{"id":"https://openalex.org/W4404341045","doi":"https://doi.org/10.48550/arxiv.2410.21747","title":"MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding","display_name":"MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4404341045","doi":"https://doi.org/10.48550/arxiv.2410.21747"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.21747","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.21747","pdf_url":"https://arxiv.org/pdf/2410.21747","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.21747","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101382035","display_name":"Yuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Yuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056972984","display_name":"Di Huang","orcid":"https://orcid.org/0000-0002-2412-9330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Di","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378919","display_name":"Yaqi Zhang","orcid":"https://orcid.org/0000-0002-6902-337X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yaqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087818121","display_name":"Wanli Ouyang","orcid":"https://orcid.org/0000-0002-9163-2761"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Wanli","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006378664","display_name":"Jile Jiao","orcid":"https://orcid.org/0000-0003-2644-717X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao, Jile","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055185546","display_name":"Xuetao Feng","orcid":"https://orcid.org/0000-0002-1309-8954"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Xuetao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115597228","display_name":"Yan Zhou","orcid":"https://orcid.org/0009-0009-4564-4014"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070906424","display_name":"Pengfei Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Pengfei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030884047","display_name":"Shixiang Tang","orcid":"https://orcid.org/0009-0005-0067-339X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Shixiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100942081","display_name":"Dan Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Dan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5101382035"],"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":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":0.9771999716758728,"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":0.9771999716758728,"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":0.9735999703407288,"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/T12031","display_name":"Speech and dialogue systems","score":0.9717000126838684,"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/motion","display_name":"Motion (physics)","score":0.7390670776367188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4452473223209381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22737213969230652}],"concepts":[{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7390670776367188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4452473223209381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22737213969230652}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.21747","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.21747","pdf_url":"https://arxiv.org/pdf/2410.21747","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.21747","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.21747","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.21747","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.21747","pdf_url":"https://arxiv.org/pdf/2410.21747","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404341045.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Generating":[0],"lifelike":[1],"human":[2],"motions":[3],"from":[4],"descriptive":[5],"texts":[6],"has":[7],"experienced":[8],"remarkable":[9],"research":[10],"focus":[11,38],"in":[12],"the":[13,18,91,103,117,124,133,154,160],"recent":[14],"years,":[15],"propelled":[16],"by":[17,31,132],"emerging":[19],"requirements":[20],"of":[21,144,156,162],"digital":[22],"humans.Despite":[23],"impressive":[24],"advances,":[25],"existing":[26],"approaches":[27],"are":[28,96],"often":[29],"constrained":[30],"limited":[32],"control":[33,67],"modalities,":[34],"task":[35],"specificity,":[36],"and":[37,64,81,146,151,169],"solely":[39],"on":[40],"body":[41,145],"motion":[42,107,128,135,165,167,171],"representations.In":[43],"this":[44],"paper,":[45],"we":[46],"present":[47],"MotionGPT-2,":[48],"a":[49,110],"unified":[50,100],"Large":[51,71],"Motion-Language":[52],"Model":[53],"(LMLM)":[54],"that":[55,116],"addresses":[56],"these":[57],"limitations.":[58],"MotionGPT-2":[59,119,163],"accommodates":[60],"multiple":[61],"motion-relevant":[62],"tasks":[63],"supporting":[65],"multimodal":[66,77],"conditions":[68],"through":[69,109],"pre-trained":[70],"Language":[72],"Models":[73],"(LLMs).":[74],"It":[75],"quantizes":[76],"inputs-such":[78],"as":[79],"text":[80],"single-frame":[82],"poses-into":[83],"discrete,":[84],"LLM-interpretable":[85],"tokens,":[86],"seamlessly":[87],"integrating":[88],"them":[89],"into":[90,99],"LLM's":[92],"vocabulary.":[93],"These":[94],"tokens":[95],"then":[97],"organized":[98],"prompts,":[101],"guiding":[102],"LLM":[104],"to":[105,123],"generate":[106],"outputs":[108],"pretraining-then-finetuning":[111],"paradigm.":[112],"We":[113],"also":[114],"show":[115],"proposed":[118],"is":[120],"highly":[121],"adaptable":[122],"challenging":[125],"3D":[126],"holistic":[127],"generation":[129],"task,":[130],"enabled":[131],"innovative":[134],"discretization":[136],"framework,":[137],"Part-Aware":[138],"VQVAE,":[139],"which":[140],"ensures":[141],"fine-grained":[142],"representations":[143],"hand":[147],"movements.":[148],"Extensive":[149],"experiments":[150],"visualizations":[152],"validate":[153],"effectiveness":[155],"our":[157],"method,":[158],"demonstrating":[159],"adaptability":[161],"across":[164],"generation,":[166],"captioning,":[168],"generalized":[170],"completion":[172],"tasks.":[173]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2024-11-14T00:00:00"}