{"id":"https://openalex.org/W7128735367","doi":"https://doi.org/10.48448/44hv-0a56","title":"VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model","display_name":"VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7128735367","doi":"https://doi.org/10.48448/44hv-0a56"},"language":"en","primary_location":{"id":"doi:10.48448/44hv-0a56","doi":"https://doi.org/10.48448/44hv-0a56","is_oa":true,"landing_page_url":"https://doi.org/10.48448/44hv-0a56","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},"volume":null,"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/44hv-0a56","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125741655","display_name":"Association for Artificial Intelligence 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Artificial Intelligence 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125696797","display_name":"Can Cui","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Can","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125738178","display_name":"Pengxiang Ding","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding, Pengxiang","raw_affiliation_strings":["Westlake University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044674916","display_name":"Zirui Ge","orcid":"https://orcid.org/0000-0001-6307-1330","observed_orcids":["https://orcid.org/0000-0001-6307-1330"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Zirui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104217786","display_name":"Pengxu Hou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Pengxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125724563","display_name":"Siteng Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Siteng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125717997","display_name":"Lingxiao Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Lingxiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125762773","display_name":"Jianyi Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jianyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125722242","display_name":"Wenxuan Song","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Wenxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125713836","display_name":"Yifan Tang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148463243","display_name":"Xinyang Tong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong, Xinyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128720642","display_name":"Wenhui Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenhui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125748977","display_name":"Yihao Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125773560","display_name":"Donglin Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Donglin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125717894","display_name":"Ru Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125746438","display_name":"Wei Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129667756","display_name":"Han Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Han","raw_affiliation_strings":["Westlake University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.5756999850273132,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5756999850273132,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.37869998812675476,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0333000011742115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-language-action-models","display_name":"vision-language-action models","score":0.9819999933242798},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.45500001311302185},{"id":"https://openalex.org/keywords/low-parameter-models","display_name":"low-parameter models","score":0.4399999976158142},{"id":"https://openalex.org/keywords/training-cost-reduction","display_name":"training cost reduction","score":0.4880000054836273}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8410999774932861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7416999936103821},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.6302000284194946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5637000203132629},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4964999854564667},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34700000286102295},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.30720001459121704},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26980000734329224},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/44hv-0a56","doi":"https://doi.org/10.48448/44hv-0a56","is_oa":true,"landing_page_url":"https://doi.org/10.48448/44hv-0a56","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/44hv-0a56","doi":"https://doi.org/10.48448/44hv-0a56","is_oa":true,"landing_page_url":"https://doi.org/10.48448/44hv-0a56","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7128735618","https://openalex.org/W4407874080","https://openalex.org/W4403794704","https://openalex.org/W7167845562","https://openalex.org/W4416026884","https://openalex.org/W4414898213","https://openalex.org/W7171876109","https://openalex.org/W4415274508","https://openalex.org/W7131819932","https://openalex.org/W7204906227"],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2,61],"typically":[3],"bridge":[4,41],"the":[5,57,75,112,116,157,167,174,192],"gap":[6],"between":[7],"perceptual":[8],"and":[9,65,81,93,142],"action":[10,46,94,117],"spaces":[11],"by":[12],"pre-training":[13],"a":[14,51,102,129,177,186],"Vision-Language":[15],"Model":[16],"(VLM)":[17],"on":[18,62,85,97,139,185],"robotic":[19,134,144],"data.":[20],"While":[21],"this":[22,34,69,120],"approach":[23],"greatly":[24],"enhances":[25],"performance,":[26,153],"it":[27],"also":[28,155],"incurs":[29],"significant":[30],"training":[31,175],"costs.":[32],"In":[33,119],"paper,":[35],"we":[36,71,100],"investigate":[37],"how":[38],"to":[39,45,55,162,166,194],"effectively":[40],"vision-language":[42],"(VL)":[43],"representations":[44],"(A).":[47],"We":[48],"introduce":[49],"VLA-Adapter,":[50],"novel":[52],"paradigm":[53],"designed":[54],"reduce":[56],"reliance":[58],"of":[59,77,176],"VLA":[60,179,196],"large-scale":[63],"VLMs":[64],"extensive":[66],"pre-training.":[67,136],"To":[68],"end,":[70],"first":[72],"systematically":[73],"analyze":[74],"effectiveness":[76],"various":[78],"VL":[79],"conditions":[80,87],"present":[82],"key":[83],"findings":[84],"which":[86,109],"are":[88],"essential":[89],"for":[90],"bridging":[91,170],"perception":[92],"spaces.":[95],"Based":[96],"these":[98],"insights,":[99],"propose":[101],"lightweight":[103],"Policy":[104],"module":[105],"with":[106],"Bridge":[107],"Attention,":[108],"autonomously":[110],"injects":[111],"optimal":[113],"condition":[114],"into":[115],"space.":[118],"way,":[121],"our":[122],"method":[123],"achieves":[124,151],"high":[125],"performance":[126],"using":[127],"only":[128,150],"0.5B-parameter":[130],"backbone,":[131],"without":[132],"any":[133],"data":[135],"Extensive":[137],"experiments":[138],"both":[140],"simulated":[141],"real-world":[143],"benchmarks":[145],"demonstrate":[146],"that":[147],"VLA-Adapter":[148,172],"not":[149],"state-of-the-art":[152],"but":[154],"offers":[156],"fast":[158],"inference":[159],"speed":[160],"reported":[161],"date.":[163],"Furthermore,":[164],"thanks":[165],"proposed":[168],"advanced":[169],"paradigm,":[171],"enables":[173],"powerful":[178],"model":[180],"in":[181],"just":[182],"8":[183],"hours":[184],"single":[187],"consumer-grade":[188],"GPU,":[189],"significantly":[190],"lowering":[191],"barrier":[193],"deploying":[195],"models.":[197]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-13T00:00:00"}