{"id":"https://openalex.org/W4417102591","doi":"https://doi.org/10.1109/iccv51701.2025.00649","title":"FedVLA: Federated Vision-Language-Action Learning with Dual Gating Mixture-of-Experts for Robotic Manipulation","display_name":"FedVLA: Federated Vision-Language-Action Learning with Dual Gating Mixture-of-Experts for Robotic Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417102591","doi":"https://doi.org/10.1109/iccv51701.2025.00649"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.02190","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076709764","display_name":"Cui Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cui Miao","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101154424","display_name":"Tao Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Chang","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045759968","display_name":"Meihan Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meihan Wu","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016248876","display_name":"Hongbin Xu","orcid":"https://orcid.org/0000-0002-3455-1527"},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Hongbin Xu","raw_affiliation_strings":["Bytedance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084461358","display_name":"Chun Guang Li","orcid":"https://orcid.org/0000-0002-7789-2209"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Li","raw_affiliation_strings":["Shenzhen MSU-BIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351426","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-4214-6556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115695468","display_name":"Xiaodong Wang","orcid":"https://orcid.org/0000-0001-8949-5967"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":"6904","last_page":"6913"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7409999966621399,"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":0.7409999966621399,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.06469999998807907,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0272000003606081,"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/task","display_name":"Task (project management)","score":0.7228999733924866},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5587999820709229},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5232999920845032},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5049999952316284},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4837000072002411},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4521999955177307},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.382099986076355},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.373199999332428},{"id":"https://openalex.org/keywords/gating","display_name":"Gating","score":0.37059998512268066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833299994468689},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7228999733924866},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5587999820709229},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5232999920845032},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5049999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016000270843506},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.382099986076355},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3675000071525574},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3671000003814697},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C82578977","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Data aggregator","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.02190","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02190","pdf_url":"https://arxiv.org/pdf/2508.02190","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.02190","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.02190","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":"pmh:oai:arXiv.org:2508.02190","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.02190","pdf_url":"https://arxiv.org/pdf/2508.02190","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8050699350","display_name":null,"funder_award_id":"2024A1515011774","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language-action":[0],"(VLA)":[1],"models":[2,21],"have":[3],"significantly":[4,170],"advanced":[5],"robotic":[6,160],"manipulation":[7],"by":[8,149],"enabling":[9,53,77],"robots":[10],"to":[11,175,186],"interpret":[12],"language":[13],"instructions":[14],"for":[15],"task":[16,101,110,182],"execution.":[17],"However,":[18],"training":[19,56,81],"these":[20],"often":[22],"relies":[23],"on":[24,100],"large-scale":[25],"user-specific":[26],"data,":[27],"raising":[28],"concerns":[29],"about":[30],"privacy":[31,60],"and":[32,73,79,95,158],"security,":[33],"which":[34,93],"in":[35],"turn":[36],"limits":[37],"their":[38,131],"broader":[39],"adoption.":[40],"To":[41,106],"address":[42],"this,":[43],"we":[44,86,112,134],"propose":[45,135],"FedVLA,":[46],"the":[47,141,163],"first":[48],"federated":[49,75,142],"VLA":[50,83],"learning":[51],"framework,":[52],"distributed":[54],"model":[55,145],"that":[57],"preserves":[58],"data":[59,191],"without":[61],"compromising":[62],"performance.":[63],"Our":[64],"framework":[65],"integrates":[66],"task-aware":[67],"representation":[68],"learning,":[69],"adaptive":[70],"expert":[71],"selection,":[72],"expert-driven":[74],"aggregation,":[76],"efficient":[78],"privacy-preserving":[80],"of":[82,165],"models.":[84],"Specifically,":[85],"introduce":[87],"an":[88,136],"Instruction":[89],"Oriented":[90],"Scene-Parsing":[91],"mechanism,":[92,119],"decomposes":[94],"enhances":[96],"object-level":[97],"features":[98],"based":[99],"instructions,":[102],"improving":[103],"contextual":[104],"understanding.":[105],"effectively":[107,189],"learn":[108],"diverse":[109],"patterns,":[111],"design":[113],"a":[114],"Dual":[115],"Gating":[116],"Mixture-of-Experts":[117],"(DGMoE)":[118],"where":[120,144],"not":[121],"only":[122],"input":[123],"tokens":[124],"but":[125],"also":[126],"self-aware":[127],"experts":[128],"adaptively":[129],"decide":[130],"activation.":[132],"Finally,":[133],"Expert-Driven":[137],"Aggregation":[138],"strategy":[139],"at":[140],"server,":[143],"aggregation":[146],"is":[147],"guided":[148],"activated":[150],"experts,":[151],"ensuring":[152],"effective":[153],"cross-client":[154],"knowledge":[155],"transfer.Extensive":[156],"simulations":[157],"real-world":[159],"experiments":[161],"demonstrate":[162],"effectiveness":[164],"our":[166],"proposals.":[167],"Notably,":[168],"DGMoE":[169],"improves":[171],"computational":[172],"efficiency":[173],"compared":[174],"its":[176],"vanilla":[177],"counterpart,":[178],"while":[179],"FedVLA":[180],"achieves":[181],"success":[183],"rates":[184],"comparable":[185],"centralized":[187],"training,":[188],"preserving":[190],"privacy.":[192]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}