{"id":"https://openalex.org/W7128804563","doi":"https://doi.org/10.48550/arxiv.2602.12063","title":"VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model","display_name":"VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W7128804563","doi":"https://doi.org/10.48550/arxiv.2602.12063"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.12063","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125905955","display_name":"Yanjiang Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yanjiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125901422","display_name":"Tony Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Tony","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016584897","display_name":"Lucy Xiaoyang Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Lucy Xiaoyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125890562","display_name":"Jianyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jianyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059975116","display_name":"P. Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Percy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125976874","display_name":"Chelsea Finn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Finn, Chelsea","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19159033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9351000189781189,"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":0.9351000189781189,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.012400000356137753,"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":0.01119999960064888,"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/fidelity","display_name":"Fidelity","score":0.6001999974250793},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4864000082015991},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4560000002384186},{"id":"https://openalex.org/keywords/real-world-data","display_name":"Real world data","score":0.448199987411499},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.43639999628067017},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.36000001430511475},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.3427000045776367},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.3377000093460083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.73089998960495},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6001999974250793},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4864000082015991},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33219999074935913},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31949999928474426},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2980000078678131},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26080000400543213},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.12063","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.12063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.12063","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":"pmh:doi:10.48550/arxiv.2602.12063","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"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":{"The":[0],"goal":[1],"of":[2,12,70,108,144],"this":[3,138,180],"paper":[4],"is":[5,28],"to":[6,43,80,104,119,140],"improve":[7,105,141],"the":[8,25,53,106,109,126,142,162,171],"performance":[9,143],"and":[10,78,165],"reliability":[11],"vision-language-action":[13],"(VLA)":[14],"models":[15,51],"through":[16],"iterative":[17,96],"online":[18],"interaction.":[19],"Since":[20],"collecting":[21],"policy":[22,58,164],"rollouts":[23],"in":[24,88,115],"real":[26,134],"world":[27,50,110],"expensive,":[29],"we":[30,136],"investigate":[31],"whether":[32],"a":[33,94,133,145,155],"learned":[34],"simulator-specifically,":[35],"an":[36],"action-conditioned":[37],"video":[38],"generation":[39],"model-can":[40],"be":[41,117,177],"used":[42,118],"generate":[44,120],"additional":[45],"rollout":[46],"data.":[47],"Unfortunately,":[48],"existing":[49],"lack":[52,68],"physical":[54,73,86],"fidelity":[55,107],"necessary":[56],"for":[57,124],"improvement:":[59],"they":[60],"are":[61],"predominantly":[62],"trained":[63],"on":[64,132,149],"demonstration":[65],"datasets":[66],"that":[67,99],"coverage":[69],"many":[71],"different":[72],"interactions":[74],"(particularly":[75],"failure":[76],"cases)":[77],"struggle":[79],"accurately":[81],"model":[82,148],"small":[83],"yet":[84],"critical":[85],"details":[87],"contact-rich":[89],"object":[90],"manipulation.":[91],"We":[92,153],"propose":[93],"simple":[95],"improvement":[97,160,167],"algorithm":[98],"uses":[100],"real-world":[101],"roll-out":[102],"data":[103,123],"model,":[111],"which":[112],"can":[113,176],"then,":[114],"turn,":[116],"supplemental":[121],"synthetic":[122,173],"improving":[125],"VLA":[127,147],"model.":[128],"In":[129],"our":[130],"experiments":[131],"robot,":[135],"use":[137],"approach":[139],"state-of-the-art":[146],"multiple":[150],"downstream":[151],"tasks.":[152],"achieve":[154],"39.2%":[156],"absolute":[157],"success":[158],"rate":[159],"over":[161],"base":[163],"11.6%":[166],"from":[168],"training":[169],"with":[170],"generated":[172],"rollouts.":[174],"Videos":[175],"found":[178],"at":[179],"anonymous":[181],"website:":[182],"https://sites.google.com/view/vla-w":[183]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-02-14T00:00:00"}