{"id":"https://openalex.org/W7162681561","doi":"https://doi.org/10.48550/arxiv.2605.28527","title":"What Frozen VLAs Already Know About Success: A Probing Study of Value-Like Structure in Foundation Robot Policies","display_name":"What Frozen VLAs Already Know About Success: A Probing Study of Value-Like Structure in Foundation Robot Policies","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162681561","doi":"https://doi.org/10.48550/arxiv.2605.28527"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.28527","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28527","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.2605.28527","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129646233","display_name":"Jiachen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I52158045","display_name":"China Agricultural University","ror":"https://ror.org/04v3ywz14","country_code":"CN","type":"education","lineage":["https://openalex.org/I52158045"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Jiachen","raw_affiliation_strings":["Peking University","China Agricultural University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"China Agricultural University","institution_ids":["https://openalex.org/I52158045"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100586000","display_name":"Junnan Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nie, Junnan","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137230329","display_name":"Junyi Lao","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lao, Junyi","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046943571","display_name":"Wei Cheng","orcid":"https://orcid.org/0000-0002-1475-4079"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng, Wei","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137231710","display_name":"Chenghao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Chenghao","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137286042","display_name":"Jiaxin Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I52158045","display_name":"China Agricultural University","ror":"https://ror.org/04v3ywz14","country_code":"CN","type":"education","lineage":["https://openalex.org/I52158045"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Jiaxin","raw_affiliation_strings":["China Agricultural University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Agricultural University","institution_ids":["https://openalex.org/I52158045"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047856952","display_name":"Songfang Huang","orcid":"https://orcid.org/0000-0001-8084-0904"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Songfang","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.6324999928474426,"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":0.6324999928474426,"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":0.10599999874830246,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.06689999997615814,"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/task","display_name":"Task (project management)","score":0.685699999332428},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.678600013256073},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5952000021934509},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5388000011444092},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.5145000219345093},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.45159998536109924},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4514999985694885},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4408000111579895}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.685699999332428},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.678600013256073},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5952000021934509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5480999946594238},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5388000011444092},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.5145000219345093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4781999886035919},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4408000111579895},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3398999869823456},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33649998903274536},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3359000086784363},{"id":"https://openalex.org/C2776299755","wikidata":"https://www.wikidata.org/wiki/Q432449","display_name":"Carry (investment)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3075999915599823},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.28527","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28527","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.2605.28527","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28527","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision--language--action":[0],"(VLA)":[1],"policies":[2],"are":[3,66,160],"trained":[4],"to":[5,13,35,149],"imitate":[6],"actions;":[7],"their":[8,182],"loss":[9],"never":[10,185],"asks":[11],"them":[12],"estimate":[14],"reward,":[15],"progress,":[16,84],"or":[17,88],"future":[18],"success.":[19],"Their":[20],"frozen":[21,62,174],"representations":[22],"nevertheless":[23],"carry":[24],"such":[25],"information,":[26],"and":[27,33,46,73,76,94,163],"it":[28],"can":[29],"be":[30],"read":[31],"out":[32,92],"used":[34],"guide":[36],"action":[37,129],"choice":[38],"without":[39],"retraining":[40],"the":[41,99,131,169],"policy.":[42],"From":[43],"mixed":[44],"successful":[45],"failed":[47],"manipulation":[48],"trajectories":[49],"on":[50,61,83,140,156],"LIBERO-Goal,":[51],"we":[52,97],"recover":[53],"Monte-Carlo":[54],"outcome":[55],"targets":[56,65],"using":[57],"lightweight":[58],"linear":[59],"probes":[60,100,107],"features.":[63],"The":[64,158],"consistently":[67],"predictable":[68],"from":[69,80,144],"OpenVLA,":[70],"Pi0.5,":[71],"DINOv2,":[72],"CLIP":[74],"features,":[75],"substantially":[77],"less":[78],"so":[79],"baselines":[81],"built":[82],"time-to-go,":[85],"task":[86,93],"identity,":[87],"proprioception.":[89],"To":[90],"rule":[91],"temporal":[95],"shortcuts,":[96],"evaluate":[98],"under":[101,146],"same-task,":[102],"same-timestep":[103],"matched":[104],"comparisons:":[105],"Pi0.5":[106,128],"still":[108],"reach":[109],"roughly":[110],"92%":[111],"pairwise":[112],"ordering":[113],"accuracy,":[114],"while":[115],"label-shuffled":[116],"controls":[117],"stay":[118],"at":[119],"chance.":[120],"Used":[121],"as":[122],"a":[123,152],"test-time":[124],"selector":[125],"over":[126],"sampled":[127],"prefixes,":[130],"same":[132],"probe":[133],"turns":[134],"this":[135],"offline":[136],"finding":[137,171],"into":[138],"behavior:":[139],"push-plate,":[141],"success":[142,180],"rises":[143],"26.7%":[145],"greedy":[147],"decoding":[148],"44.3%,":[150],"with":[151],"second":[153],"positive":[154],"case":[155],"wine-rack.":[157],"gains":[159],"not":[161],"universal":[162],"require":[164],"additional":[165],"inference":[166],"compute,":[167],"but":[168],"underlying":[170],"is":[172],"clean:":[173],"VLAs":[175],"already":[176],"encode":[177],"information":[178],"about":[179],"that":[181],"imitation":[183],"objective":[184],"explicitly":[186],"demands.":[187]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-29T00:00:00"}