{"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/multimodal-interaction/papers/ran/1","list_of":"/task/multimodal-interaction","task":"multimodal interaction","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","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.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,9],"of":9,"counts":{"archive_papers_tagged":106,"with_a_code_link":41,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":106,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":9,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":9,"listed_every_run_a_failure_of_syntologys_instrument":0,"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":"/task/multimodal-interaction/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/i2moe-interpretable-multimodal-interaction","slug":"i2moe-interpretable-multimodal-interaction","title":"I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts","date":"2025-05-25","arxiv_id":"2505.19190","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/i2moe-interpretable-multimodal-interaction#ran","syntology_url":"https://syntology.ai/paper/2505.19190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19190"}},"official":{"repos":["raina-xin/i2moe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ovtr-end-to-end-open-vocabulary-multiple","slug":"ovtr-end-to-end-open-vocabulary-multiple","title":"OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer","date":"2025-03-13","arxiv_id":"2503.10616","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ovtr-end-to-end-open-vocabulary-multiple#ran","syntology_url":"https://syntology.ai/paper/2503.10616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10616"}},"official":{"repos":["jinyanglii/ovtr"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dissecting-dissonance-benchmarking-large","slug":"dissecting-dissonance-benchmarking-large","title":"Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions","date":"2024-08-02","arxiv_id":"2408.01091","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dissecting-dissonance-benchmarking-large#ran","syntology_url":"https://syntology.ai/paper/2408.01091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01091"}},"official":{"repos":["shiyegao/Self-Contradictory-Instructions-SCI"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tip-tabular-image-pre-training-for-multimodal","slug":"tip-tabular-image-pre-training-for-multimodal","title":"TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Data","date":"2024-07-10","arxiv_id":"2407.07582","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/tip-tabular-image-pre-training-for-multimodal#ran","syntology_url":"https://syntology.ai/paper/2407.07582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07582"}},"official":{"repos":["siyi-wind/tip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/look-m-look-once-optimization-in-kv-cache-for","slug":"look-m-look-once-optimization-in-kv-cache-for","title":"LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference","date":"2024-06-26","arxiv_id":"2406.18139","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/look-m-look-once-optimization-in-kv-cache-for#ran","syntology_url":"https://syntology.ai/paper/2406.18139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18139"}},"official":{"repos":["sustechbruce/look-m"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/agent-ai-surveying-the-horizons-of-multimodal","slug":"agent-ai-surveying-the-horizons-of-multimodal","title":"Agent AI: Surveying the Horizons of Multimodal Interaction","date":"2024-01-07","arxiv_id":"2401.03568","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent-ai-surveying-the-horizons-of-multimodal#ran","syntology_url":"https://syntology.ai/paper/2401.03568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03568"}},"official":{"repos":["guilk/kat"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mmoe-mixture-of-multimodal-interaction","slug":"mmoe-mixture-of-multimodal-interaction","title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts","date":"2023-11-16","arxiv_id":"2311.09580","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mmoe-mixture-of-multimodal-interaction#ran","syntology_url":"https://syntology.ai/paper/2311.09580","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09580"}},"official":{"repos":["lwaekfjlk/mmoe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modal-implicit-relation-reasoning-and","slug":"cross-modal-implicit-relation-reasoning-and","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","date":"2023-03-22","arxiv_id":"2303.12501","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/cross-modal-implicit-relation-reasoning-and#ran","syntology_url":"https://syntology.ai/paper/2303.12501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12501"}},"official":{"repos":["anosorae/irra"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/vilt-vision-and-language-transformer-without","slug":"vilt-vision-and-language-transformer-without","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","date":"2021-02-05","arxiv_id":"2102.03334","repositories_listed":6,"syntology":{"n":4,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/vilt-vision-and-language-transformer-without#ran","syntology_url":"https://syntology.ai/paper/2102.03334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.03334"}},"official":{"repos":["dandelin/vilt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}}],"record_sha256":"4507bd907222db4823196e7ed0b252956483d5143ab37765c7563c27c6c1c479","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}