{"id":"https://openalex.org/W7131639211","doi":"https://doi.org/10.48550/arxiv.2602.21633","title":"Self-Correcting VLA: Online Action Refinement via Sparse World Imagination","display_name":"Self-Correcting VLA: Online Action Refinement via Sparse World Imagination","publication_year":2026,"publication_date":"2026-02-25","ids":{"openalex":"https://openalex.org/W7131639211","doi":"https://doi.org/10.48550/arxiv.2602.21633"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.21633","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.21633","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":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.2602.21633","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126902686","display_name":"Chenyv Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Chenyv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126887618","display_name":"Wentao Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Wentao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126918989","display_name":"Lei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126929891","display_name":"Fengling Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Fengling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126934870","display_name":"Jingjing Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jingjing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056347218","display_name":"Guoli Yang","orcid":"https://orcid.org/0000-0002-1780-8757"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Guoli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126931701","display_name":"Heng Tao Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Heng Tao","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.635200023651123,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.635200023651123,"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":0.1420000046491623,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03610000014305115,"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/action","display_name":"Action (physics)","score":0.6229000091552734},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5806000232696533},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5717999935150146},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5429999828338623},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48649999499320984},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.47839999198913574},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.43639999628067017},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3790000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279999852180481},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6229000091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.593500018119812},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5806000232696533},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5717999935150146},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5429999828338623},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48649999499320984},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.47839999198913574},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4253000020980835},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39800000190734863},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3296000063419342},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.30889999866485596},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.28450000286102295},{"id":"https://openalex.org/C207451115","wikidata":"https://www.wikidata.org/wiki/Q12898216","display_name":"Throwing","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.21633","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.21633","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":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.2602.21633","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.21633","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":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":{"Standard":[0],"vision-language-action":[1],"(VLA)":[2],"models":[3,42],"rely":[4,60],"on":[5,28,61,136,143],"fitting":[6],"statistical":[7],"data":[8],"priors,":[9],"limiting":[10],"their":[11],"robust":[12],"understanding":[13],"of":[14],"underlying":[15],"physical":[16,21,117],"dynamics.":[17],"Reinforcement":[18],"learning":[19],"enhances":[20],"grounding":[22],"through":[23,87],"exploration":[24],"yet":[25],"typically":[26],"relies":[27],"external":[29],"reward":[30],"signals":[31],"that":[32,49,155],"remain":[33],"isolated":[34],"from":[35,148],"the":[36,112,122,137,161,176],"agent's":[37],"internal":[38],"states.":[39,141],"World":[40],"action":[41,85,124],"have":[43],"emerged":[44],"as":[45],"a":[46,170,180],"promising":[47],"paradigm":[48],"integrates":[50],"imagination":[51,95],"and":[52,106,151,169],"control":[53],"to":[54,101,114,127],"enable":[55],"predictive":[56,99],"planning.":[57],"However,":[58],"they":[59],"implicit":[62],"context":[63],"modeling,":[64],"lacking":[65],"explicit":[66],"mechanisms":[67],"for":[68],"self-improvement.":[69],"To":[70],"solve":[71],"these":[72],"problems,":[73],"we":[74,120],"propose":[75],"Self-Correcting":[76],"VLA":[77],"(SC-VLA),":[78],"which":[79],"achieve":[80,157],"self-improvement":[81],"by":[82,96],"intrinsically":[83],"guiding":[84],"refinement":[86,125],"sparse":[88,93,139],"imagination.":[89],"We":[90],"first":[91],"design":[92],"world":[94],"integrating":[97],"auxiliary":[98],"heads":[100],"forecast":[102],"current":[103],"task":[104,163],"progress":[105],"future":[107,140],"trajectory":[108,133],"trends,":[109],"thereby":[110],"constraining":[111],"policy":[113],"encode":[115],"short-term":[116],"evolution.":[118],"Then":[119],"introduce":[121],"online":[123],"module":[126],"reshape":[128],"progress-dependent":[129],"dense":[130],"rewards,":[131],"adjusting":[132],"orientation":[134],"based":[135],"predicted":[138],"Evaluations":[142],"challenging":[144],"robot":[145],"manipulation":[146],"tasks":[147],"simulation":[149],"benchmarks":[150],"real-world":[152,184],"settings":[153],"demonstrate":[154],"SC-VLA":[156],"state-of-the-art":[158],"performance,":[159],"yielding":[160],"highest":[162],"throughput":[164],"with":[165],"16%":[166],"fewer":[167],"steps":[168],"9%":[171],"higher":[172],"success":[173],"rate":[174],"than":[175],"best-performing":[177],"baselines,":[178],"alongside":[179],"14%":[181],"gain":[182],"in":[183],"experiments.":[185],"Code":[186],"is":[187],"available":[188],"at":[189],"https://github.com/Kisaragi0/SC-VLA.":[190]},"counts_by_year":[],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2026-02-27T00:00:00"}