{"id":"https://openalex.org/W4411640154","doi":"https://doi.org/10.1109/tpami.2025.3582389","title":"CAT+: Investigating and Enhancing Audio-Visual Understanding in Large Language Models","display_name":"CAT+: Investigating and Enhancing Audio-Visual Understanding in Large Language Models","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411640154","doi":"https://doi.org/10.1109/tpami.2025.3582389","pmid":"https://pubmed.ncbi.nlm.nih.gov/40560702"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3582389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3582389","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005658216","display_name":"Qilang Ye","orcid":"https://orcid.org/0009-0004-6907-702X"},"institutions":[{"id":"https://openalex.org/I4396570619","display_name":"Great Bay University","ror":"https://ror.org/01hdgge16","country_code":null,"type":"education","lineage":["https://openalex.org/I4396570619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qilang Ye","raw_affiliation_strings":["Great Bay University, Dongguan, China"],"raw_orcid":"https://orcid.org/0009-0004-6907-702X","affiliations":[{"raw_affiliation_string":"Great Bay University, Dongguan, China","institution_ids":["https://openalex.org/I4396570619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103099781","display_name":"Zitong Yu","orcid":"https://orcid.org/0000-0003-0422-6616"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]},{"id":"https://openalex.org/I4396570619","display_name":"Great Bay University","ror":"https://ror.org/01hdgge16","country_code":null,"type":"education","lineage":["https://openalex.org/I4396570619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zitong Yu","raw_affiliation_strings":["Dongguan Key Laboratory for Intelligence and Information Technology, Great Bay University, Dongguan, China","Great Bay University, Dongguan, China"],"raw_orcid":"https://orcid.org/0000-0003-0422-6616","affiliations":[{"raw_affiliation_string":"Dongguan Key Laboratory for Intelligence and Information Technology, Great Bay University, Dongguan, China","institution_ids":["https://openalex.org/I2799850029"]},{"raw_affiliation_string":"Great Bay University, Dongguan, China","institution_ids":["https://openalex.org/I4396570619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037878863","display_name":"Rui Shao","orcid":"https://orcid.org/0000-0003-0090-9604"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Shao","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0090-9604","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040232431","display_name":"Yawen Cui","orcid":"https://orcid.org/0000-0002-9337-687X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yawen Cui","raw_affiliation_strings":["The Hong Kong Polytechnic University, Kowloon, Hong Kong","Hong Kong Polytechnic University, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-9337-687X","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077333494","display_name":"Xiangui Kang","orcid":"https://orcid.org/0000-0002-3134-0353"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangui Kang","raw_affiliation_strings":["Guangdong Key Lab of Information Security, School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China","Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3134-0353","affiliations":[{"raw_affiliation_string":"Guangdong Key Lab of Information Security, School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058509635","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0002-2242-6139"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I63548447","display_name":"Lappeenranta-Lahti University of Technology","ror":"https://ror.org/0208vgz68","country_code":"FI","type":"education","lineage":["https://openalex.org/I63548447"]}],"countries":["CN","FI"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China","Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland"],"raw_orcid":"https://orcid.org/0000-0002-2242-6139","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Lappeenranta-Lahti University of Technology LUT, Lappeenranta, Finland","institution_ids":["https://openalex.org/I63548447"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042899882","display_name":"Philip H. S. Torr","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip Torr","raw_affiliation_strings":["University of Oxford, Oxford, U.K"],"raw_orcid":"https://orcid.org/0009-0006-0259-5732","affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068837264","display_name":"Xiaochun Cao","orcid":"https://orcid.org/0000-0001-7141-708X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochun Cao","raw_affiliation_strings":["School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7141-708X","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.8721,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.98183195,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"47","issue":"10","first_page":"8674","last_page":"8690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9383999705314636,"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/computer-science","display_name":"Computer science","score":0.7230435013771057},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6524055600166321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5259727835655212},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43459299206733704},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.416980504989624},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3901456594467163},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3347635865211487},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2963162660598755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7230435013771057},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6524055600166321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5259727835655212},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43459299206733704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.416980504989624},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3901456594467163},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3347635865211487},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2963162660598755}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2025.3582389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3582389","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40560702","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40560702","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:ora.ox.ac.uk:uuid:67d0a928-3683-43ac-bcb1-3d59d7c0ed80","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"http://purl.org/coar/resource_type/c_dcae04bc"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2256185642","display_name":null,"funder_award_id":"62171309","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2471551971","display_name":null,"funder_award_id":"62441619","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4414281452","display_name":null,"funder_award_id":"62025604","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5972905494","display_name":null,"funder_award_id":"62306090","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G809398285","display_name":null,"funder_award_id":"62306061","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2250539671","https://openalex.org/W2765716052","https://openalex.org/W2896457183","https://openalex.org/W2904452845","https://openalex.org/W2949153209","https://openalex.org/W2952728748","https://openalex.org/W2954199749","https://openalex.org/W2962735233","https://openalex.org/W2963961878","https://openalex.org/W2964213933","https://openalex.org/W2964220823","https://openalex.org/W2966683369","https://openalex.org/W2980339970","https://openalex.org/W2998166190","https://openalex.org/W3034383590","https://openalex.org/W3034730770","https://openalex.org/W3044495139","https://openalex.org/W3201174429","https://openalex.org/W3202965415","https://openalex.org/W3205708381","https://openalex.org/W4304098310","https://openalex.org/W4309674289","https://openalex.org/W4312256574","https://openalex.org/W4312380001","https://openalex.org/W4385801138","https://openalex.org/W4386071707","https://openalex.org/W4386113246","https://openalex.org/W4388192054","https://openalex.org/W4389519587","https://openalex.org/W4389523832","https://openalex.org/W4394625659","https://openalex.org/W4401042773","https://openalex.org/W4402671548","https://openalex.org/W4402671735","https://openalex.org/W4402727142","https://openalex.org/W4402727922","https://openalex.org/W4402753774","https://openalex.org/W4402754220","https://openalex.org/W4403002096","https://openalex.org/W4403998616","https://openalex.org/W4404784276","https://openalex.org/W4405953164","https://openalex.org/W4412158322"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5,26],"gained":[6],"significant":[7],"attention":[8],"due":[9,66],"to":[10,56,62,67,87,109,130],"their":[11],"rich":[12],"internal":[13],"implicit":[14],"knowledge":[15],"for":[16,30],"cross-modal":[17],"learning.":[18],"Although":[19],"advances":[20],"in":[21,28,147,172],"bringing":[22],"audio-visuals":[23],"into":[24],"LLMs":[25],"resulted":[27],"boosts":[29],"a":[31,111,153],"variety":[32],"of":[33,72,134,145,165,194],"Audio-Visual":[34],"Question":[35],"Answering":[36],"(AVQA)":[37],"tasks,":[38],"they":[39],"still":[40],"face":[41],"two":[42,77],"crucial":[43],"challenges:":[44],"1)":[45],"audio-visual":[46,50,57,113,149],"ambiguity,":[47],"and":[48,106,118,177,187],"2)":[49],"hallucination.":[51],"Existing":[52],"MLLMs":[53,146],"can":[54],"respond":[55],"content,":[58],"yet":[59],"sometimes":[60],"fail":[61],"describe":[63],"specific":[64],"objects":[65],"the":[68,76,82,96,132,142,163,173,191],"ambiguity":[69],"or":[70],"hallucination":[71],"responses.":[73],"To":[74,140],"overcome":[75],"aforementioned":[78],"issues,":[79],"we":[80,122,151],"introduce":[81,123],"CAT+,":[83],"which":[84,101],"enhances":[85],"MLLM":[86],"ensure":[88],"more":[89],"robust":[90],"multimodal":[91],"understanding.":[92],"We":[93],"first":[94],"propose":[95],"Sequential":[97],"Question-guided":[98],"Module":[99],"(SQM),":[100],"combines":[102],"tiny":[103],"transformer":[104],"layers":[105],"cascades":[107],"Q-Formers":[108],"realize":[110],"solid":[112],"grounding.":[114],"After":[115],"feature":[116],"alignment":[117],"high-quality":[119],"instruction":[120],"tuning,":[121],"Ambiguity":[124],"Scoring":[125],"Direct":[126],"Preference":[127],"Optimization":[128],"(AS-DPO)":[129],"correct":[131],"problem":[133],"CAT+":[135],"bias":[136],"toward":[137],"ambiguous":[138],"descriptions.":[139],"explore":[141],"hallucinatory":[143],"deficits":[144],"dynamic":[148],"scenes,":[150],"build":[152],"new":[154],"Audio-visual":[155],"Hallucination":[156],"Benchmark,":[157],"named":[158],"AVHbench.":[159],"This":[160],"benchmark":[161],"detects":[162],"extent":[164],"MLLM's":[166],"hallucinations":[167],"across":[168,183],"three":[169],"different":[170],"protocols":[171],"perceptual":[174],"object,":[175],"counting,":[176],"holistic":[178],"description":[179],"tasks.":[180],"Extensive":[181],"experiments":[182],"video-based":[184],"understanding,":[185],"open-ended,":[186],"close-ended":[188],"AVQA":[189],"demonstrate":[190],"superior":[192],"performance":[193],"our":[195],"method.":[196],"The":[197],"AVHbench":[198],"is":[199],"released":[200],"at":[201],"https://github.com/rikeilong/Bay-CAT.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}