{"id":"https://openalex.org/W7162121028","doi":"https://doi.org/10.48550/arxiv.2605.22671","title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","display_name":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","publication_year":2026,"publication_date":"2026-05-21","ids":{"openalex":"https://openalex.org/W7162121028","doi":"https://doi.org/10.48550/arxiv.2605.22671"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.22671","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22671","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.2605.22671","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136759364","display_name":"Bing Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Bing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136801129","display_name":"Zaijing Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zaijing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136782991","display_name":"Rui Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136735868","display_name":"Junda Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Junda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054211485","display_name":"April Hua Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, April Hua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136760090","display_name":"Wei-Shi Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Wei-Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136734578","display_name":"Liqiang Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Liqiang","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":0.8938000202178955,"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":0.8938000202178955,"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":0.013899999670684338,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.013399999588727951,"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/abstraction","display_name":"Abstraction","score":0.6855999827384949},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6079000234603882},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.541700005531311},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5404000282287598},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.48410001397132874},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.45170000195503235},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41999998688697815},{"id":"https://openalex.org/keywords/behavioral-modeling","display_name":"Behavioral modeling","score":0.3765999972820282},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.3614000082015991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7319999933242798},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6855999827384949},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6079000234603882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5777999758720398},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.541700005531311},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5404000282287598},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.45170000195503235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43380001187324524},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C78639753","wikidata":"https://www.wikidata.org/wiki/Q3318160","display_name":"Behavioral modeling","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C2778858076","wikidata":"https://www.wikidata.org/wiki/Q5249539","display_name":"Decodes","level":3,"score":0.3294000029563904},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30959999561309814},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C2777379011","wikidata":"https://www.wikidata.org/wiki/Q938545","display_name":"Implicit learning","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.22671","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22671","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.2605.22671","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22671","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-Action":[0],"(VLA)":[1],"models":[2],"often":[3,36],"suffer":[4],"from":[5],"performance":[6,151],"degradation":[7],"under":[8],"distribution":[9],"shifts,":[10],"as":[11],"they":[12,34],"struggle":[13],"to":[14,26,46,92],"learn":[15],"generalized":[16],"behavior":[17,28,100],"representations":[18,29],"across":[19],"varying":[20],"environments.":[21],"While":[22],"existing":[23],"approaches":[24],"attempt":[25],"construct":[27],"through":[30,65],"action-centric":[31],"latent":[32],"variables,":[33],"are":[35],"limited":[37],"by":[38,116],"short-horizon":[39],"temporal":[40],"fragmentation":[41],"and":[42,102,130,139,166],"static":[43],"execution-alignment,":[44],"leading":[45],"inconsistent":[47],"behaviors":[48],"in":[49,144],"complex":[50],"scenarios.":[51],"To":[52],"address":[53],"these":[54],"limitations,":[55],"we":[56],"propose":[57],"\\textbf{BehaviorVLA},":[58],"a":[59,69,88,98],"framework":[60],"that":[61],"facilitates":[62],"robust":[63],"manipulation":[64],"the":[66,81,104,150,158],"learning":[67],"of":[68,136,152,157],"temporally":[70],"coherent":[71],"behavioral":[72],"representations.":[73],"Our":[74],"approach":[75],"features":[76],"two":[77],"symmetric":[78],"components:":[79],"(1)":[80],"\\textbf{Visuomotor":[82],"Behavior":[83,106],"Encoder":[84],"(VBE)},":[85],"which":[86,109],"utilizes":[87],"causal":[89],"Mamba-based":[90],"architecture":[91],"aggregate":[93],"long-horizon":[94],"trajectory":[95],"information":[96],"into":[97,113],"unified":[99],"representation;":[101],"(2)":[103],"\\textbf{Phase-conditioned":[105],"Decoder":[107],"(PBD)},":[108],"decodes":[110],"this":[111],"representation":[112],"precise":[114],"actions":[115],"dynamically":[117],"aligning":[118],"task-level":[119],"priors":[120],"with":[121],"real-time":[122],"execution":[123],"progress.":[124],"Experiments":[125],"on":[126],"RoboTwin":[127],"2.0,":[128],"LIBERO,":[129],"CALVIN":[131],"demonstrate":[132],"state-of-the-art":[133],"success":[134],"rates":[135],"58\\%,":[137],"98\\%,":[138],"4.36":[140],"(Avg.Len),":[141],"respectively.":[142],"Notably,":[143],"real-world":[145],"sim-to-real":[146],"transfer,":[147],"BehaviorVLA":[148],"matches":[149],"OpenVLA-OFT":[153],"using":[154],"only":[155],"50\\%":[156],"demonstration":[159],"data,":[160],"showcasing":[161],"its":[162],"superior":[163],"data":[164],"efficiency":[165],"generalization.":[167]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-23T00:00:00"}