{"id":"https://openalex.org/W7160830976","doi":"https://doi.org/10.48550/arxiv.2605.07061","title":"Do Joint Audio-Video Generation Models Understand Physics?","display_name":"Do Joint Audio-Video Generation Models Understand Physics?","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160830976","doi":"https://doi.org/10.48550/arxiv.2605.07061"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2605.07061","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.07061","pdf_url":"https://arxiv.org/pdf/2605.07061","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2605.07061","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135861014","display_name":"Zijun Cui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cui, Zijun","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135899475","display_name":"Xiulong Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Xiulong","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153467357","display_name":"Hao Fang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fang, Hao","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110710337","display_name":"Mingwei Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Mingwei","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100314979","display_name":"Jiageng Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Jiageng","raw_affiliation_strings":["University of California , Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135879619","display_name":"Zexin Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Zexin","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011256066","display_name":"Weiguo Pian","orcid":"https://orcid.org/0000-0002-4653-7415","observed_orcids":["https://orcid.org/0000-0002-4653-7415"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pian, Weiguo","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132800851","display_name":"Shijian Deng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deng, Shijian","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135829009","display_name":"Feiyu Du","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Du, Feiyu","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064970009","display_name":"Chenming Ge","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ge, Chenming","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5146602921","display_name":"Yapeng Tian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian, Yapeng","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9071999788284302,"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":0.9071999788284302,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0658000037074089,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.0035000001080334187,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/physical-consistency","display_name":"physical consistency","score":0.5920000076293945},{"id":"https://openalex.org/keywords/multimodal-language-models","display_name":"multimodal language models","score":0.7950000166893005},{"id":"https://openalex.org/keywords/benchmark-evaluation","display_name":"benchmark evaluation","score":0.39800000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733299970626831},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6790000200271606},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5601000189781189},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47110000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4555000066757202},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3179999887943268},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.287200003862381},{"id":"https://openalex.org/C2780589192","wikidata":"https://www.wikidata.org/wiki/Q7285140","display_name":"Raising (metalworking)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2556999921798706},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2605.07061","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.07061","pdf_url":"https://arxiv.org/pdf/2605.07061","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2605.07061","doi":"https://doi.org/10.48550/arxiv.2605.07061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07061","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2605.07061","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.07061","pdf_url":"https://arxiv.org/pdf/2605.07061","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160830976.pdf","grobid_xml":"https://content.openalex.org/works/W7160830976.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W4297750695","https://openalex.org/W4304195432","https://openalex.org/W4392970325","https://openalex.org/W4399453732","https://openalex.org/W4403346161","https://openalex.org/W4406191642","https://openalex.org/W4414815232","https://openalex.org/W4415055100","https://openalex.org/W4417069117","https://openalex.org/W4417290295","https://openalex.org/W4417531116","https://openalex.org/W6910607073","https://openalex.org/W6948369276","https://openalex.org/W6966581363","https://openalex.org/W6967030891","https://openalex.org/W7117318636","https://openalex.org/W7117977076","https://openalex.org/W7118630684","https://openalex.org/W7119523234","https://openalex.org/W7124753722","https://openalex.org/W7131394878","https://openalex.org/W7140213015","https://openalex.org/W7154629535","https://openalex.org/W7154947098","https://openalex.org/W7157774129"],"related_works":["https://openalex.org/W7162755192","https://openalex.org/W7117977076","https://openalex.org/W4399453732","https://openalex.org/W6966581363","https://openalex.org/W7140114327","https://openalex.org/W7114766516","https://openalex.org/W7161726325","https://openalex.org/W7160286610","https://openalex.org/W7143332438","https://openalex.org/W7160894421"],"abstract_inverted_index":{"Joint":[0],"audio-video":[1,42,75,184],"generation":[2,78],"models":[3,47,117],"are":[4],"rapidly":[5],"approaching":[6],"professional":[7],"production":[8],"quality,":[9],"raising":[10],"a":[11,34,146,151],"central":[12],"question:":[13],"do":[14],"they":[15],"understand":[16],"audio-visual":[17],"physics,":[18],"or":[19],"merely":[20],"generate":[21],"plausible":[22],"sounds":[23],"and":[24,56,96,103,129,132,174],"frames":[25],"that":[26,70,109,149,162],"violate":[27],"real-world":[28,65],"consistency?":[29],"We":[30,141],"introduce":[31,143],"AV-Phys":[32,44,144],"Bench,":[33],"benchmark":[35],"for":[36,182],"evaluating":[37],"physical":[38,91,94,98,122,172],"commonsense":[39],"in":[40],"joint":[41,183],"generation.":[43,185],"Bench":[45],"tests":[46],"across":[48],"three":[49,101],"scene":[50,176],"categories:":[51],"Steady":[52],"State,":[53],"Event":[54],"Transition,":[55],"Environment":[57],"Transition.":[58],"It":[59],"covers":[60],"physics-grounded":[61],"subcategories":[62],"drawn":[63],"from":[64,120],"scenes,":[66],"plus":[67],"Anti-AV-Physics":[68,139],"prompts":[69],"deliberately":[71],"request":[72],"physically":[73],"inconsistent":[74],"behavior.":[76],"Each":[77],"is":[79],"evaluated":[80],"along":[81],"five":[82],"dimensions:":[83],"visual":[84,90],"semantic":[85,88],"adherence,":[86,89],"audio":[87,93],"commonsense,":[92,95],"cross-modal":[97,171],"commonsense.":[99],"Across":[100],"proprietary":[102,135],"four":[104],"open-source":[105],"models,":[106],"we":[107],"find":[108],"Seedance":[110],"2.0":[111],"performs":[112],"best":[113],"overall,":[114],"but":[115],"all":[116],"remain":[118],"far":[119],"robust":[121],"understanding.":[123],"Performance":[124],"drops":[125],"sharply":[126],"on":[127,138],"event-driven":[128],"environment-driven":[130],"transitions,":[131],"even":[133],"strong":[134],"systems":[136],"collapse":[137],"prompts.":[140],"further":[142],"Agent,":[145],"ReAct-style":[147],"evaluator":[148],"combines":[150],"multimodal":[152],"language":[153],"model":[154],"with":[155,165],"deterministic":[156],"acoustic":[157],"measurement":[158],"tools,":[159],"producing":[160],"rankings":[161],"closely":[163],"align":[164],"human":[166],"ratings.":[167],"Our":[168],"results":[169],"identify":[170],"consistency":[173],"transition-driven":[175],"dynamics":[177],"as":[178],"key":[179],"open":[180],"challenges":[181]},"counts_by_year":[{"year":2026,"cited_by_count":10}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-05-12T00:00:00"}
