{"id":"https://openalex.org/W7155164012","doi":"https://doi.org/10.48550/arxiv.2604.19734","title":"UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling","display_name":"UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155164012","doi":"https://doi.org/10.48550/arxiv.2604.19734"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.19734","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19734","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.19734","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134312818","display_name":"Boyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Boyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134342770","display_name":"Yi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134337915","display_name":"Lu Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134283622","display_name":"Jerry Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Jerry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134339546","display_name":"Yuying Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Yuying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134227166","display_name":"Yixiao Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Yixiao","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/T10812","display_name":"Human Pose and Action Recognition","score":0.23549999296665192,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.23549999296665192,"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":0.20319999754428864,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.14790000021457672,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.45680001378059387},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4180999994277954},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4120999872684479},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.37940001487731934},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.3508000075817108},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3481000065803528},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3379000127315521},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3183000087738037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7452999949455261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.535099983215332},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49959999322891235},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.45680001378059387},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3481000065803528},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3179999887943268},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C90697248","wikidata":"https://www.wikidata.org/wiki/Q1062896","display_name":"Character animation","level":4,"score":0.2621999979019165},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.19734","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19734","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.19734","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19734","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scaling":[0],"humanoid":[1,141,184,206,224],"foundation":[2],"models":[3],"is":[4],"bottlenecked":[5],"by":[6,188,197],"the":[7,22,56,201],"scarcity":[8],"of":[9,104,203],"robotic":[10],"data.":[11],"While":[12],"massive":[13],"egocentric":[14],"human":[15,127,175,204,220],"data":[16,128,132,176],"offers":[17,213],"a":[18,26,43,47,67,91,99,190,209,214],"scalable":[19,215],"alternative,":[20],"bridging":[21],"cross-embodiment":[23,158,193],"chasm":[24],"remains":[25],"fundamental":[27],"challenge":[28],"due":[29],"to":[30,74,77,84,129,217],"kinematic":[31],"mismatches.":[32],"We":[33,108],"introduce":[34],"UniT":[35,65,110,212],"(Unified":[36],"Latent":[37],"Action":[38],"Tokenizer":[39],"via":[40,160],"Visual":[41],"Anchoring),":[42],"framework":[44],"that":[45,58,174],"establishes":[46],"unified":[48,121,161],"physical":[49,78,106],"language":[50],"for":[51,183],"human-to-humanoid":[52,168],"transfer.":[53,151,170],"Grounded":[54],"in":[55],"philosophy":[57],"heterogeneous":[59],"kinematics":[60,76],"share":[61],"universal":[62],"visual":[63,88],"consequences,":[64],"employs":[66],"tri-branch":[68],"cross-reconstruction":[69],"mechanism:":[70],"actions":[71,83],"predict":[72],"vision":[73,81],"anchor":[75],"outcomes,":[79],"while":[80],"reconstructs":[82],"filter":[85],"out":[86],"irrelevant":[87],"confounders.":[89],"Concurrently,":[90],"fusion":[92],"branch":[93],"synergies":[94],"these":[95,120],"purified":[96],"modalities":[97],"into":[98,179,208,222],"shared":[100,210],"discrete":[101],"latent":[102],"space":[103],"embodiment-agnostic":[105],"intents.":[107],"validate":[109],"across":[111],"two":[112],"paradigms:":[113],"1)":[114],"Policy":[115],"Learning":[116],"(VLA-UniT):":[117],"By":[118,156],"predicting":[119],"tokens,":[122],"it":[123,165],"effectively":[124],"leverages":[125],"diverse":[126],"achieve":[130],"state-of-the-art":[131],"efficiency":[133],"and":[134,144,205],"robust":[135],"out-of-distribution":[136],"(OOD)":[137],"generalization":[138],"on":[139],"both":[140],"simulation":[142],"benchmark":[143],"real-world":[145],"deployments,":[146],"notably":[147],"demonstrating":[148],"zero-shot":[149],"task":[150],"2)":[152],"World":[153],"Modeling":[154],"(WM-UniT):":[155],"aligning":[157],"dynamics":[159],"tokens":[162],"as":[163],"conditions,":[164],"realizes":[166],"direct":[167],"action":[169,181],"This":[171],"alignment":[172],"ensures":[173],"seamlessly":[177],"translates":[178],"enhanced":[180],"controllability":[182],"video":[185],"generation.":[186],"Ultimately,":[187],"inducing":[189],"highly":[191],"aligned":[192],"representation":[194],"(empirically":[195],"verified":[196],"t-SNE":[198],"visualizations":[199],"revealing":[200],"convergence":[202],"features":[207],"manifold),":[211],"path":[216],"distill":[218],"vast":[219],"knowledge":[221],"general-purpose":[223],"capabilities.":[225]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-23T00:00:00"}