{"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":"/ran/5","feed":"ran","feed_label":"Code that ran","page":5,"n_pages":10,"per_stream_per_page":15,"claim":"Per-sample execution status on synthesized fixtures; 'ran' is not a correctness claim about the paper. n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code.","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)","samples_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'","samples_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)","papers_ran_checked":"legacy name, kept unchanged so existing readers do not break: papers with at least one sample that ran with no instrument failure (honoured, violated, or ran with no contract checked); it does not mean a contract was checked"},"sample_gap":{"source":"syntology-graph","read_at":"2026-10-05T00:36:11+00:00","samples":294260,"samples_ran":211169,"samples_constructed":22388,"samples_ran_checked":147384,"samples_instrument":63785,"samples_unverified":83091,"samples_by_status":{"ran_honours":15745,"ran_violates":5703,"ran_draft_wrong":50332,"ran_fixture":13453,"ran":125936,"unverified":83091},"ran":{"n_ran":211169,"n_constructed":22388,"n_ran_checked":147384,"n_instrument":63785,"n_honours":15745,"n_violates":5703,"n_no_contract":125936,"n_draft_wrong":50332,"n_check_could_not_run":13453,"n_unverified":83091},"ran_phrase":"211,169 ran (of which 22,388 constructed an object rather than computing a result; 147,384 with no instrument failure: 15,745 honoured, 5,703 violated, 125,936 with no contract checked; 63,785 where Syntology's instrument failed) · 83,091 unverified","papers_harvested":51887,"papers_ran":48557,"papers_ran_checked":40099,"papers_ran_instrument_only":8458,"papers_harvested_nothing_ran":3330,"papers_without_a_page":{"papers":2441,"non_arxiv":1954,"non_arxiv_by_family":{"acl_anthology":731,"cvf":489,"aaai":439,"ijcai":117,"openreview":96,"bare_number":82},"pre_snapshot":487,"other":0,"links":18061,"samples_distinct":16187,"papers_with_a_ran_sample":2343,"counted_in_totals":true,"rule":"papers in Syntology's layer with harvested samples and no page here; counted in the headline sample and paper totals they already inflate; never given a page or a syntology.ai link (a non-arXiv id is never read as an arXiv id); the ids are repaired upstream in export_graph_layer.py, not here","sentence":"Papers in Syntology's layer with harvested samples and no page here: 2,441. Of these, 1,954 carry an id in the export that is not an arXiv id (731 ACL Anthology ids, 489 CVF open access ids, 439 AAAI ids, 117 IJCAI ids, 96 OpenReview ids, 82 bare-number ids), and 487 have an arXiv id from before the snapshot that the archive catalogue does not hold. Their 18,061 sample links, and the 2,343 of these papers with a sample that ran, are counted in the site's sample and paper totals"},"sample":"one function or class; identical code under several papers counted once"},"streams":{"post_freeze":{"source":"syntology-graph","read_at":"2026-10-05T00:36:11+00:00","order":"arXiv id descending","dates":"arXiv's metadata (CC0) where held; otherwise month_from_arxiv_id","n_with_arxiv_metadata":6651,"first":61,"last":75,"total":6651,"n_in_feed":150,"papers_ran_split":{"with_a_sample_that_ran":6651,"with_a_run_with_no_instrument_failure":5550,"every_run_a_failure_of_syntologys_instrument":1101,"of":"the stream's total (every paper it lists, over all its pages)"},"excluded":{"no_yymm_arxiv_id":0},"cards":[{"kind":"post","source":"syntology-graph","title":"Robust Policy Optimization via Adversarial Importance Sampling","url":"/paper/arxiv-2609-13044","arxiv_id":"2609.13044","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/AmineAndam04/advrl","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":3,"official":null}},{"kind":"post","source":"syntology-graph","title":"Dual-guided Hierarchical Edge Localization for Large-scale Optimal Transport Across Dimensions","url":"/paper/arxiv-2609-13010","arxiv_id":"2609.13010","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/WenzhouXia/hello-ot","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":11,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":3,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":null}},{"kind":"post","source":"syntology-graph","title":"Judging by the Cover: Cleaning LLM Truthfulness Benchmarks to Avoid Surface-Level Feature Leakage","url":"/paper/arxiv-2609-13003","arxiv_id":"2609.13003","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/foadnamjoo/audit-prune","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":null}},{"kind":"post","source":"syntology-graph","title":"Generative Retrieval for Unsupervised Text-Based Person Search","url":"/paper/arxiv-2609-12965","arxiv_id":"2609.12965","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/Flame-Chasers/GTR","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":7,"official":null}},{"kind":"post","source":"syntology-graph","title":"LLM-Enhanced Dual-Branch Learning for Large-Scale Multi-Label Text Classification","url":"/paper/arxiv-2609-12915","arxiv_id":"2609.12915","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/huiyegit/DualMLC","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":8,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":null}},{"kind":"post","source":"syntology-graph","title":"Cognition on Graph: Navigating Massive Knowledge Space via Cognitive Cycles and Bidirectional Graph-Text Synergy","url":"/paper/arxiv-2609-12791","arxiv_id":"2609.12791","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/zhougengxian/CoG","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":19,"n_ran":17,"n_constructed":0,"n_ran_checked":10,"n_instrument":7,"n_unverified":2,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":null}},{"kind":"post","source":"syntology-graph","title":"Optimizing for the decision not the prediction: an exploration of Smooth Net Benefit as a training objective","url":"/paper/arxiv-2609-12752","arxiv_id":"2609.12752","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/KoenGorgels/Smooth-Net-Benefit","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":11,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":11,"official":null}},{"kind":"post","source":"syntology-graph","title":"Physics-Guided Synthetic High-Frequency Ultrasound Generation for Skin Layer Segmentation","url":"/paper/arxiv-2609-12735","arxiv_id":"2609.12735","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/Finn-02/synthetic-hfus-skin-layer-segmentation","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":23,"n_ran":19,"n_constructed":0,"n_ran_checked":11,"n_instrument":8,"n_unverified":4,"n_ran_honours":4,"n_ran_violates":0,"n_pointer_only_for_licence":23,"official":null}},{"kind":"post","source":"syntology-graph","title":"InRTL: Effective Intra-Inter Interaction Learning for Relational Tables","url":"/paper/arxiv-2609-12712","arxiv_id":"2609.12712","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/W1nterFloW/InRTL","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_ran_honours":1,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":null}},{"kind":"post","source":"syntology-graph","title":"LifeMem: Enabling Lifelong Experience Reuse for LLM Agents","url":"/paper/arxiv-2609-12655","arxiv_id":"2609.12655","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/BITHLP/LifeMem","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":8,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":2,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":8,"official":null}},{"kind":"post","source":"syntology-graph","title":"SWARM: A Multilingual Human-Annotated Dataset for Russian Propaganda Detection in Search Engine Results","url":"/paper/arxiv-2609-12653","arxiv_id":"2609.12653","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/manueltonneau/swarm","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":26,"n_ran":22,"n_constructed":0,"n_ran_checked":8,"n_instrument":14,"n_unverified":4,"n_ran_honours":3,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":null}},{"kind":"post","source":"syntology-graph","title":"Explaining Time Series Forecasting with Horizon-Resolved Attribution","url":"/paper/arxiv-2609-12639","arxiv_id":"2609.12639","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/seunghan96/HRX","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":12,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":2,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":null}},{"kind":"post","source":"syntology-graph","title":"RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation","url":"/paper/arxiv-2609-12622","arxiv_id":"2609.12622","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/zaoxienian/RA-SOD","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":8,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":null}},{"kind":"post","source":"syntology-graph","title":"Clustering-Based Balanced Sampling and Allocation with Data Parallelism for High-Performance Fine-Tuning","url":"/paper/arxiv-2609-12584","arxiv_id":"2609.12584","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/kaist-dmlab/CluSTER","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":10,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":null}},{"kind":"post","source":"syntology-graph","title":"RoES: Rotational Equivariant Selective-frequency Fusion for Multimodal Images","url":"/paper/arxiv-2609-12497","arxiv_id":"2609.12497","date":"2026-09-11","month_from_arxiv_id":null,"title_date_abstract_source":"arXiv metadata, CC0 1.0","repo_url":"https://github.com/BryceLosky/RoES-Fusion","n_repos":1,"official":false,"framework":null,"tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_ran_honours":1,"n_ran_violates":0,"n_pointer_only_for_licence":5,"official":null}}]},"archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","filter":"repository link and at least one Syntology-ran sample","order":"archive date descending; an undated row is placed by its arXiv-id month after that month's dated rows","first":61,"last":75,"total":38710,"n_in_feed":150,"papers_ran_split":{"with_a_sample_that_ran":38710,"with_a_run_with_no_instrument_failure":31633,"every_run_a_failure_of_syntologys_instrument":7077,"of":"the stream's total (every paper it lists, over all its pages)"},"n_placed_by_arxiv_id_month":1274,"n_dated_after_snapshot":0,"max_archive_date":"2025-07-17","excluded":{"no_date_no_arxiv_id":8,"code_link_without_paper_row":1},"cards":[{"kind":"archive","source":"pwc-archive","title":"Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer","url":"/paper/latent-chain-of-thought-decoding-the-depth","arxiv_id":"2507.02199","date":"2025-07-02","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/wenquanlu/huginn-latent-cot","n_repos":1,"official":true,"framework":"pytorch","tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":11,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_ran_honours":1,"n_ran_violates":2,"n_pointer_only_for_licence":11,"official":{"repos":["wenquanlu/huginn-latent-cot"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"kind":"archive","source":"pwc-archive","title":"Energy-Based Transformers are Scalable Learners and Thinkers","url":"/paper/energy-based-transformers-are-scalable","arxiv_id":"2507.02092","date":"2025-07-02","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/alexiglad/EBT","n_repos":1,"official":true,"framework":"pytorch","tasks":[{"slug":"denoising","name":"Denoising","url":"/task/denoising"},{"slug":"image-denoising","name":"Image Denoising","url":"/task/image-denoising"},{"slug":"math","name":"Math","url":"/task/math"}],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_ran_honours":0,"n_ran_violates":1,"n_pointer_only_for_licence":1,"official":{"repos":["alexiglad/EBT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"kind":"archive","source":"pwc-archive","title":"Kwai Keye-VL Technical Report","url":"/paper/kwai-keye-vl-technical-report","arxiv_id":"2507.01949","date":"2025-07-02","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/kwai-keye/keye","n_repos":1,"official":true,"framework":"pytorch","tasks":[{"slug":"instruction-following","name":"Instruction Following","url":"/task/instruction-following"},{"slug":"reinforcement-learning-1","name":"Reinforcement Learning (RL)","url":"/task/reinforcement-learning-1"},{"slug":"video-understanding","name":"Video Understanding","url":"/task/video-understanding"}],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":13,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":2,"n_ran_honours":5,"n_ran_violates":0,"n_pointer_only_for_licence":13,"official":{"repos":["kwai-keye/keye"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"kind":"archive","source":"pwc-archive","title":"GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","url":"/paper/glm-4-1v-thinking-towards-versatile","arxiv_id":"2507.01006","date":"2025-07-01","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/thudm/glm-4.1v-thinking","n_repos":1,"official":true,"framework":null,"tasks":[{"slug":"multimodal-reasoning","name":"Multimodal Reasoning","url":"/task/multimodal-reasoning"},{"slug":"video-understanding","name":"Video Understanding","url":"/task/video-understanding"},{"slug":"document-understanding","name":"document understanding","url":"/task/document-understanding"}],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":11,"n_ran":11,"n_constructed":0,"n_ran_checked":1,"n_instrument":10,"n_unverified":0,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":{"repos":["thudm/glm-4.1v-thinking"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"kind":"archive","source":"pwc-archive","title":"LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling","url":"/paper/ld-rps-zero-shot-unified-image-restoration","arxiv_id":"2507.00790","date":"2025-07-01","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/amap-ml/ld-rps","n_repos":1,"official":true,"framework":"jax","tasks":[{"slug":"image-restoration","name":"Image Restoration","url":"/task/image-restoration"},{"slug":"unified-image-restoration","name":"Unified Image Restoration","url":"/task/unified-image-restoration"}],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_ran_honours":4,"n_ran_violates":0,"n_pointer_only_for_licence":8,"official":{"repos":["amap-ml/ld-rps"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"kind":"archive","source":"pwc-archive","title":"UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions","url":"/paper/umdatrack-unified-multi-domain-adaptive","arxiv_id":"2507.00648","date":"2025-07-01","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/z-z188/umdatrack","n_repos":1,"official":true,"framework":"pytorch","tasks":[{"slug":"domain-adaptation","name":"Domain Adaptation","url":"/task/domain-adaptation"},{"slug":"object-tracking","name":"Object Tracking","url":"/task/object-tracking"},{"slug":"visual-object-tracking","name":"Visual Object Tracking","url":"/task/visual-object-tracking"}],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_ran_honours":1,"n_ran_violates":0,"n_pointer_only_for_licence":1,"official":{"repos":["z-z188/umdatrack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"kind":"archive","source":"pwc-archive","title":"LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs","url":"/paper/llava-sp-enhancing-visual-representation-with","arxiv_id":"2507.00505","date":"2025-07-01","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/cnfaker/llava-sp","n_repos":1,"official":true,"framework":"pytorch","tasks":[{"slug":"large-language-model","name":"Large Language Model","url":"/task/large-language-model"}],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":8,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":0,"n_ran_honours":0,"n_ran_violates":1,"n_pointer_only_for_licence":1,"official":{"repos":["cnfaker/llava-sp"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"kind":"archive","source":"pwc-archive","title":"SE(3)-Equivariant Diffusion Policy in Spherical Fourier Space","url":"/paper/se-3-equivariant-diffusion-policy-in-1","arxiv_id":"2507.01723","date":null,"month_from_arxiv_id":"2025-07","title_date_abstract_source":null,"repo_url":"https://github.com/amazon-science/Spherical_Diffusion_Policy","n_repos":1,"official":true,"framework":"pytorch","tasks":[],"n_task_tags_without_task_page":0,"ranked_on":[{"leaderboard":"/sota/robot-manipulation-on-mimicgen","task":"Robot Manipulation","dataset":"MimicGen"}],"n_ranked_on":1,"venue":null,"syntology":{"n_samples":14,"n_ran":7,"n_constructed":6,"n_ran_checked":7,"n_instrument":0,"n_unverified":7,"n_ran_honours":1,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":{"repos":["amazon-science/Spherical_Diffusion_Policy"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["official"]}}},{"kind":"archive","source":"pwc-archive","title":"RAG-R1 : Incentivize the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism","url":"/paper/rag-r1-incentivize-the-search-and-reasoning","arxiv_id":"2507.02962","date":"2025-06-30","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/inclusionai/aworld","n_repos":1,"official":false,"framework":null,"tasks":[{"slug":"question-answering","name":"Question Answering","url":"/task/question-answering"},{"slug":"rag","name":"RAG","url":"/task/rag"},{"slug":"reinforcement-learning-1","name":"Reinforcement Learning (RL)","url":"/task/reinforcement-learning-1"},{"slug":"retrieval","name":"Retrieval","url":"/task/retrieval"},{"slug":"retrieval-augmented-generation","name":"Retrieval-augmented Generation","url":"/task/retrieval-augmented-generation"}],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":null}},{"kind":"archive","source":"pwc-archive","title":"FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation","url":"/paper/fadrm-fast-and-accurate-data-residual","arxiv_id":"2506.24125","date":"2025-06-30","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/jiacheng8/fadrm","n_repos":1,"official":true,"framework":"pytorch","tasks":[{"slug":"computational-efficiency","name":"Computational Efficiency","url":"/task/computational-efficiency"},{"slug":"dataset-distillation","name":"Dataset Distillation","url":"/task/dataset-distillation"}],"n_task_tags_without_task_page":1,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":18,"n_ran":17,"n_constructed":0,"n_ran_checked":5,"n_instrument":12,"n_unverified":1,"n_ran_honours":3,"n_ran_violates":1,"n_pointer_only_for_licence":3,"official":{"repos":["jiacheng8/fadrm"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"kind":"archive","source":"pwc-archive","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","url":"/paper/spiral-self-play-on-zero-sum-games","arxiv_id":"2506.24119","date":"2025-06-30","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/spiral-rl/spiral","n_repos":1,"official":true,"framework":null,"tasks":[{"slug":"math","name":"Math","url":"/task/math"},{"slug":"multi-agent-reinforcement-learning","name":"Multi-agent Reinforcement Learning","url":"/task/multi-agent-reinforcement-learning"}],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":9,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":0,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":{"repos":["spiral-rl/spiral"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"kind":"archive","source":"pwc-archive","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","url":"/paper/flash-vstream-efficient-real-time","arxiv_id":"2506.23825","date":"2025-06-30","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/IVGSZ/Flash-VStream","n_repos":1,"official":true,"framework":"pytorch","tasks":[{"slug":"mme","name":"MME","url":"/task/mme"},{"slug":"video-understanding","name":"Video Understanding","url":"/task/video-understanding"},{"slug":"cross-modal-alignment","name":"cross-modal alignment","url":"/task/cross-modal-alignment"}],"n_task_tags_without_task_page":3,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":11,"n_ran":7,"n_constructed":0,"n_ran_checked":0,"n_instrument":7,"n_unverified":4,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":{"repos":["IVGSZ/Flash-VStream"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"kind":"archive","source":"pwc-archive","title":"Dataset Distillation via Vision-Language Category Prototype","url":"/paper/dataset-distillation-via-vision-language","arxiv_id":"2506.23580","date":"2025-06-30","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/Guang000/Awesome-Dataset-Distillation","n_repos":2,"official":true,"framework":null,"tasks":[{"slug":"dataset-distillation","name":"Dataset Distillation","url":"/task/dataset-distillation"},{"slug":"descriptive","name":"Descriptive","url":"/task/descriptive"},{"slug":"large-language-model","name":"Large Language Model","url":"/task/large-language-model"}],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":2,"official":{"repos":["Guang000/Awesome-Dataset-Distillation","zou-yawen/dataset-distillation-via-vision-language-category-prototype"],"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"]}}},{"kind":"archive","source":"pwc-archive","title":"NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments","url":"/paper/navmorph-a-self-evolving-world-model-for","arxiv_id":"2506.23468","date":"2025-06-30","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/feliciaxyao/navmorph","n_repos":1,"official":true,"framework":"pytorch","tasks":[{"slug":"decision-making","name":"Decision Making","url":"/task/decision-making"},{"slug":"vision-and-language-navigation","name":"Vision and Language Navigation","url":"/task/vision-and-language-navigation"}],"n_task_tags_without_task_page":0,"ranked_on":[],"n_ranked_on":0,"venue":null,"syntology":{"n_samples":12,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":1,"n_ran_honours":1,"n_ran_violates":1,"n_pointer_only_for_licence":12,"official":{"repos":["feliciaxyao/navmorph"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"kind":"archive","source":"pwc-archive","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","url":"/paper/memfof-high-resolution-training-for-memory","arxiv_id":"2506.23151","date":"2025-06-29","month_from_arxiv_id":null,"title_date_abstract_source":null,"repo_url":"https://github.com/msu-video-group/memfof","n_repos":1,"official":true,"framework":"pytorch","tasks":[{"slug":"optical-flow-estimation","name":"Optical Flow Estimation","url":"/task/optical-flow-estimation"}],"n_task_tags_without_task_page":1,"ranked_on":[{"leaderboard":"/sota/optical-flow-estimation-on-sintel-clean","task":"Optical Flow Estimation","dataset":"Sintel-clean"},{"leaderboard":"/sota/optical-flow-estimation-on-sintel-final","task":"Optical Flow Estimation","dataset":"Sintel-final"},{"leaderboard":"/sota/optical-flow-estimation-on-kitti-2015-train","task":"Optical Flow Estimation","dataset":"KITTI 2015 (train)"},{"leaderboard":"/sota/optical-flow-estimation-on-kitti-2015","task":"Optical Flow Estimation","dataset":"KITTI 2015"}],"n_ranked_on":5,"venue":null,"syntology":{"n_samples":13,"n_ran":9,"n_constructed":7,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_ran_honours":0,"n_ran_violates":0,"n_pointer_only_for_licence":0,"official":{"repos":["msu-video-group/memfof"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":7,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}}]}},"record_sha256":"bce09a725a769573d6cdef29f4726571d29e6b79057ff0e141d595ae63214cdc","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}