with_a_code_link":41,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":100,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":3,"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"},"items":[{"url":"/paper/recurrent-models-of-visual-attention","slug":"recurrent-models-of-visual-attention","title":"Recurrent Models of Visual Attention","date":"2014-06-24","arxiv_id":"1406.6247","repositories_listed":20,"syntology":{"n":24,"n_ran":21,"n_constructed":0,"n_ran_checked":20,"n_instrument":1,"n_unverified":3,"n_honours":4,"n_violates":2,"n_no_contract":14,"n_pointer_only":2,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 4 honoured, 2 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/recurrent-models-of-visual-attention#ran","syntology_url":"https://syntology.ai/paper/1406.6247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1406.6247"}},"official":null}},{"url":"/paper/dual-attention-networks-for-few-shot-fine","slug":"dual-attention-networks-for-few-shot-fine","title":"Dual Attention Networks for Few-Shot Fine-Grained Recognition","date":"2022-06-28","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/deep-attention-recurrent-q-network","slug":"deep-attention-recurrent-q-network","title":"Deep Attention Recurrent Q-Network","date":"2015-12-05","arxiv_id":"1512.01693","repositories_listed":3,"syntology":null},{"url":"/paper/learning-texture-transformer-network-for-1","slug":"learning-texture-transformer-network-for-1","title":"Learning Texture Transformer Network for Image Super-Resolution","date":"2020-06-07","arxiv_id":"2006.04139","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-texture-transformer-network-for-1#ran","syntology_url":"https://syntology.ai/paper/2006.04139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04139"}},"official":{"repos":["researchmm/TTSR"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/190807644","slug":"190807644","title":"Saccader: Improving Accuracy of Hard Attention Models for Vision","date":"2019-08-20","arxiv_id":"1908.07644","repositories_listed":2,"syntology":null},{"url":"/paper/exact-hard-monotonic-attention-for-character","slug":"exact-hard-monotonic-attention-for-character","title":"Exact Hard Monotonic Attention for Character-Level Transduction","date":"2019-05-15","arxiv_id":"1905.06319","repositories_listed":2,"syntology":null},{"url":"/paper/hard-non-monotonic-attention-for-character","slug":"hard-non-monotonic-attention-for-character","title":"Hard Non-Monotonic Attention for Character-Level Transduction","date":"2018-08-29","arxiv_id":"1808.10024","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hard-non-monotonic-attention-for-character#ran","syntology_url":"https://syntology.ai/paper/1808.10024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.10024"}},"official":{"repos":["shijie-wu/neural-transducer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/overcoming-catastrophic-forgetting-with-hard","slug":"overcoming-catastrophic-forgetting-with-hard","title":"Overcoming catastrophic forgetting with hard attention to the task","date":"2018-01-04","arxiv_id":"1801.01423","repositories_listed":2,"syntology":null},{"url":"/paper/center-guided-classifier-for-semantic","slug":"center-guided-classifier-for-semantic","title":"Center-guided Classifier for Semantic Segmentation of Remote Sensing Images","date":"2025-03-21","arxiv_id":"2503.16963","repositories_listed":1,"syntology":null},{"url":"/paper/hard-attention-gates-with-gradient-routing","slug":"hard-attention-gates-with-gradient-routing","title":"Hard-Attention Gates with Gradient Routing for Endoscopic Image Computing","date":"2024-07-05","arxiv_id":"2407.04400","repositories_listed":1,"syntology":null},{"url":"/paper/trip-trainable-region-of-interest-prediction","slug":"trip-trainable-region-of-interest-prediction","title":"TRIP: Trainable Region-of-Interest Prediction for Hardware-Efficient Neuromorphic Processing on Event-based Vision","date":"2024-06-25","arxiv_id":"2406.17483","repositories_listed":1,"syntology":null},{"url":"/paper/tree-based-hard-attention-with-self","slug":"tree-based-hard-attention-with-self","title":"Recurrent Alignment with Hard Attention for Hierarchical Text Rating","date":"2024-02-14","arxiv_id":"2402.08874","repositories_listed":1,"syntology":null},{"url":"/paper/mutual-distillation-learning-for-person-re","slug":"mutual-distillation-learning-for-person-re","title":"Mutual Distillation Learning For Person Re-Identification","date":"2024-01-12","arxiv_id":"2401.06430","repositories_listed":1,"syntology":null},{"url":"/paper/vamos-versatile-action-models-for-video","slug":"vamos-versatile-action-models-for-video","title":"Vamos: Versatile Action Models for Video Understanding","date":"2023-11-22","arxiv_id":"2311.13627","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":1,"n_no_contract":2,"n_pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vamos-versatile-action-models-for-video#ran","syntology_url":"https://syntology.ai/paper/2311.13627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13627"}},"official":{"repos":["brown-palm/Vamos"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/investigation-of-architectures-and-receptive","slug":"investigation-of-architectures-and-receptive","title":"Investigation of Architectures and Receptive Fields for Appearance-based Gaze Estimation","date":"2023-08-18","arxiv_id":"2308.09593","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-learning-dynamics-of-attention","slug":"on-the-learning-dynamics-of-attention","title":"On the Learning Dynamics of Attention Networks","date":"2023-07-25","arxiv_id":"2307.13421","repositories_listed":1,"syntology":null},{"url":"/paper/hat-cl-a-hard-attention-to-the-task-pytorch","slug":"hat-cl-a-hard-attention-to-the-task-pytorch","title":"HAT-CL: A Hard-Attention-to-the-Task PyTorch Library for Continual Learning","date":"2023-07-18","arxiv_id":"2307.09653","repositories_listed":1,"syntology":null},{"url":"/paper/coherent-concept-based-explanations-in","slug":"coherent-concept-based-explanations-in","title":"Coherent Concept-based Explanations in Medical Image and Its Application to Skin Lesion Diagnosis","date":"2023-04-10","arxiv_id":"2304.04579","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-perceive-in-deep-model-free","slug":"learning-to-perceive-in-deep-model-free","title":"Learning to Perceive in Deep Model-Free Reinforcement Learning","date":"2023-01-10","arxiv_id":"2301.03730","repositories_listed":1,"syntology":null},{"url":"/paper/table-retrieval-may-not-necessitate-table","slug":"table-retrieval-may-not-necessitate-table","title":"Table Retrieval May Not Necessitate Table-specific Model Design","date":"2022-05-19","arxiv_id":"2205.09843","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"11 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; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/table-retrieval-may-not-necessitate-table#ran","syntology_url":"https://syntology.ai/paper/2205.09843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09843"}},"official":{"repos":["zorazrw/nqt-retrieval"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/binding-actions-to-objects-in-world-models","slug":"binding-actions-to-objects-in-world-models","title":"Binding Actions to Objects in World Models","date":"2022-04-27","arxiv_id":"2204.13022","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/binding-actions-to-objects-in-world-models#ran","syntology_url":"https://syntology.ai/paper/2204.13022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.13022"}},"official":{"repos":["ondrejba/action_attention_iclr_22"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"url":"/paper/consistency-driven-sequential-transformers","slug":"consistency-driven-sequential-transformers","title":"Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes","date":"2022-04-01","arxiv_id":"2204.00656","repositories_listed":1,"syntology":null},{"url":"/paper/a-probabilistic-hard-attention-model-for","slug":"a-probabilistic-hard-attention-model-for","title":"A Probabilistic Hard Attention Model For Sequentially Observed Scenes","date":"2021-11-15","arxiv_id":"2111.07534","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-interlocking-dynamics-of","slug":"understanding-interlocking-dynamics-of","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","date":"2021-10-26","arxiv_id":"2110.13880","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/understanding-interlocking-dynamics-of#ran","syntology_url":"https://syntology.ai/paper/2110.13880","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13880"}},"official":{"repos":["gorov/understanding_interlocking"],"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":["official"]}}},{"url":"/paper/self-attention-networks-can-process-bounded","slug":"self-attention-networks-can-process-bounded","title":"Self-Attention Networks Can Process Bounded Hierarchical Languages","date":"2021-05-24","arxiv_id":"2105.11115","repositories_listed":1,"syntology":null},{"url":"/paper/amr-parsing-with-action-pointer-transformer","slug":"amr-parsing-with-action-pointer-transformer","title":"AMR Parsing with Action-Pointer Transformer","date":"2021-04-29","arxiv_id":"2104.14674","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_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) · 1 unverified","sample_list":"/paper/amr-parsing-with-action-pointer-transformer#ran","syntology_url":"https://syntology.ai/paper/2104.14674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14674"}},"official":null}},{"url":"/paper/fanet-a-feedback-attention-network-for","slug":"fanet-a-feedback-attention-network-for","title":"FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation","date":"2021-03-31","arxiv_id":"2103.17235","repositories_listed":1,"syntology":null},{"url":"/paper/hard-attention-for-scalable-image","slug":"hard-attention-for-scalable-image","title":"Hard-Attention for Scalable Image Classification","date":"2021-02-20","arxiv_id":"2102.10212","repositories_listed":1,"syntology":null},{"url":"/paper/a-hybrid-attention-mechanism-for-weakly","slug":"a-hybrid-attention-mechanism-for-weakly","title":"A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization","date":"2021-01-03","arxiv_id":"2101.00545","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-transformers-with-approximate-1","slug":"optimizing-transformers-with-approximate-1","title":"AxFormer: Accuracy-driven Approximation of Transformers for Faster, Smaller and more Accurate NLP Models","date":"2020-10-07","arxiv_id":"2010.03688","repositories_listed":1,"syntology":null},{"url":"/paper/read-highlight-and-summarize-a-hierarchical","slug":"read-highlight-and-summarize-a-hierarchical","title":"Read, Highlight and Summarize: A Hierarchical Neural Semantic Encoder-based Approach","date":"2019-10-08","arxiv_id":"1910.03177","repositories_listed":1,"syntology":null},{"url":"/paper/neural-architectures-for-nested-ner-through-1","slug":"neural-architectures-for-nested-ner-through-1","title":"Neural Architectures for Nested NER through Linearization","date":"2019-08-19","arxiv_id":"1908.06926","repositories_listed":1,"syntology":null},{"url":"/paper/graph-representation-learning-via-hard-and","slug":"graph-representation-learning-via-hard-and","title":"Graph Representation Learning via Hard and Channel-Wise Attention Networks","date":"2019-07-05","arxiv_id":"1907.04652","repositories_listed":1,"syntology":null},{"url":"/paper/190600672","slug":"190600672","title":"Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS","date":"2019-06-03","arxiv_id":"1906.00672","repositories_listed":1,"syntology":null},{"url":"/paper/surprisingly-easy-hard-attention-for-sequence","slug":"surprisingly-easy-hard-attention-for-sequence","title":"Surprisingly Easy Hard-Attention for Sequence to Sequence Learning","date":"2018-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-visual-question-answering-by","slug":"learning-visual-question-answering-by","title":"Learning Visual Question Answering by Bootstrapping Hard Attention","date":"2018-08-01","arxiv_id":"1808.00300","repositories_listed":1,"syntology":null},{"url":"/paper/latent-alignment-and-variational-attention","slug":"latent-alignment-and-variational-attention","title":"Latent Alignment and Variational Attention","date":"2018-07-10","arxiv_id":"1807.03756","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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) · 1 unverified","sample_list":"/paper/latent-alignment-and-variational-attention#ran","syntology_url":"https://syntology.ai/paper/1807.03756","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.03756"}},"official":{"repos":["harvardnlp/var-attn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sequence-to-sequence-models-for-cache","slug":"sequence-to-sequence-models-for-cache","title":"Sequence-to-sequence Models for Cache Transition Systems","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/reinforced-self-attention-network-a-hybrid-of","slug":"reinforced-self-attention-network-a-hybrid-of","title":"Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling","date":"2018-01-31","arxiv_id":"1801.10296","repositories_listed":1,"syntology":null},{"url":"/paper/morphological-inflection-generation-with-hard","slug":"morphological-inflection-generation-with-hard","title":"Morphological Inflection Generation with Hard Monotonic Attention","date":"2016-11-04","arxiv_id":"1611.01487","repositories_listed":1,"syntology":null},{"url":"/paper/progressive-attention-networks-for-visual","slug":"progressive-attention-networks-for-visual","title":"Progressive Attention Networks for Visual Attribute Prediction","date":"2016-06-08","arxiv_id":"1606.02393","repositories_listed":1,"syntology":null},{"url":null,"slug":"comparison-of-different-unique-hard-attention","title":"Comparison of different Unique hard attention transformer models by the formal languages they can recognize","date":"2025-06-03","arxiv_id":"2506.03370","repositories_listed":0,"syntology":null},{"url":null,"slug":"characterizing-the-expressivity-of","title":"Characterizing the Expressivity of Transformer Language Models","date":"2025-05-29","arxiv_id":"2505.23623","repositories_listed":0,"syntology":null},{"url":null,"slug":"exact-expressive-power-of-transformers-with","title":"Exact Expressive Power of Transformers with Padding","date":"2025-05-25","arxiv_id":"2505.18948","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergence-of-fixational-and-saccadic","title":"Emergence of Fixational and Saccadic Movements in a Multi-Level Recurrent Attention Model for Vision","date":"2025-05-19","arxiv_id":"2505.13191","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11199","title":"NoPE: The Counting Power of Transformers with No Positional Encodings","date":"2025-05-16","arxiv_id":"2505.11199","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuroevolution-of-self-attention-over-proto","title":"Neuroevolution of Self-Attention Over Proto-Objects","date":"2025-04-30","arxiv_id":"2505.00186","repositories_listed":0,"syntology":null},{"url":null,"slug":"attentiondrop-a-novel-regularization-method","title":"AttentionDrop: A Novel Regularization Method for Transformer Models","date":"2025-04-16","arxiv_id":"2504.12088","repositories_listed":0,"syntology":null},{"url":null,"slug":"unique-hard-attention-a-tale-of-two-sides","title":"Unique Hard Attention: A Tale of Two Sides","date":"2025-03-18","arxiv_id":"2503.14615","repositories_listed":0,"syntology":null},{"url":null,"slug":"lower-bounds-for-chain-of-thought-reasoning","title":"Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers","date":"2025-02-04","arxiv_id":"2502.02393","repositories_listed":0,"syntology":null},{"url":null,"slug":"ehrenfeucht-haussler-rank-and-chain-of","title":"Ehrenfeucht-Haussler Rank and Chain of Thought","date":"2025-01-22","arxiv_id":"2501.12997","repositories_listed":0,"syntology":null},{"url":null,"slug":"simulating-hard-attention-using-soft","title":"Simulating Hard Attention Using Soft Attention","date":"2024-12-13","arxiv_id":"2412.09925","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformers-in-uniform-tc-0","title":"Transformers in Uniform TC$^0$","date":"2024-09-20","arxiv_id":"2409.13629","repositories_listed":0,"syntology":null},{"url":null,"slug":"soft-hard-attention-u-net-model-and-benchmark","title":"Soft-Hard Attention U-Net Model and Benchmark Dataset for Multiscale Image Shadow Removal","date":"2024-08-07","arxiv_id":"2408.03734","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformers-as-transducers","title":"Transformers as Transducers","date":"2024-04-02","arxiv_id":"2404.02040","repositories_listed":0,"syntology":null},{"url":null,"slug":"gqhan-a-grover-inspired-quantum-hard","title":"GQHAN: A Grover-inspired Quantum Hard Attention Network","date":"2024-01-25","arxiv_id":"2401.14089","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-unsupervised-image-generation-with","title":"Multi-View Unsupervised Image Generation with Cross Attention Guidance","date":"2023-12-07","arxiv_id":"2312.04337","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-diffusion-with-stamina-stack-and","title":"Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters","date":"2023-11-30","arxiv_id":"2311.18763","repositories_listed":0,"syntology":null},{"url":null,"slug":"masked-hard-attention-transformers-and","title":"Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages","date":"2023-10-21","arxiv_id":"2310.13897","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-attention-for-few-shot-learning","title":"Language-Guided Reinforcement Learning for Hard Attention in Few-Shot Learning","date":"2023-10-11","arxiv_id":"2310.07800","repositories_listed":0,"syntology":null},{"url":null,"slug":"logical-languages-accepted-by-transformer","title":"Logical Languages Accepted by Transformer Encoders with Hard Attention","date":"2023-10-05","arxiv_id":"2310.03817","repositories_listed":0,"syntology":null},{"url":null,"slug":"average-hard-attention-transformers-are","title":"Average-Hard Attention Transformers are Constant-Depth Uniform Threshold Circuits","date":"2023-08-06","arxiv_id":"2308.03212","repositories_listed":0,"syntology":null},{"url":null,"slug":"mesaha-net-multi-encoders-based-self-adaptive","title":"MESAHA-Net: Multi-Encoders based Self-Adaptive Hard Attention Network with Maximum Intensity Projections for Lung Nodule Segmentation in CT Scan","date":"2023-04-04","arxiv_id":"2304.01576","repositories_listed":0,"syntology":null},{"url":null,"slug":"mimicking-a-pathologist-dual-attention-model","title":"Dual Attention Model with Reinforcement Learning for Classification of Histology Whole-Slide Images","date":"2023-02-19","arxiv_id":"2302.09682","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-pneumonia-attention-based-contrastive","title":"Deep Pneumonia: Attention-Based Contrastive Learning for Class-Imbalanced Pneumonia Lesion Recognition in Chest X-rays","date":"2022-07-23","arxiv_id":"2207.11393","repositories_listed":0,"syntology":null},{"url":null,"slug":"formal-language-recognition-by-hard-attention","title":"Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity","date":"2022-04-13","arxiv_id":"2204.06618","repositories_listed":0,"syntology":null},{"url":"/paper/video-violence-recognition-and-localization","slug":"video-violence-recognition-and-localization","title":"Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model","date":"2022-02-04","arxiv_id":"2202.02212","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-only-need-one-model-for-open-domain","title":"You Only Need One Model for Open-domain Question Answering","date":"2021-12-14","arxiv_id":"2112.07381","repositories_listed":0,"syntology":null},{"url":null,"slug":"claws-contrastive-learning-with-hard","title":"CLAWS: Contrastive Learning with hard Attention and Weak Supervision","date":"2021-12-01","arxiv_id":"2112.00847","repositories_listed":0,"syntology":null},{"url":null,"slug":"sharp-attention-for-sequence-to-sequence","title":"Sharp Attention for Sequence to Sequence Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"specialized-transformers-faster-smaller-and","title":"Specialized Transformers: Faster, Smaller and more Accurate NLP Models","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-power-of-saturated-transformers-a-view","title":"Saturated Transformers are Constant-Depth Threshold Circuits","date":"2021-06-30","arxiv_id":"2106.16213","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-emergent-fake-news-detection-via","title":"Multimodal Emergent Fake News Detection via Meta Neural Process Networks","date":"2021-06-22","arxiv_id":"2106.13711","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-decoupling-attention-markov-networks","title":"Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification","date":"2021-04-28","arxiv_id":"2104.13718","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-latent-monotonic-attention","title":"A study of latent monotonic attention variants","date":"2021-03-30","arxiv_id":"2103.16710","repositories_listed":0,"syntology":null},{"url":null,"slug":"hard-attention-control-by-mutual-information-1","title":"Hard Attention Control By Mutual Information Maximization","date":"2021-03-10","arxiv_id":"2103.06371","repositories_listed":0,"syntology":null},{"url":null,"slug":"achieving-explainability-in-a-visual-hard","title":"Achieving Explainability in a Visual Hard Attention Model through Content Prediction","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"near-optimal-glimpse-sequences-for-training","title":"Near-Optimal Glimpse Sequences for Training Hard Attention Neural Networks","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"amr-parsing-with-action-pointer-transformer-1","title":"AMR Parsing with Action-Pointer Transformer","date":"2020-11-24","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"danhar-dual-attention-network-for-multimodal","title":"DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensors","date":"2020-06-25","arxiv_id":"2006.14435","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiresolution-attention-extractor-for-small","title":"MultiResolution Attention Extractor for Small Object Detection","date":"2020-06-10","arxiv_id":"2006.05941","repositories_listed":0,"syntology":null},{"url":"/paper/generative-adversarial-networks-based-on-2","slug":"generative-adversarial-networks-based-on-2","title":"Generative Adversarial Networks Based on Collaborative Learning and Attention Mechanism for Hyperspectral Image Classification","date":"2020-04-03","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-attention-models-for-memory","title":"Improved Attention Models for Memory Augmented Neural Network Adaptive Controllers","date":"2020-03-19","arxiv_id":"1910.01189","repositories_listed":0,"syntology":null},{"url":null,"slug":"upper-middle-and-lower-region-learning-for","title":"Upper, Middle and Lower Region Learning for Facial Action Unit Detection","date":"2020-02-10","arxiv_id":"2002.04023","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-brain-magnetic-resonance-image","title":"Robust Brain Magnetic Resonance Image Segmentation for Hydrocephalus Patients: Hard and Soft Attention","date":"2020-01-12","arxiv_id":"2001.03857","repositories_listed":0,"syntology":null},{"url":"/paper/learning-deep-graph-matching-with-channel","slug":"learning-deep-graph-matching-with-channel","title":"Learning deep graph matching with channel-independent embedding and Hungarian attention","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"text-as-environment-a-deep-reinforcement","title":"Text as Environment: A Deep Reinforcement Learning Text Readability Assessment Model","date":"2019-12-12","arxiv_id":"1912.05957","repositories_listed":0,"syntology":null},{"url":null,"slug":"effect-of-choice-of-probability-distribution","title":"Effect of choice of probability distribution, randomness, and search methods for alignment modeling in sequence-to-sequence text-to-speech synthesis using hard alignment","date":"2019-10-28","arxiv_id":"1910.12383","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-guided-external-memory-network-for","title":"Object Guided External Memory Network for Video Object Detection","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"look-harder-a-neural-machine-translation","title":"Look Harder: A Neural Machine Translation Model with Hard Attention","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"theoretical-limitations-of-self-attention-in","title":"Theoretical Limitations of Self-Attention in Neural Sequence Models","date":"2019-06-16","arxiv_id":"1906.06755","repositories_listed":0,"syntology":null},{"url":null,"slug":"near-optimal-glimpse-sequences-for-improved","title":"Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training","date":"2019-06-13","arxiv_id":"1906.05462","repositories_listed":0,"syntology":null},{"url":null,"slug":"patchwork-a-patch-wise-attention-network-for","title":"Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streams","date":"2019-04-03","arxiv_id":"1904.01784","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-differentiable-self-disambiguated-sense","title":"A Differentiable Self-disambiguated Sense Embedding Model via Scaled Gumbel Softmax","date":"2018-09-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"extractive-adversarial-networks-high-recall","title":"Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts","date":"2018-09-01","arxiv_id":"1809.01499","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-multi-scale-attention-networks","title":"Hierarchical Multi-scale Attention Networks for Action Recognition","date":"2017-08-25","arxiv_id":"1708.07590","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-exploration-of-neural-sequence-to-sequence","title":"An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing","date":"2017-06-13","arxiv_id":"1706.04138","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-hard-alignments-with-variational","title":"Learning Hard Alignments with Variational Inference","date":"2017-05-16","arxiv_id":"1705.05524","repositories_listed":0,"syntology":null},{"url":null,"slug":"word-representation-models-for","title":"Word Representation Models for Morphologically Rich Languages in Neural Machine Translation","date":"2016-06-14","arxiv_id":"1606.04217","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-memory-networks","title":"Hierarchical Memory Networks","date":"2016-05-24","arxiv_id":"1605.07427","repositories_listed":0,"syntology":null}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":9,"papers_where_code_ran_first_page":"/task/hard-attention/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/hard-attention/papers/ran/1","json":"/task/hard-attention/papers/ran/1.json","rows":9}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"2428e5cb834eb0f13167e77d7fb08373710d1424e2dd38830705677b0da15d8c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}