{"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/audio-visual-question-answering","name":"Audio-visual Question Answering","slug":"audio-visual-question-answering","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":27,"papers_with_code":19,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":2,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/audio-visual-question-answering-on-music-avqa","slug":"audio-visual-question-answering-on-music-avqa","dataset":"MUSIC-AVQA","dataset_url":"/dataset/music-avqa","rows_in_archive":6,"metrics":["Acc"],"first_row_in_archive_order":{"model":"VAST","paper_title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","paper_url":"/paper/vast-a-vision-audio-subtitle-text-omni-1","paper_date":"2023-05-29","arxiv_id":"2305.18500","code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"},{"title":"txh-mercury/vast","url":"https://github.com/txh-mercury/vast"}],"syntology":{"n":42,"n_ran":35,"n_constructed":4,"n_ran_checked":25,"n_instrument":10,"n_unverified":7,"n_honours":4,"n_violates":1,"n_no_contract":20,"n_pointer_only":8,"phrase":"35 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 1 violated, 20 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}},"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}}],"datasets":[{"url":"/dataset/music-avqa","name":"MUSIC-AVQA","full_name":"","num_papers_in_archive":51},{"url":"/dataset/music-avqa-v2-0","name":"MUSIC-AVQA v2.0","full_name":"","num_papers_in_archive":5}],"subtasks":[{"url":"/task/audio-visual-question-answering-music-avqa-v2","name":"AUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0)"}],"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":27,"of":27,"of_with_code":19,"tagged_in_all":27,"counts":{"archive_papers_tagged":27,"with_a_code_link":19,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":27,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/vast-a-vision-audio-subtitle-text-omni-1","slug":"vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","repositories_listed":2,"syntology":{"n":42,"n_ran":35,"n_constructed":4,"n_ran_checked":25,"n_instrument":10,"n_unverified":7,"n_honours":4,"n_violates":1,"n_no_contract":20,"n_pointer_only":8,"phrase":"35 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 1 violated, 20 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}},"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/fortisavqa-and-maven-a-benchmark-dataset-and","slug":"fortisavqa-and-maven-a-benchmark-dataset-and","title":"FortisAVQA and MAVEN: a Benchmark Dataset and Debiasing Framework for Robust Multimodal Reasoning","date":"2025-04-01","arxiv_id":"2504.00487","repositories_listed":1,"syntology":null},{"url":"/paper/pave-patching-and-adapting-video-large","slug":"pave-patching-and-adapting-video-large","title":"PAVE: Patching and Adapting Video Large Language Models","date":"2025-03-25","arxiv_id":"2503.19794","repositories_listed":1,"syntology":null},{"url":"/paper/question-aware-gaussian-experts-for-audio","slug":"question-aware-gaussian-experts-for-audio","title":"Question-Aware Gaussian Experts for Audio-Visual Question Answering","date":"2025-03-06","arxiv_id":"2503.04459","repositories_listed":1,"syntology":null},{"url":"/paper/avqacl-a-novel-benchmark-for-audio-visual","slug":"avqacl-a-novel-benchmark-for-audio-visual","title":"AVQACL: A Novel Benchmark for Audio-Visual Question Answering Continual Learning","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/boosting-audio-visual-question-answering-via","slug":"boosting-audio-visual-question-answering-via","title":"Boosting Audio Visual Question Answering via Key Semantic-Aware Cues","date":"2024-07-30","arxiv_id":"2407.20693","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/boosting-audio-visual-question-answering-via#ran","syntology_url":"https://syntology.ai/paper/2407.20693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20693"}},"official":{"repos":["gewu-lab/tspm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-trimodal-relation-for-avqa-with","slug":"learning-trimodal-relation-for-avqa-with","title":"Learning Trimodal Relation for AVQA with Missing Modality","date":"2024-07-23","arxiv_id":"2407.16171","repositories_listed":1,"syntology":{"n":24,"n_ran":20,"n_constructed":14,"n_ran_checked":18,"n_instrument":2,"n_unverified":4,"n_honours":4,"n_violates":0,"n_no_contract":14,"n_pointer_only":3,"phrase":"20 ran (of which 14 constructed an object rather than computing a result; 18 with no instrument failure: 4 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-trimodal-relation-for-avqa-with#ran","syntology_url":"https://syntology.ai/paper/2407.16171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16171"}},"official":{"repos":["visualaikhu/missing-avqa"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":14,"n_ran_no_instrument_failure":15,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/towards-multilingual-audio-visual-question","slug":"towards-multilingual-audio-visual-question","title":"Towards Multilingual Audio-Visual Question Answering","date":"2024-06-13","arxiv_id":"2406.09156","repositories_listed":1,"syntology":null},{"url":"/paper/look-listen-and-answer-overcoming-biases-for","slug":"look-listen-and-answer-overcoming-biases-for","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","date":"2024-04-18","arxiv_id":"2404.12020","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/look-listen-and-answer-overcoming-biases-for#ran","syntology_url":"https://syntology.ai/paper/2404.12020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12020"}},"official":{"repos":["reml-group/music-avqa-r"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"url":"/paper/answering-diverse-questions-via-text-attached","slug":"answering-diverse-questions-via-text-attached","title":"Answering Diverse Questions via Text Attached with Key Audio-Visual Clues","date":"2024-03-11","arxiv_id":"2403.06679","repositories_listed":1,"syntology":null},{"url":"/paper/cat-enhancing-multimodal-large-language-model","slug":"cat-enhancing-multimodal-large-language-model","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","date":"2024-03-07","arxiv_id":"2403.04640","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":5,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cat-enhancing-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2403.04640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04640"}},"official":{"repos":["rikeilong/bay-cat"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/object-aware-adaptive-positivity-learning-for","slug":"object-aware-adaptive-positivity-learning-for","title":"Object-aware Adaptive-Positivity Learning for Audio-Visual Question Answering","date":"2023-12-20","arxiv_id":"2312.12816","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/object-aware-adaptive-positivity-learning-for#ran","syntology_url":"https://syntology.ai/paper/2312.12816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12816"}},"official":{"repos":["zhangbin-ai/apl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/progressive-spatio-temporal-perception-for","slug":"progressive-spatio-temporal-perception-for","title":"Progressive Spatio-temporal Perception for Audio-Visual Question Answering","date":"2023-08-10","arxiv_id":"2308.05421","repositories_listed":1,"syntology":null},{"url":"/paper/target-aware-spatio-temporal-reasoning-via","slug":"target-aware-spatio-temporal-reasoning-via","title":"Target-Aware Spatio-Temporal Reasoning via Answering Questions in Dynamics Audio-Visual Scenarios","date":"2023-05-21","arxiv_id":"2305.12397","repositories_listed":1,"syntology":null},{"url":"/paper/valor-vision-audio-language-omni-perception","slug":"valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","arxiv_id":"2304.08345","repositories_listed":1,"syntology":null},{"url":"/paper/vision-transformers-are-parameter-efficient","slug":"vision-transformers-are-parameter-efficient","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","date":"2022-12-15","arxiv_id":"2212.07983","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":2,"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/vision-transformers-are-parameter-efficient#ran","syntology_url":"https://syntology.ai/paper/2212.07983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07983"}},"official":{"repos":["GenjiB/LAVISH"],"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/learning-to-answer-questions-in-dynamic-audio","slug":"learning-to-answer-questions-in-dynamic-audio","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","date":"2022-03-26","arxiv_id":"2203.14072","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/learning-to-answer-questions-in-dynamic-audio#ran","syntology_url":"https://syntology.ai/paper/2203.14072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14072"}},"official":{"repos":["GeWu-Lab/MUSIC-AVQA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/pano-avqa-grounded-audio-visual-question-1","slug":"pano-avqa-grounded-audio-visual-question-1","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","date":"2021-10-11","arxiv_id":"2110.05122","repositories_listed":1,"syntology":null},{"url":"/paper/pano-avqa-grounded-audio-visual-question","slug":"pano-avqa-grounded-audio-visual-question","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360deg Videos","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"learning-sparsity-for-effective-and-efficient","title":"Learning Sparsity for Effective and Efficient Music Performance Question Answering","date":"2025-06-02","arxiv_id":"2506.01319","repositories_listed":0,"syntology":null},{"url":null,"slug":"music-s-multimodal-complexity-in-avqa-why-we","title":"Music's Multimodal Complexity in AVQA: Why We Need More than General Multimodal LLMs","date":"2025-05-27","arxiv_id":"2505.20638","repositories_listed":0,"syntology":null},{"url":null,"slug":"patch-level-sounding-object-tracking-for","title":"Patch-level Sounding Object Tracking for Audio-Visual Question Answering","date":"2024-12-14","arxiv_id":"2412.10749","repositories_listed":0,"syntology":null},{"url":null,"slug":"sasr-net-source-aware-semantic-representation","title":"SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering","date":"2024-11-07","arxiv_id":"2411.04933","repositories_listed":0,"syntology":null},{"url":null,"slug":"omcat-omni-context-aware-transformer","title":"OMCAT: Omni Context Aware Transformer","date":"2024-10-15","arxiv_id":"2410.12109","repositories_listed":0,"syntology":null},{"url":null,"slug":"shmamba-structured-hyperbolic-state-space","title":"SHMamba: Structured Hyperbolic State Space Model for Audio-Visual Question Answering","date":"2024-06-14","arxiv_id":"2406.09833","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-powered-tass-target-aware-single-stream","title":"CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering","date":"2024-05-13","arxiv_id":"2405.07451","repositories_listed":0,"syntology":null},{"url":"/paper/cad-contextual-multi-modal-alignment-for","slug":"cad-contextual-multi-modal-alignment-for","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","date":"2023-10-25","arxiv_id":"2310.16754","repositories_listed":0,"syntology":null}],"syntology_records":8,"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":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/audio-visual-question-answering-on-music-avqa","since_archive":"/sota/audio-visual-question-answering-on-music-avqa#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/task/audio-visual-question-answering/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/audio-visual-question-answering/papers/ran/1","json":"/task/audio-visual-question-answering/papers/ran/1.json","rows":6}],"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":"9d20a5ba4f0fb36940bfbdfe1d8effe3cf9be25dfa4a72eda840ac56009f1e37","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}