{"id":"https://openalex.org/W7164022720","doi":"https://doi.org/10.48550/arxiv.2606.08520","title":"Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data","display_name":"Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data","publication_year":2026,"publication_date":"2026-06-07","ids":{"openalex":"https://openalex.org/W7164022720","doi":"https://doi.org/10.48550/arxiv.2606.08520"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08520","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08520","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.2606.08520","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122414047","display_name":"Linqi Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Linqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108933637","display_name":"Shiduo Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shiduo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138219412","display_name":"Shenling Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Shenling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138259403","display_name":"Chenxin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chenxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136047797","display_name":"Zhaoyang Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Zhaoyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138260913","display_name":"Lei Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138225463","display_name":"Xiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136088415","display_name":"Chenchen Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Chenchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138257017","display_name":"Zhe Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046216363","display_name":"Pengfang Qian","orcid":"https://orcid.org/0000-0003-3086-4697"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Pengfang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138269992","display_name":"Jingjing Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Jingjing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138255737","display_name":"Xipeng Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Xipeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138272723","display_name":"Xuanjing Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Xuanjing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138225456","display_name":"Yu-Gang Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Yu-Gang","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9251000285148621,"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":0.9251000285148621,"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":0.011500000022351742,"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":0.01080000028014183,"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":0.758899986743927},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.7276999950408936},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5803999900817871},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5447999835014343},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5317000150680542},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.46939998865127563},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3433000147342682},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3203999996185303}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.758899986743927},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7276999950408936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5849000215530396},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5803999900817871},{"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/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5317000150680542},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.2745000123977661},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.26820001006126404},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.2583000063896179},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08520","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08520","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.2606.08520","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08520","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":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"are":[3,26],"powerful":[4],"general-purpose":[5],"reasoners,":[6],"yet":[7],"converting":[8],"them":[9],"into":[10,234],"robot":[11,38,49,107,123,215,237],"control":[12],"policies":[13],"(VLAs)":[14],"is":[15,21,65,227],"surprisingly":[16],"difficult.":[17],"The":[18],"root":[19],"cause":[20],"a":[22,45,132,147,197],"two-fold":[23],"gap:":[24],"VLMs":[25],"trained":[27],"on":[28,48,143],"internet-scale":[29],"images":[30],"with":[31,89,196],"language-understanding":[32,128],"objectives,":[33,129],"while":[34,125,171],"VLAs":[35],"must":[36],"perceive":[37],"scenes":[39,108],"and":[40,67,109,139,218],"predict":[41],"motor":[42],"actions.":[43],"Fine-tuning":[44],"VLM":[46,137,156,232],"directly":[47],"action":[50,113,169,201],"data":[51,117,195,202],"forces":[52],"the":[53,62,68,90,105,119,155,166,173,180,183,204,228],"model":[54,167,205],"to":[55,75,157,182,206,208,230],"cross":[56],"both":[57],"gaps":[58],"at":[59],"once":[60],"--":[61,100],"learning":[63],"curve":[64],"steep":[66],"rich":[69],"generalizations":[70],"learned":[71],"during":[72],"pretraining":[73,138],"tend":[74],"degrade":[76],"rather":[77],"than":[78],"transfer.":[79],"We":[80,94,187],"argue":[81],"that":[82,190,222],"this":[83,223],"gap":[84],"can":[85],"be":[86],"bridged":[87],"gradually":[88,164],"right":[91],"intermediate":[92],"data.":[93],"introduce":[95],"\\emph{embodied":[96],"trajectory-coupled":[97],"(ETC)":[98],"data}":[99],"vision-language":[101],"supervision":[102],"derived":[103],"from":[104],"same":[106],"trajectories":[110],"used":[111],"for":[112],"learning.":[114],"Because":[115],"ETC":[116,194],"shares":[118],"visual":[120],"context":[121],"of":[122,200],"operation":[124],"retaining":[126],"familiar":[127],"it":[130],"provides":[131],"natural":[133],"stepping":[134],"stone":[135],"between":[136],"VLA":[140],"fine-tuning.":[141],"Building":[142],"this,":[144],"we":[145],"design":[146],"three-stage":[148],"training":[149],"recipe.":[150],"Distribution":[151],"Bridging":[152,162],"first":[153],"adapts":[154],"embodied":[158],"visual-language":[159,210],"semantics.":[160],"Objective":[161],"then":[163],"shifts":[165],"toward":[168],"prediction":[170],"preserving":[172],"acquired":[174],"representations.":[175],"Retentive":[176],"Adaptation":[177],"finally":[178],"specializes":[179],"policy":[181],"target":[184],"deployment":[185],"domain.":[186],"further":[188],"show":[189],"mixing":[191],"task-relevant":[192],"out-of-distribution":[193],"small":[198],"amount":[199],"enables":[203],"generalize":[207],"novel":[209],"conditions":[211],"without":[212],"requiring":[213],"additional":[214],"demonstrations.":[216],"Simulation":[217],"real-robot":[219],"experiments":[220],"confirm":[221],"gradual":[224],"bridging":[225],"strategy":[226],"key":[229],"transferring":[231],"generalization":[233],"robust,":[235],"deployable":[236],"policies.":[238]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}