{"id":"https://openalex.org/W7125276686","doi":"https://doi.org/10.48550/arxiv.2601.12993","title":"Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization","display_name":"Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization","publication_year":2026,"publication_date":"2026-01-19","ids":{"openalex":"https://openalex.org/W7125276686","doi":"https://doi.org/10.48550/arxiv.2601.12993"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.12993","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.12993","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.12993","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123520537","display_name":"Hao Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Luo, Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123485115","display_name":"Ye Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ye","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123523503","display_name":"Wanpeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wanpeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017047744","display_name":"Sipeng Zheng","orcid":"https://orcid.org/0000-0001-5331-6314"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Sipeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100591146","display_name":"Ziheng Xi","orcid":"https://orcid.org/0009-0008-7007-8803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi, Ziheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090850096","display_name":"Chaoyi Xu","orcid":"https://orcid.org/0000-0002-9870-4297"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Chaoyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123520934","display_name":"Haiweng Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Haiweng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123530251","display_name":"Haoqi Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Haoqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123483293","display_name":"Chi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123482916","display_name":"Yiqing Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yiqing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100609931","display_name":"Yicheng Feng","orcid":"https://orcid.org/0000-0002-4652-7794"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Yicheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103979188","display_name":"Zongqing Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Zongqing","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5123520537"],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3287999927997589,"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":0.3287999927997589,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.2615000009536743,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.13680000603199005,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6291000247001648},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.49900001287460327},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.3955000042915344},{"id":"https://openalex.org/keywords/data-driven","display_name":"Data-driven","score":0.38190001249313354},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3743000030517578},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.3716999888420105},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.3395000100135803},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.30979999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7186999917030334},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6291000247001648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5789999961853027},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.49900001287460327},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4041000008583069},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3955000042915344},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3743000030517578},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C107953548","wikidata":"https://www.wikidata.org/wiki/Q1172433","display_name":"Wired glove","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2614000141620636},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.25429999828338623},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.12993","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.12993","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":"doi:10.48550/arxiv.2601.12993","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.12993","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46259984374046326}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,178],"introduce":[1,154],"Being-H0.5,":[2],"a":[3,30,40,75,107,125,129],"foundational":[4],"Vision-Language-Action":[5],"(VLA)":[6],"model":[7],"designed":[8],"for":[9,44,157],"robust":[10],"cross-embodiment":[11,146,200],"generalization":[12],"across":[13,67,170],"diverse":[14],"robotic":[15,70,120,204],"platforms.":[16,99,205],"While":[17],"existing":[18],"VLAs":[19],"often":[20],"struggle":[21],"with":[22,172],"morphological":[23],"heterogeneity":[24],"and":[25,97,111,119,162,175,193],"data":[26,66,96],"scarcity,":[27],"we":[28,50,105,153],"propose":[29],"human-centric":[31,103],"learning":[32],"paradigm":[33,114],"that":[34,79,181],"treats":[35],"human":[36,95,117],"interaction":[37],"traces":[38],"as":[39,190],"universal":[41],"\"mother":[42],"tongue\"":[43],"physical":[45],"interaction.":[46],"To":[47],"support":[48],"this,":[49],"present":[51],"UniHand-2.0,":[52],"the":[53,150],"largest":[54],"embodied":[55],"pre-training":[56,113],"recipe":[57],"to":[58,91,115,134,144,166],"date,":[59],"comprising":[60],"over":[61],"35,000":[62],"hours":[63],"of":[64],"multimodal":[65],"30":[68],"distinct":[69],"embodiments.":[71],"Our":[72],"approach":[73],"introduces":[74],"Unified":[76],"Action":[77],"Space":[78],"maps":[80],"heterogeneous":[81],"robot":[82],"controls":[83],"into":[84],"semantically":[85],"aligned":[86],"slots,":[87],"enabling":[88],"low-resource":[89],"robots":[90],"bootstrap":[92],"skills":[93],"from":[94,139],"high-resource":[98],"Built":[100],"upon":[101],"this":[102],"foundation,":[104],"design":[106,127],"unified":[108],"sequential":[109],"modeling":[110],"multi-task":[112],"bridge":[116],"demonstrations":[118],"execution.":[121],"Architecturally,":[122],"Being-H0.5":[123,182],"utilizes":[124],"Mixture-of-Transformers":[126],"featuring":[128],"novel":[130],"Mixture-of-Flow":[131],"(MoF)":[132],"framework":[133],"decouple":[135],"shared":[136],"motor":[137],"primitives":[138],"specialized":[140],"embodiment-specific":[141],"experts.":[142],"Finally,":[143],"make":[145],"policies":[147],"stable":[148],"in":[149],"real":[151],"world,":[152],"Manifold-Preserving":[155],"Gating":[156],"robustness":[158],"under":[159],"sensory":[160],"shift":[161],"Universal":[163],"Async":[164],"Chunking":[165],"universalize":[167],"chunked":[168],"control":[169,176],"embodiments":[171],"different":[173],"latency":[174],"profiles.":[177],"empirically":[179],"demonstrate":[180],"achieves":[183],"state-of-the-art":[184],"results":[185],"on":[186,202],"simulated":[187],"benchmarks,":[188],"such":[189],"LIBERO":[191],"(98.9%)":[192],"RoboCasa":[194],"(53.9%),":[195],"while":[196],"also":[197],"exhibiting":[198],"strong":[199],"capabilities":[201],"five":[203]},"counts_by_year":[],"updated_date":"2026-01-22T23:33:04.759266","created_date":"2026-01-22T00:00:00"}