{"id":"https://openalex.org/W7137961329","doi":"https://doi.org/10.1609/aaai.v40i12.37936","title":"UniMo: Unified Motion Generation and Understanding with Chain of Thought","display_name":"UniMo: Unified Motion Generation and Understanding with Chain of Thought","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137961329","doi":"https://doi.org/10.1609/aaai.v40i12.37936"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i12.37936","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37936","pdf_url":null,"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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i12.37936","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014128546","display_name":"Guocun Wang","orcid":"https://orcid.org/0009-0000-1815-2342"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guocun Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129696050","display_name":"Kenkun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenkun Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129675091","display_name":"Jing Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Lin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084103247","display_name":"Guorui Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guorui Song","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129710882","display_name":"Jian Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129707407","display_name":"Xiaoguang Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoguang Han","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5014128546"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30681818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"12","first_page":"9729","last_page":"9737"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.5184000134468079,"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":0.5184000134468079,"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":0.16949999332427979,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.13860000669956207,"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/leverage","display_name":"Leverage (statistics)","score":0.7480000257492065},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6661999821662903},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6003999710083008},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5820000171661377},{"id":"https://openalex.org/keywords/chain","display_name":"Chain (unit)","score":0.45739999413490295},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4440999925136566},{"id":"https://openalex.org/keywords/unified-model","display_name":"Unified Model","score":0.3666999936103821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7511000037193298},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7480000257492065},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6661999821662903},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6003999710083008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5935999751091003},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44830000400543213},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2718000113964081},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i12.37936","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37936","pdf_url":null,"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.v40i12.37936","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37936","pdf_url":null,"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":[{"score":0.6097642779350281,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"3D":[1],"human":[2],"motion":[3,54,120,140],"generation":[4,141],"and":[5,41,74,113,132,142],"understanding":[6],"methods":[7],"often":[8],"exhibit":[9],"limited":[10],"interpretability,":[11],"restricting":[12],"effective":[13],"mutual":[14],"enhancement":[15],"between":[16],"these":[17,62],"inherently":[18],"related":[19],"tasks.":[20],"While":[21],"current":[22],"unified":[23,131],"frameworks":[24],"based":[25],"on":[26],"large":[27],"language":[28],"models":[29],"(LLMs)":[30],"leverage":[31],"linguistic":[32],"priors,":[33],"they":[34],"frequently":[35],"encounter":[36],"challenges":[37],"in":[38,49,119,138],"semantic":[39,114],"alignment":[40],"task":[42],"coherence.":[43],"Moreover,":[44],"the":[45,82],"next-token":[46],"prediction":[47,58],"paradigm":[48],"LLMs":[50],"is":[51],"ill-suited":[52],"for":[53],"sequences,":[55],"causing":[56],"cumulative":[57,117],"errors.":[59],"To":[60],"address":[61],"limitations,":[63],"we":[64],"propose":[65],"UniMo,":[66],"a":[67,100],"novel":[68],"framework":[69],"that":[70,103,126],"integrates":[71],"motion-language":[72],"information":[73],"interpretable":[75],"chain":[76],"of":[77,107],"thought":[78],"(CoT)":[79],"reasoning":[80],"into":[81],"LLM":[83],"via":[84],"supervised":[85],"fine-tuning":[86],"(SFT).":[87],"We":[88],"further":[89],"introduce":[90],"reinforcement":[91],"learning":[92],"with":[93],"Group":[94],"Relative":[95],"Policy":[96],"Optimization":[97],"(GRPO)":[98],"as":[99],"post-training":[101],"strategy":[102],"optimizes":[104],"over":[105],"groups":[106],"tokens":[108],"to":[109],"enforce":[110],"structural":[111],"correctness":[112],"alignment,":[115],"mitigating":[116],"errors":[118],"token":[121],"prediction.":[122],"Extensive":[123],"experiments":[124],"demonstrate":[125],"UniMo":[127],"significantly":[128],"outperforms":[129],"existing":[130],"task-specific":[133],"models,":[134],"achieving":[135],"state-of-the-art":[136],"performance":[137],"both":[139],"understanding.":[143]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}