{"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":"/code/bipartite-soft-matching","entry":"bipartite_soft_matching","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","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)"},"n_papers":14,"n_papers_ran":13,"n_papers_ran_no_instrument_failure":3,"n_papers_ran_instrument_only":10,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":11,"n_samples_ran":10,"n_samples_constructed":0,"n_samples_ran_checked":3,"n_samples_instrument":7,"n_samples_unverified":1,"n_samples_fingerprinted":2,"n_places":14,"n_places_pointer_only":8,"n_places_pointer_only_link_open":1,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":7,"ran":3,"unverified":1},"key_notes":{"n_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'","n_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)"},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2608.01298","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2608-01298","title":"UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"JN-Yun/UDT","path":"models/UDT.py","file_url":"https://github.com/JN-Yun/UDT/blob/HEAD/models/UDT.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, JN-Yun/UDT when it was checked","code_sha256":"64e4c00ba026c8e5","code_sha256_prefix":"64e4c00ba026c8e5","mcp_get_code":{"code_sha256":"64e4c00ba026c8e5"}},{"arxiv_id":"2511.05299","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2511-05299","title":"LiveStar: Live Streaming Assistant for Real-World Online Video Understanding","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"yzy-bupt/LiveStar","path":"inference/modeling_livestar_chat.py","file_url":"https://github.com/yzy-bupt/LiveStar/blob/HEAD/inference/modeling_livestar_chat.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, yzy-bupt/LiveStar when it was checked","code_sha256":"7b4b78698a6dbdeb","code_sha256_prefix":"7b4b78698a6dbdeb","mcp_get_code":{"code_sha256":"7b4b78698a6dbdeb"}},{"arxiv_id":"2412.10569","arxiv_id_is_arxiv":true,"paper":"/paper/learning-to-merge-tokens-via-decoupled","title":"Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers","date":"2024-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"movinghoon/dtem","path":"dtem/dtem.py","file_url":"https://github.com/movinghoon/dtem/blob/HEAD/dtem/dtem.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, movinghoon/dtem when it was checked","code_sha256":"a7408ebd9837b099","code_sha256_prefix":"a7408ebd9837b099","mcp_get_code":{"code_sha256":"a7408ebd9837b099"}},{"arxiv_id":"2409.09808","arxiv_id_is_arxiv":true,"paper":"/paper/famba-v-fast-vision-mamba-with-cross-layer","title":"Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion","date":"2024-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aiot-mlsys-lab/famba-v","path":"fambav/token_merge.py","file_url":"https://github.com/aiot-mlsys-lab/famba-v/blob/HEAD/fambav/token_merge.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, aiot-mlsys-lab/famba-v when it was checked","code_sha256":"424049f15b90678d","code_sha256_prefix":"424049f15b90678d","mcp_get_code":{"code_sha256":"424049f15b90678d"}},{"arxiv_id":"2409.01156","arxiv_id_is_arxiv":true,"paper":"/paper/tempme-video-temporal-token-merging-for","title":"TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval","date":"2024-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LunarShen/TempMe","path":"tvr/models/module_tome_patch.py","file_url":"https://github.com/LunarShen/TempMe/blob/HEAD/tvr/models/module_tome_patch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"c8bfd649bf334138","code_sha256_prefix":"c8bfd649bf334138","mcp_get_code":{"code_sha256":"c8bfd649bf334138"}},{"arxiv_id":"2404.17176","arxiv_id_is_arxiv":true,"paper":"/paper/moviechat-question-aware-sparse-memory-for","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","date":"2024-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rese1f/MovieChat","path":"MovieChat/models/eva_vit_with_tome.py","file_url":"https://github.com/rese1f/MovieChat/blob/HEAD/MovieChat/models/eva_vit_with_tome.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"54a7a818ecf43861","code_sha256_prefix":"54a7a818ecf43861","mcp_get_code":{"code_sha256":"54a7a818ecf43861"}},{"arxiv_id":"2404.09490","arxiv_id_is_arxiv":true,"paper":"/paper/leveraging-temporal-contextualization-for","title":"Leveraging Temporal Contextualization for Video Action Recognition","date":"2024-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver-ai/tc-clip","path":"clip/transformer_blocks_tc.py","file_url":"https://github.com/naver-ai/tc-clip/blob/HEAD/clip/transformer_blocks_tc.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, naver-ai/tc-clip (NOASSERTION)","code_sha256":"84cccfdd563db842","code_sha256_prefix":"84cccfdd563db842","mcp_get_code":{"code_sha256":"84cccfdd563db842"}},{"arxiv_id":"2403.10030","arxiv_id_is_arxiv":true,"paper":"/paper/multi-criteria-token-fusion-with-one-step","title":"Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers","date":"2024-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlvlab/MCTF","path":"utils/mctf.py","file_url":"https://github.com/mlvlab/MCTF/blob/HEAD/utils/mctf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"58a3d8aacef250bc","code_sha256_prefix":"58a3d8aacef250bc","mcp_get_code":{"code_sha256":"58a3d8aacef250bc"}},{"arxiv_id":"2403.09192","arxiv_id_is_arxiv":true,"paper":"/paper/pyra-parallel-yielding-re-activation-for","title":"PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation","date":"2024-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-mig/pyra","path":"model/adaptive_merge.py","file_url":"https://github.com/thu-mig/pyra/blob/HEAD/model/adaptive_merge.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b6129d06b30c292b","code_sha256_prefix":"b6129d06b30c292b","mcp_get_code":{"code_sha256":"b6129d06b30c292b"}},{"arxiv_id":"2310.19060","arxiv_id_is_arxiv":true,"paper":"/paper/testa-temporal-spatial-token-aggregation-for","title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding","date":"2023-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"renshuhuai-andy/testa","path":"testa/merge.py","file_url":"https://github.com/renshuhuai-andy/testa/blob/HEAD/testa/merge.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"87f39a589f593732","code_sha256_prefix":"87f39a589f593732","mcp_get_code":{"code_sha256":"87f39a589f593732"}},{"arxiv_id":"2310.01812","arxiv_id_is_arxiv":true,"paper":"/paper/ppt-token-pruning-and-pooling-for-efficient","title":"PPT: Token Pruning and Pooling for Efficient Vision Transformers","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xjwu1024/PPT","path":"merge.py","file_url":"https://github.com/xjwu1024/PPT/blob/HEAD/merge.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from facebookresearch/tome, and GitHub could not classify the licence of that repository (NOASSERTION)","code_sha256":"424049f15b90678d","code_sha256_prefix":"424049f15b90678d","mcp_get_code":{"code_sha256":"424049f15b90678d"}},{"arxiv_id":"2307.10780","arxiv_id_is_arxiv":true,"paper":"/paper/learned-thresholds-token-merging-and-pruning","title":"Learned Thresholds Token Merging and Pruning for Vision Transformers","date":"2023-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mxbonn/ltmp","path":"ltmp/token_merging.py","file_url":"https://github.com/mxbonn/ltmp/blob/HEAD/ltmp/token_merging.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, mxbonn/ltmp when it was checked","code_sha256":"424049f15b90678d","code_sha256_prefix":"424049f15b90678d","mcp_get_code":{"code_sha256":"424049f15b90678d"}},{"arxiv_id":"2210.09461","arxiv_id_is_arxiv":true,"paper":"/paper/token-merging-your-vit-but-faster","title":"Token Merging: Your ViT But Faster","date":"2022-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/tome","path":"tome/merge.py","file_url":"https://github.com/facebookresearch/tome/blob/HEAD/tome/merge.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, facebookresearch/tome (NOASSERTION)","code_sha256":"424049f15b90678d","code_sha256_prefix":"424049f15b90678d","mcp_get_code":{"code_sha256":"424049f15b90678d"}},{"arxiv_id":"Zhang_Beyond_Training_Dynamic_Token_Merging_for_Zero-Shot_Video_Understanding_ICCV_2025_paper","arxiv_id_is_arxiv":false,"paper":null,"title":"CVF open access id Zhang_Beyond_Training_Dynamic_Token_Merging_for_Zero-Shot_Video_Understanding_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Jam1ezhang/DYTO","path":"dyto/llava/model/merge.py","file_url":"https://github.com/Jam1ezhang/DYTO/blob/HEAD/dyto/llava/model/merge.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"4c4f5297423e8810","code_sha256_prefix":"4c4f5297423e8810","mcp_get_code":{"code_sha256":"4c4f5297423e8810"}}],"record_sha256":"562a4eade82bd20cc91b32dd0cc6377aa9e4afda2fc7f12151076d5b7b911bac","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}