{"id":"https://openalex.org/W7225269732","doi":"https://doi.org/10.48550/arxiv.2611.05279","title":"M\u00f6bius: A Unified Motion-Language Model Bridging Understanding and Generation","display_name":"M\u00f6bius: A Unified Motion-Language Model Bridging Understanding and Generation","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225269732","doi":"https://doi.org/10.48550/arxiv.2611.05279"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2611.05279","doi":"https://doi.org/10.48550/arxiv.2611.05279","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.05279","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"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2611.05279","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123185857","display_name":"Jiazhi Shu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shu, Jiazhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160679356","display_name":"Chengfeng Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Chengfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146604229","display_name":"Jinyi Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jinyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160699397","display_name":"Yubo Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yubo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059487131","display_name":"Zhiyang Dou","orcid":"https://orcid.org/0000-0003-0186-8269","observed_orcids":["https://orcid.org/0000-0003-0186-8269"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dou, Zhiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160654661","display_name":"Ronghui Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ronghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160722643","display_name":"Yu Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160626422","display_name":"Xinwei Jiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Xinwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035823189","display_name":"Zijiao Zeng","orcid":"https://orcid.org/0009-0008-0378-373X","observed_orcids":["https://orcid.org/0009-0008-0378-373X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Zijiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160680822","display_name":"Yuan Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T12290","display_name":"Human Motion and Animation","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T12290","display_name":"Human Motion and Animation","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.0003000000142492354,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/human-motion-understanding","display_name":"human motion understanding","score":0.7490000128746033},{"id":"https://openalex.org/keywords/text-to-motion-generation","display_name":"text-to-motion generation","score":0.8880000114440918},{"id":"https://openalex.org/keywords/motion-editing","display_name":"motion editing","score":0.699999988079071},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.6790000200271606},{"id":"https://openalex.org/keywords/multimodal-representation","display_name":"multimodal representation","score":0.7630000114440918},{"id":"https://openalex.org/keywords/humanml3d","display_name":"HumanML3D","score":0.8309999704360962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7372000217437744},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6862000226974487},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6173999905586243},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5246999859809875},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4982999861240387},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4641000032424927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39329999685287476},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30169999599456787},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C124774092","wikidata":"https://www.wikidata.org/wiki/Q6917782","display_name":"Motion field","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2802000045776367}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2611.05279","doi":"https://doi.org/10.48550/arxiv.2611.05279","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.05279","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":"doi:10.48550/arxiv.2611.05279","doi":"https://doi.org/10.48550/arxiv.2611.05279","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.05279","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7140204962","https://openalex.org/W7129081770","https://openalex.org/W7127988747","https://openalex.org/W7213286805","https://openalex.org/W7212377329","https://openalex.org/W7137961329","https://openalex.org/W4405429568","https://openalex.org/W4415332630","https://openalex.org/W4402754184","https://openalex.org/W7138893360"],"abstract_inverted_index":{"We":[0,51],"aim":[1],"to":[2,41,136],"build":[3],"a":[4,18,33,42,103,122],"truly":[5],"unified":[6,132],"motion":[7,16,22,28,49,68,105,112,133,143],"model":[8],"that":[9,147],"can":[10],"understand,":[11],"generate,":[12],"and":[13,74,86,118,139,153],"edit":[14],"human":[15],"within":[17,121],"single":[19,123],"framework.":[20],"Existing":[21],"UMMs":[23],"remain":[24],"only":[25],"partially":[26],"unified:":[27],"understanding":[29,85],"is":[30,38,150],"handled":[31],"by":[32],"language":[34],"model,":[35],"while":[36,81],"generation":[37,87],"often":[39],"delegated":[40],"separate":[43],"diffusion":[44,58],"module":[45],"operating":[46],"over":[47],"learned":[48],"latents.":[50],"introduce":[52],"M\u00f6bius,":[53],"which":[54],"brings":[55],"the":[56,61],"entire":[57],"process":[59,84],"into":[60],"same":[62],"multimodal":[63],"representation":[64],"space":[65],"used":[66],"for":[67],"understanding.":[69],"Clean":[70],"motion,":[71,73,97],"noisy":[72],"text":[75],"jointly":[76],"participate":[77],"in":[78],"shared":[79],"attention,":[80],"role-specific":[82],"parameters":[83,138],"streams.":[88],"Importantly,":[89],"M\u00f6bius":[90,127],"operates":[91],"directly":[92],"on":[93],"continuous":[94],"frame-level":[95],"raw":[96],"requiring":[98],"neither":[99],"discrete":[100],"tokenization":[101],"nor":[102],"pretrained":[104],"VAE.":[106],"This":[107],"simple":[108],"formulation":[109],"naturally":[110],"supports":[111],"captioning,":[113],"text-to-motion":[114],"generation,":[115],"temporal":[116],"completion,":[117],"instruction-guided":[119],"editing":[120],"model.":[124],"On":[125],"HumanML3D,":[126],"achieves":[128],"state-of-the-art":[129],"performance":[130],"among":[131],"models.":[134],"Scaling":[135],"1.7B":[137],"1,700":[140],"hours":[141],"of":[142],"data":[144],"further":[145],"demonstrates":[146],"our":[148],"framework":[149],"both":[151],"effective":[152],"scalable.":[154]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}