{"id":"https://openalex.org/W7155036684","doi":"https://doi.org/10.48550/arxiv.2604.17800","title":"ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning","display_name":"ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7155036684","doi":"https://doi.org/10.48550/arxiv.2604.17800"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.17800","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17800","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.2604.17800","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134114693","display_name":"Tuan Van Vo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Van Vo, Tuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101669230","display_name":"Tan Nguyen","orcid":"https://orcid.org/0000-0003-2575-6296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Tan Q.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134188775","display_name":"Khang Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Khang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134170981","display_name":"Nhat Xuan Tran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tran, Nhat Xuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134157896","display_name":"Duy H. M. Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Duy H. M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128686351","display_name":"An T. Le","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le, An T.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043775193","display_name":"Ngo Anh Vien","orcid":"https://orcid.org/0000-0001-9646-267X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vien, Ngo Anh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134124261","display_name":"Minh Nhat Vu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vu, Minh Nhat","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":0.9714000225067139,"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":0.9714000225067139,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.005200000014156103,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.002300000051036477,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7342000007629395},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.609499990940094},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5591999888420105},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5008999705314636},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45350000262260437},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.41620001196861267},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3935999870300293}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7342000007629395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6438000202178955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6312999725341797},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.609499990940094},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4684000015258789},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39660000801086426},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.31200000643730164},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.27649998664855957}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.17800","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17800","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.2604.17800","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.17800","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":[{"display_name":"Quality Education","score":0.6849983930587769,"id":"https://metadata.un.org/sdg/4"}],"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":[2,89,158],"have":[3],"gained":[4],"much":[5],"attention":[6,121],"from":[7],"the":[8,36,103,110,126,139,169,200,204,206],"research":[9],"community":[10],"thanks":[11],"to":[12,90,92,124,143],"their":[13,27,95],"strength":[14],"in":[15,48,196],"translating":[16],"multimodal":[17,64,171],"observations":[18],"with":[19,70,78,102,106,185],"linguistic":[20,131],"instructions":[21],"into":[22],"desired":[23],"robotic":[24,76],"actions.":[25,96,149],"Despite":[26],"advancements,":[28],"VLAs":[29,69,101],"often":[30],"overlook":[31],"explicit":[32],"reasoning":[33,79,116],"and":[34,50,114,133,148,165,173,188,209],"learn":[35,91],"functional":[37],"input-action":[38],"mappings,":[39],"omitting":[40],"crucial":[41],"logical":[42],"steps,":[43],"which":[44],"are":[45],"especially":[46],"pronounced":[47],"interpretability":[49],"generalization":[51,112],"for":[52],"complex,":[53],"long-horizon":[54],"manipulation":[55,181],"tasks.":[56],"In":[57],"this":[58,151],"work,":[59],"we":[60,98,154],"propose":[61],"ReFineVLA,":[62,107,137],"a":[63,160,177],"reasoning-aware":[65],"framework":[66],"that":[67,156],"fine-tunes":[68],"teacher-guided":[71],"reasons.":[72],"We":[73,118],"first":[74],"augment":[75],"datasets":[77,105],"rationales":[80],"generated":[81],"by":[82],"an":[83],"expert":[84],"teacher":[85],"model,":[86],"guiding":[87],"VLA":[88],"reason":[93],"about":[94],"Then,":[97],"fine-tune":[99],"pre-trained":[100],"reasoning-enriched":[104],"while":[108],"maintaining":[109],"underlying":[111],"abilities":[113],"boosting":[115],"capabilities.":[117],"also":[119],"conduct":[120],"map":[122],"visualization":[123],"analyze":[125],"alignment":[127],"among":[128],"visual":[129],"observation,":[130],"prompts,":[132],"to-be-executed":[134],"actions":[135],"of":[136,179],"reflecting":[138],"model":[140],"is":[141],"ability":[142],"focus":[144],"on":[145,183,203],"relevant":[146],"tasks":[147],"Through":[150],"additional":[152],"step,":[153],"explore":[155],"ReFineVLA-trained":[157],"exhibit":[159],"meaningful":[161],"agreement":[162],"between":[163],"vision-language":[164],"action":[166],"domains,":[167],"highlighting":[168],"enhanced":[170],"understanding":[172],"generalization.":[174],"Evaluated":[175],"across":[176],"suite":[178],"simulated":[180],"benchmarks":[182],"SimplerEnv":[184],"both":[186,205],"WidowX":[187,207],"Google":[189,210],"Robot":[190,211],"tasks,":[191],"ReFineVLA":[192],"achieves":[193],"state-of-the-art":[194],"performance,":[195],"success":[197],"rate":[198],"over":[199],"second-best":[201],"method":[202],"benchmark":[208],"Tasks.":[212]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-22T00:00:00"}