{"id":"https://openalex.org/W7138404676","doi":"https://doi.org/10.1609/aaai.v40i7.37418","title":"GENMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration","display_name":"GENMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138404676","doi":"https://doi.org/10.1609/aaai.v40i7.37418"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i7.37418","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37418","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37418/41380","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37418/41380","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129729058","display_name":"Kaiyi Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kaiyi Huang","raw_affiliation_strings":["University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129667202","display_name":"Yukun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yukun Huang","raw_affiliation_strings":["University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129656235","display_name":"Xuefei Ning","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefei Ning","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129716954","display_name":"Zinan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zinan Lin","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129745157","display_name":"Yu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Tsinghua University, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129686129","display_name":"Xihui Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xihui Liu","raw_affiliation_strings":["University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"7","first_page":"5049","last_page":"5057"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4862000048160553,"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":0.4862000048160553,"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":0.3546999990940094,"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/T12290","display_name":"Human Motion and Animation","score":0.030799999833106995,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.6481000185012817},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5141000151634216},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.3612000048160553},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36079999804496765},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3402000069618225},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.3384000062942505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8140000104904175},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.6481000185012817},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5141000151634216},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42730000615119934},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3682999908924103},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3612000048160553},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.323199987411499},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2978000044822693},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2808000147342682},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i7.37418","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37418","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37418/41380","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i7.37418","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37418","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37418/41380","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.6231289505958557,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138404676.pdf","grobid_xml":"https://content.openalex.org/works/W7138404676.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-video":[0],"generation":[1,246],"models":[2],"have":[3],"shown":[4],"significant":[5],"progress":[6],"in":[7,107,160,242],"recent":[8],"years.":[9],"However,":[10],"they":[11],"still":[12],"struggle":[13],"with":[14,28,67,96],"compositional":[15,195,236,244],"text":[16,132,237],"prompts,":[17,133],"such":[18],"as":[19],"attribute":[20],"binding":[21],"for":[22,139,218],"multiple":[23],"objects,":[24,31],"temporal":[25],"dynamics":[26],"associated":[27],"differ-":[29],"ent":[30],"and":[32,65,79,98,128,136,151,185,239],"interactions":[33],"between":[34,71],"objects.":[35],"Inspired":[36],"by":[37,163,171,230],"ef-":[38],"fective":[39],"human":[40],"creative":[41],"workflow,":[42],"we":[43,155,198],"propose":[44],"GENMAC,":[45],"a":[46,59,88,100,157,165,200,211],"multi-agent":[47,153],"collaboration":[48],"framework":[49,57],"that":[50,119],"enables":[51],"composi-":[52],"tional":[53],"text-to-video":[54,196,245],"generation.":[55,144],"The":[56,111],"incorporates":[58],"three-stage":[60],"collaborative":[61],"workflow:":[62],"DESIGN,":[63],"GENERATION,":[64],"REDESIGN,":[66],"an":[68],"iterative":[69],"loop":[70],"the":[72,81,85,108,115,123,131,140,206,225,243],"latter":[73],"two":[74],"stages":[75],"to":[76,121,190,203],"progressively":[77],"verify":[78,122],"refine":[80],"generated":[82,124],"videos.":[83],"In":[84],"DESIGN":[86],"stage,":[87],"large":[89,175],"language":[90,176],"model":[91,104],"(Design":[92],"Agent)":[93],"plans":[94],"objects":[95],"layouts,":[97,135],"then":[99],"video":[101],"gener-":[102],"ation":[103],"synthesizes":[105],"videos":[106,232],"GENERATION":[109],"stage.":[110],"REDESIGN":[112],"stage":[113,118,162],"is":[114],"most":[116],"challenging":[117],"aims":[120],"videos,":[125],"suggest":[126],"corrections,":[127],"re-":[129],"design":[130,199],"frame-wise":[134],"guidance":[137],"scales":[138],"next":[141],"iteration":[142],"of":[143,149,167,194,213,227],"To":[145],"avoid":[146],"halluci-":[147],"nation":[148],"single-agent":[150],"naive":[152],"frameworks,":[154],"apply":[156],"division-of-labor":[158],"strategy":[159],"this":[161],"introducing":[164],"sequence":[166],"specialized":[168,217],"agents,":[169,215],"executed":[170],"MLLMs":[172],"(mul-":[173],"timodal":[174],"models):":[177],"Verification":[178],"Agent,":[179,182,184],"Sugges-":[180],"tion":[181],"Correction":[183],"Output":[186],"Structuring":[187],"Agent.":[188],"Furthermore,":[189],"tackle":[191],"diverse":[192],"scenarios":[193],"generation,":[197],"self-routing":[201],"mechanism":[202],"adaptively":[204],"select":[205],"proper":[207],"correction":[208,214],"agent":[209],"from":[210],"suite":[212],"each":[216],"one":[219],"scenario.":[220],"Ex-":[221],"tensive":[222],"experiments":[223],"demonstrate":[224],"effectiveness":[226],"GEN-":[228],"MAC":[229],"generating":[231],"based":[233],"on":[234],"long":[235],"prompts":[238],"achieving":[240],"state-of-the-art":[241],"benchmark.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}