{"id":"https://openalex.org/W7138302322","doi":"https://doi.org/10.1609/aaai.v40i11.37878","title":"CoMA: Compositional Human Motion Generation with Multi-modal Agents","display_name":"CoMA: Compositional Human Motion Generation with Multi-modal Agents","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138302322","doi":"https://doi.org/10.1609/aaai.v40i11.37878"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i11.37878","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37878","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37878/41840","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/37878/41840","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100606010","display_name":"Shanlin Sun","orcid":"https://orcid.org/0000-0002-4519-7287"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanlin Sun","raw_affiliation_strings":["University of California, Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Irvine","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129751887","display_name":"Jiaqi Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Xu","raw_affiliation_strings":["University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051894863","display_name":"G. Araujo","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gabriel De Araujo","raw_affiliation_strings":["University of California, Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Irvine","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129653827","display_name":"Shenghan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenghan Zhou","raw_affiliation_strings":["Chongqing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129723498","display_name":"Hanwen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanwen Zhang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129730988","display_name":"Ziheng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziheng Huang","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129661473","display_name":"Chenyu You","orcid":null},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenyu You","raw_affiliation_strings":["State University of New York at Stony Brook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Stony Brook","institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129673959","display_name":"Xiaohui Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohui Xie","raw_affiliation_strings":["University of California, Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Irvine","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"11","first_page":"9206","last_page":"9214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.6417999863624573,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.6417999863624573,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.16779999434947968,"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":0.05119999870657921,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.7544000148773193},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.621399998664856},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5871999859809875},{"id":"https://openalex.org/keywords/human-motion","display_name":"Human motion","score":0.54339998960495},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4629000127315521},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.4146000146865845},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.36039999127388},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.33570000529289246}],"concepts":[{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7544000148773193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7524999976158142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6617000102996826},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.621399998664856},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5871999859809875},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5737000107765198},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.54339998960495},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4146000146865845},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3314000070095062},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.31450000405311584},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.260699987411499}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i11.37878","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37878","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37878/41840","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.v40i11.37878","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37878","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37878/41840","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138302322.pdf","grobid_xml":"https://content.openalex.org/works/W7138302322.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0],"human":[1,59],"motion":[2,36,60,81,101,107],"generation":[3,95],"has":[4],"seen":[5],"substantial":[6],"advancement":[7],"in":[8,27],"recent":[9],"years.":[10],"While":[11],"state-of-the-art":[12,123],"approaches":[13],"have":[14],"improved":[15,112],"performance":[16,121],"significantly,":[17],"they":[18],"still":[19],"struggle":[20],"with":[21,103],"complex":[22,58],"and":[23,38,63,74,87,99,109,133],"detailed":[24,104],"motions":[25],"unseen":[26],"training":[28,45],"data,":[29],"largely":[30],"due":[31],"to":[32],"the":[33,39,116],"scarcity":[34],"of":[35,42,96,130],"datasets":[37],"prohibitive":[40],"cost":[41],"generating":[43],"new":[44],"examples.":[46],"To":[47],"address":[48],"these":[49],"challenges,":[50],"we":[51,126],"introduce":[52],"CoMA,":[53],"an":[54],"agent-based":[55],"solution":[56],"for":[57,89,111],"generation,":[61],"editing,":[62,108],"comprehension.":[64],"CoMA":[65],"leverages":[66],"multiple":[67],"collaborative":[68],"agents":[69],"powered":[70],"by":[71],"large":[72],"language":[73],"vision":[75],"models,":[76],"alongside":[77],"a":[78,128],"mask":[79],"transformer-based":[80],"generator":[82],"featuring":[83],"body":[84],"part-specific":[85],"encoders":[86],"codebooks":[88],"fine-grained":[90],"control.":[91],"Our":[92],"framework":[93],"enables":[94],"both":[97],"short":[98],"long":[100,134],"sequences":[102],"instructions,":[105],"text-guided":[106],"self-correction":[110],"quality.":[113],"Evaluations":[114],"on":[115],"HumanML3D":[117],"dataset":[118],"demonstrate":[119],"competitive":[120],"against":[122],"methods.":[124],"Additionally,":[125],"create":[127],"set":[129],"context-rich,":[131],"compositional,":[132],"text":[135],"prompts,":[136],"where":[137],"user":[138],"studies":[139],"show":[140],"our":[141],"method":[142],"significantly":[143],"outperforms":[144],"existing":[145],"approaches.":[146]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-18T00:00:00"}