{"id":"https://openalex.org/W7147346756","doi":"https://doi.org/10.48550/arxiv.2603.28766","title":"HandX: Scaling Bimanual Motion and Interaction Generation","display_name":"HandX: Scaling Bimanual Motion and Interaction Generation","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7147346756","doi":"https://doi.org/10.48550/arxiv.2603.28766"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2603.28766","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.28766","pdf_url":"https://arxiv.org/pdf/2603.28766","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.28766","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132586886","display_name":"Zimu Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zimu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132693678","display_name":"Yucheng Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yucheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101571671","display_name":"Xiyan Xu","orcid":"https://orcid.org/0009-0009-4609-064X","observed_orcids":["https://orcid.org/0009-0009-4609-064X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Xiyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132664215","display_name":"Ziyin Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ziyin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132555152","display_name":"Sirui Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Sirui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132605552","display_name":"Kai Zhou","orcid":"https://orcid.org/0009-0003-4681-1327","observed_orcids":["https://orcid.org/0009-0003-4681-1327"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132730068","display_name":"Bing Zhou","orcid":"https://orcid.org/0000-0002-0838-7858","observed_orcids":["https://orcid.org/0000-0002-0838-7858"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Bing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132687646","display_name":"Chuan Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Chuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132639316","display_name":"Jian Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132726620","display_name":"Yu-Xiong Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yu-Xiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016962709","display_name":"Liang-Yan Gui","orcid":"https://orcid.org/0009-0005-8204-3577","observed_orcids":["https://orcid.org/0009-0005-8204-3577"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gui, Liang-Yan","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":true,"cited_by_count":1,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.0003000000142492354,"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":9.999999747378752e-05,"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/finger-dynamics","display_name":"finger dynamics","score":0.8889999985694885},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7670000195503235},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8009999990463257},{"id":"https://openalex.org/keywords/autoregressive-models","display_name":"autoregressive models","score":0.9259999990463257},{"id":"https://openalex.org/keywords/contact-events","display_name":"contact events","score":0.5299999713897705}],"concepts":[{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7257999777793884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6868000030517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5726000070571899},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5570999979972839},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48649999499320984},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.37119999527931213},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3328000009059906},{"id":"https://openalex.org/C2778931886","wikidata":"https://www.wikidata.org/wiki/Q5164827","display_name":"Contact dynamics","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C81302111","wikidata":"https://www.wikidata.org/wiki/Q2916417","display_name":"Contact force","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C2780806968","wikidata":"https://www.wikidata.org/wiki/Q6045196","display_name":"Interaction model","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.25429999828338623},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2603.28766","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.28766","pdf_url":"https://arxiv.org/pdf/2603.28766","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2603.28766","doi":"https://doi.org/10.48550/arxiv.2603.28766","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28766","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":"pmh:oai:arXiv.org:2603.28766","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.28766","pdf_url":"https://arxiv.org/pdf/2603.28766","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1957999595","display_name":null,"funder_award_id":"#2020-67021-32799","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"},{"id":"https://openalex.org/G2926720356","display_name":null,"funder_award_id":"32799","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"},{"id":"https://openalex.org/G539587745","display_name":"RI: Medium: Creating Knowledge with All-Novel-Class Computer Vision","funder_award_id":"2106825","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5620962805","display_name":null,"funder_award_id":"67021","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G953761186","display_name":"RI: Small: Empowering Longer Video Understanding via Token Compression, Selection, and Reasoning","funder_award_id":"2519216","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"},{"id":"https://openalex.org/F4320312143","display_name":"National Centre for Supercomputing Applications","ror":"https://ror.org/03r10zj06"},{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332299","display_name":"National Institute of Food and Agriculture","ror":"https://ror.org/05qx3fv49"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7147346756.pdf","grobid_xml":"https://content.openalex.org/works/W7147346756.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W4297808394","https://openalex.org/W4385764101","https://openalex.org/W4387839234","https://openalex.org/W4390041933","https://openalex.org/W4391305822","https://openalex.org/W4414981886","https://openalex.org/W4415334874","https://openalex.org/W4416749668","https://openalex.org/W4417299960","https://openalex.org/W7118854641","https://openalex.org/W7131633817","https://openalex.org/W7160040527"],"related_works":["https://openalex.org/W4417307846","https://openalex.org/W7134804361","https://openalex.org/W4409367575","https://openalex.org/W4413147696","https://openalex.org/W4402703088","https://openalex.org/W4413145043","https://openalex.org/W4417041439","https://openalex.org/W7119496200","https://openalex.org/W4382457768","https://openalex.org/W7117122519"],"abstract_inverted_index":{"Synthesizing":[0],"human":[1],"motion":[2,9,95,142],"has":[3],"advanced":[4],"rapidly,":[5],"yet":[6],"realistic":[7],"hand":[8],"and":[10,30,33,45,60,64,70,100,103,126,131],"bimanual":[11,38,78,168],"interaction":[12],"remain":[13],"underexplored.":[14],"Whole-body":[15],"models":[16,110,133,158],"often":[17],"miss":[18],"the":[19,123],"fine-grained":[20],"cues":[21],"that":[22,40,92],"drive":[23],"dexterous":[24,141],"behavior,":[25],"finger":[26,43,82,101],"articulation,":[27],"contact":[28,98],"timing,":[29],"inter-hand":[31],"coordination,":[32],"existing":[34,66],"resources":[35],"lack":[36],"high-fidelity":[37],"sequences":[39],"capture":[41],"nuanced":[42],"dynamics":[44],"collaboration.":[46],"To":[47],"fill":[48],"this":[49],"gap,":[50],"we":[51,87,128],"present":[52],"HandX,":[53],"a":[54,72,89],"unified":[55],"foundation":[56],"spanning":[57],"data,":[58],"annotation,":[59,86],"evaluation.":[61],"We":[62,151],"consolidate":[63],"filter":[65],"datasets":[67,163],"for":[68],"quality,":[69],"collect":[71],"new":[73],"motion-capture":[74],"dataset":[75,171],"targeting":[76],"underrepresented":[77],"interactions":[79],"with":[80,118,134],"detailed":[81],"dynamics.":[83],"For":[84],"scalable":[85],"introduce":[88],"decoupled":[90],"strategy":[91],"extracts":[93],"representative":[94],"features,":[96],"e.g.,":[97],"events":[99],"flexion,":[102],"then":[104],"leverages":[105],"reasoning":[106],"from":[107],"large":[108],"language":[109],"to":[111,174],"produce":[112,164],"fine-grained,":[113],"semantically":[114,166],"rich":[115],"descriptions":[116],"aligned":[117],"these":[119],"features.":[120],"Building":[121],"on":[122,160],"resulting":[124],"data":[125],"annotations,":[127],"benchmark":[129],"diffusion":[130],"autoregressive":[132],"versatile":[135],"conditioning":[136],"modes.":[137],"Experiments":[138],"demonstrate":[139],"high-quality":[140],"generation,":[143],"supported":[144],"by":[145],"our":[146],"newly":[147],"proposed":[148],"hand-focused":[149],"metrics.":[150],"further":[152],"observe":[153],"clear":[154],"scaling":[155],"trends:":[156],"larger":[157],"trained":[159],"larger,":[161],"higher-quality":[162],"more":[165],"coherent":[167],"motion.":[169],"Our":[170],"is":[172],"released":[173],"support":[175],"future":[176],"research.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-04-02T00:00:00"}