{"id":"https://openalex.org/W7166814374","doi":"https://doi.org/10.18653/v1/2026.acl-long.1697","title":"Probing Audio-Visual Reasoning in Multimodal Language Models through the Lens of Audio","display_name":"Probing Audio-Visual Reasoning in Multimodal Language Models through the Lens of Audio","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166814374","doi":"https://doi.org/10.18653/v1/2026.acl-long.1697"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1697","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1697","pdf_url":"https://aclanthology.org/2026.acl-long.1697.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1697.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030869039","display_name":"Kaixiong Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaixiong Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139787831","display_name":"Kaituo Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaituo Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139765527","display_name":"Bohao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bohao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139765764","display_name":"Yibing Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yibing Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139838484","display_name":"Mofan Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mofan Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139809432","display_name":"Shijia Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shijia Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139791896","display_name":"Jiaming Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaming Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139807460","display_name":"Benyou Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benyou Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102019858","display_name":"Yutong Bai","orcid":"https://orcid.org/0000-0002-6210-7757"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutong Bai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139830437","display_name":"Zhuoran Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuoran Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139728083","display_name":"Xiangyu Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyu Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86150761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"36603","last_page":"36645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.794700026512146,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.794700026512146,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.025499999523162842,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.01720000058412552,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.40290001034736633},{"id":"https://openalex.org/keywords/lens","display_name":"Lens (geology)","score":0.36250001192092896},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.35359999537467957},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.3165999948978424},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.29190000891685486},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2867000102996826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6212000250816345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4887000024318695},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45489999651908875},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3855000138282776},{"id":"https://openalex.org/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3345000147819519},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29679998755455017},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1697","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1697","pdf_url":"https://aclanthology.org/2026.acl-long.1697.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1697","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1697","pdf_url":"https://aclanthology.org/2026.acl-long.1697.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8568803071975708}],"awards":[{"id":"https://openalex.org/G3917743038","display_name":null,"funder_award_id":"8115074","funder_id":"https://openalex.org/F4320335138","funder_display_name":"Shun Hing Institute of Advanced Engineering"},{"id":"https://openalex.org/G8285413768","display_name":null,"funder_award_id":"62306261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"},{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"},{"id":"https://openalex.org/F4320335138","display_name":"Shun Hing Institute of Advanced Engineering","ror":"https://ror.org/00t33hh48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166814374.pdf","grobid_xml":"https://content.openalex.org/works/W7166814374.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Kaixiong":[0],"Gong,":[1],"Kaituo":[2],"Feng,":[3],"Bohao":[4],"Li,":[5],"Yibing":[6],"Wang,":[7,15],"Mofan":[8],"Cheng,":[9],"Shijia":[10],"Yang,":[11,19],"Jiaming":[12],"Han,":[13],"Benyou":[14],"Yutong":[16],"Bai,":[17],"Zhuoran":[18],"Xiangyu":[20],"Yue.":[21],"Proceedings":[22],"of":[23,28],"the":[24,29],"64th":[25],"Annual":[26],"Meeting":[27],"Association":[30],"for":[31],"Computational":[32],"Linguistics":[33],"(Volume":[34],"1:":[35],"Long":[36],"Papers).":[37],"2026.":[38]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
