{"id":"https://openalex.org/W7172336143","doi":"https://doi.org/10.48550/arxiv.2607.29613","title":"WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning","display_name":"WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning","publication_year":2026,"publication_date":"2026-07-31","ids":{"openalex":"https://openalex.org/W7172336143","doi":"https://doi.org/10.48550/arxiv.2607.29613"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.29613","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.29613","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2607.29613","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144279483","display_name":"Senyu Fei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei, Senyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144242599","display_name":"Xiaopeng Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Xiaopeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017974335","display_name":"Siyin Wang","orcid":"https://orcid.org/0009-0008-7992-2476"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Siyin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144253505","display_name":"Xianzhong Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Xianzhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144305269","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":"last","author":{"id":"https://openalex.org/A5144273569","display_name":"Xipeng Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Xipeng","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":0.37369999289512634,"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":0.37369999289512634,"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":0.328900009393692,"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":0.131400004029274,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7750999927520752},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5701000094413757},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5212000012397766},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4374000132083893},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4090000092983246},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.38359999656677246},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3671000003814697},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.33869999647140503}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7750999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6718999743461609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.65829998254776},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5701000094413757},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5212000012397766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.489300012588501},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.29613","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.29613","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.29613","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.29613","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.5386558175086975,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,77],"(RL)":[2],"post-training":[3],"of":[4,46],"Vision-Language-Action":[5],"(VLA)":[6],"models":[7],"has":[8],"shown":[9],"strong":[10,197],"promise":[11],"for":[12,76,105],"robotic":[13],"manipulation.":[14],"Among":[15],"RL":[16],"methods,":[17],"critic-based":[18],"approaches":[19],"rely":[20],"on":[21,28,120,176,204],"a":[22,38,86,121],"value":[23,107],"estimator":[24],"that":[25,135,183],"predominantly":[26],"operates":[27],"single-frame":[29,32],"observations":[30],"or":[31],"VLM":[33],"backbone":[34],"latents,":[35],"which":[36],"is":[37,139,163],"fundamental":[39],"mismatch":[40],"with":[41,62,165,195,213],"the":[42,57,82,96,101,114,136],"partially":[43],"observable":[44],"nature":[45],"robot":[47],"control.":[48],"A":[49],"naive":[50],"approach":[51],"to":[52,142],"incorporate":[53],"observation":[54],"history":[55],"into":[56,155],"critic":[58],"incurs":[59],"exponential":[60],"complexity":[61],"high-dimensional":[63],"visual":[64],"space,":[65],"and":[66,131,158,162,172,192,211],"still":[67],"fails":[68],"because":[69],"pure":[70],"scalar-return":[71],"regression":[72],"provides":[73],"insufficient":[74],"supervision":[75],"cross-temporal":[78],"dynamics.":[79],"We":[80,200],"identify":[81],"root":[83],"cause":[84],"as":[85],"state":[87,130],"approximation":[88],"problem:":[89],"without":[90],"an":[91],"explicit":[92],"world":[93],"modeling":[94],"objective,":[95],"critic's":[97,137],"representation":[98,138],"cannot":[99],"capture":[100,143],"temporal":[102,144],"structure":[103],"needed":[104],"accurate":[106],"estimation.":[108],"To":[109],"address":[110],"this,":[111],"we":[112],"propose":[113],"World":[115],"Critic":[116],"Model":[117],"(WCM),":[118],"built":[119],"lightweight":[122],"LeJEPA":[123],"architecture;":[124],"WCM":[125,152,184,203],"jointly":[126],"predicts":[127],"future":[128],"latent":[129],"estimates":[132],"values,":[133],"such":[134],"explicitly":[140],"trained":[141],"dynamics":[145],"rather":[146],"than":[147],"merely":[148],"regress":[149],"scalar":[150],"returns.":[151],"integrates":[153],"seamlessly":[154],"both":[156,190],"on-policy":[157],"off-policy":[159,214],"training":[160],"pipelines":[161],"compatible":[164],"state-of-the-art":[166,187],"VLA":[167],"backbones":[168],"including":[169],"Pi0,":[170],"Pi0.5,":[171],"OpenVLA-OFT.":[173],"Extensive":[174],"experiments":[175],"149":[177],"tasks":[178,208],"across":[179,219],"four":[180],"benchmarks":[181],"demonstrate":[182],"consistently":[185],"achieves":[186],"performance":[188],"in":[189],"in-distribution":[191],"out-of-distribution":[193],"settings,":[194],"particularly":[196],"generalization":[198],"gains.":[199],"further":[201],"validate":[202],"seven":[205],"real-world":[206],"manipulation":[207],"using":[209],"OpenVLA-OFT":[210],"Pi0.5":[212],"RL,":[215],"confirming":[216],"stable":[217],"deployment":[218],"diverse":[220],"settings.":[221]},"counts_by_year":[],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2026-08-04T00:00:00"}