{"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-captioning/papers/ran/1","list_of":"/task/audio-captioning","task":"Audio captioning","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":[1,17],"of":17,"counts":{"archive_papers_tagged":119,"with_a_code_link":62,"where_syntology_ran_a_sample":17,"not_listed_spam_title":0,"listed":119,"listed_where_code_ran":17,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":16,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/audio-captioning/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/video-salmonn-2-captioning-enhanced-audio","slug":"video-salmonn-2-captioning-enhanced-audio","title":"video-SALMONN 2: Captioning-Enhanced Audio-Visual Large Language Models","date":"2025-06-18","arxiv_id":"2506.15220","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-salmonn-2-captioning-enhanced-audio#ran","syntology_url":"https://syntology.ai/paper/2506.15220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.15220"}},"official":{"repos":["bytedance/video-salmonn-2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mellow-a-small-audio-language-model-for","slug":"mellow-a-small-audio-language-model-for","title":"Mellow: a small audio language model for reasoning","date":"2025-03-11","arxiv_id":"2503.08540","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mellow-a-small-audio-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2503.08540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08540"}},"official":{"repos":["soham97/mellow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/adiff-explaining-audio-difference-using","slug":"adiff-explaining-audio-difference-using","title":"ADIFF: Explaining audio difference using natural language","date":"2025-02-06","arxiv_id":"2502.04476","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adiff-explaining-audio-difference-using#ran","syntology_url":"https://syntology.ai/paper/2502.04476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04476"}},"official":{"repos":["soham97/adiff"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/audiosetcaps-an-enriched-audio-caption","slug":"audiosetcaps-an-enriched-audio-caption","title":"AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models","date":"2024-11-28","arxiv_id":"2411.18953","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"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 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) · 0 unverified","sample_list":"/paper/audiosetcaps-an-enriched-audio-caption#ran","syntology_url":"https://syntology.ai/paper/2411.18953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.18953"}},"official":{"repos":["jishengbai/audiosetcaps"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tell-what-you-hear-from-what-you-see-video-to","slug":"tell-what-you-hear-from-what-you-see-video-to","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","date":"2024-11-08","arxiv_id":"2411.05679","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"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) · 0 unverified","sample_list":"/paper/tell-what-you-hear-from-what-you-see-video-to#ran","syntology_url":"https://syntology.ai/paper/2411.05679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05679"}},"official":{"repos":["DragonLiu1995/multimodal-llm-for-audio-gen"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-automated-audio-captioning-via","slug":"enhancing-automated-audio-captioning-via","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","date":"2024-06-19","arxiv_id":"2406.13275","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/enhancing-automated-audio-captioning-via#ran","syntology_url":"https://syntology.ai/paper/2406.13275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13275"}},"official":{"repos":["frankenliu/LOAE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/2406-15487","slug":"2406-15487","title":"Improving Text-To-Audio Models with Synthetic Captions","date":"2024-06-18","arxiv_id":"2406.15487","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2406-15487#ran","syntology_url":"https://syntology.ai/paper/2406.15487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15487"}},"official":null}},{"url":"/paper/audio-flamingo-a-novel-audio-language-model","slug":"audio-flamingo-a-novel-audio-language-model","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","date":"2024-02-02","arxiv_id":"2402.01831","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/audio-flamingo-a-novel-audio-language-model#ran","syntology_url":"https://syntology.ai/paper/2402.01831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01831"}},"official":{"repos":["NVIDIA/audio-flamingo"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/qwen-audio-advancing-universal-audio","slug":"qwen-audio-advancing-universal-audio","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","date":"2023-11-14","arxiv_id":"2311.07919","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/qwen-audio-advancing-universal-audio#ran","syntology_url":"https://syntology.ai/paper/2311.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07919"}},"official":{"repos":["qwenlm/qwen-audio"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-audio-captioning-with-audio","slug":"zero-shot-audio-captioning-with-audio","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","date":"2023-11-14","arxiv_id":"2311.08396","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":17,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/zero-shot-audio-captioning-with-audio#ran","syntology_url":"https://syntology.ai/paper/2311.08396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08396"}},"official":{"repos":["explainableml/zeraucap"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/lauragpt-listen-attend-understand-and","slug":"lauragpt-listen-attend-understand-and","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","date":"2023-10-07","arxiv_id":"2310.04673","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lauragpt-listen-attend-understand-and#ran","syntology_url":"https://syntology.ai/paper/2310.04673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04673"}},"official":null}},{"url":"/paper/recap-retrieval-augmented-audio-captioning","slug":"recap-retrieval-augmented-audio-captioning","title":"RECAP: Retrieval-Augmented Audio Captioning","date":"2023-09-18","arxiv_id":"2309.09836","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/recap-retrieval-augmented-audio-captioning#ran","syntology_url":"https://syntology.ai/paper/2309.09836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.09836"}},"official":{"repos":["sreyan88/recap"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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":29,"n_instrument":6,"n_unverified":7,"n_honours":2,"n_violates":1,"n_no_contract":26,"n_pointer_only":8,"phrase":"35 ran (of which 4 constructed an object rather than computing a result; 29 with no instrument failure: 2 honoured, 1 violated, 26 with no contract checked; 6 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":12,"n_unverified":7,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/pengi-an-audio-language-model-for-audio-tasks-1","slug":"pengi-an-audio-language-model-for-audio-tasks-1","title":"Pengi: An Audio Language Model for Audio Tasks","date":"2023-05-19","arxiv_id":"2305.11834","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pengi-an-audio-language-model-for-audio-tasks-1#ran","syntology_url":"https://syntology.ai/paper/2305.11834","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11834"}},"official":{"repos":["microsoft/pengi"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/wavcaps-a-chatgpt-assisted-weakly-labelled","slug":"wavcaps-a-chatgpt-assisted-weakly-labelled","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","date":"2023-03-30","arxiv_id":"2303.17395","repositories_listed":3,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/wavcaps-a-chatgpt-assisted-weakly-labelled#ran","syntology_url":"https://syntology.ai/paper/2303.17395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17395"}},"official":{"repos":["xinhaomei/wavcaps"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/cl4ac-a-contrastive-loss-for-audio-captioning","slug":"cl4ac-a-contrastive-loss-for-audio-captioning","title":"CL4AC: A Contrastive Loss for Audio Captioning","date":"2021-07-21","arxiv_id":"2107.09990","repositories_listed":2,"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/cl4ac-a-contrastive-loss-for-audio-captioning#ran","syntology_url":"https://syntology.ai/paper/2107.09990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09990"}},"official":{"repos":["liuxubo717/cl4ac","liuxubo717/contrastive_loss_for_audio_captioning"],"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":["official"]}}},{"url":"/paper/clotho-an-audio-captioning-dataset","slug":"clotho-an-audio-captioning-dataset","title":"Clotho: An Audio Captioning Dataset","date":"2019-10-21","arxiv_id":"1910.09387","repositories_listed":7,"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":17,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":5,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/clotho-an-audio-captioning-dataset#ran","syntology_url":"https://syntology.ai/paper/1910.09387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.09387"}},"official":null}}],"record_sha256":"be9f8280faf417483234c80cae1e0e00725d0ae68075e298b843d841336037d9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}