{"id":"https://openalex.org/W7163585994","doi":"https://doi.org/10.48550/arxiv.2606.04968","title":"Potential-Guided Flow Matching for Vision-Language-Action Policy Improvement","display_name":"Potential-Guided Flow Matching for Vision-Language-Action Policy Improvement","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7163585994","doi":"https://doi.org/10.48550/arxiv.2606.04968"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.04968","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04968","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.2606.04968","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100313252","display_name":"Yunpeng Mei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mei, Yunpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053699035","display_name":"Jiakai He","orcid":"https://orcid.org/0000-0003-0216-2516"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Jiakai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052814625","display_name":"Hongjie Cao","orcid":"https://orcid.org/0000-0001-5681-0916"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Hongjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137905772","display_name":"Chenyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chenyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137863283","display_name":"Xiaowen Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xiaowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137840927","display_name":"Yihan Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137836962","display_name":"Jiamin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiamin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120003409","display_name":"Chenbo Xin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin, Chenbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137831568","display_name":"Peng Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137809741","display_name":"Yuxuan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137835185","display_name":"Yijie Wang","orcid":"https://orcid.org/0000-0002-2023-6972"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137871599","display_name":"Xinhu Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Xinhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137901574","display_name":"Gao Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137822745","display_name":"Jie Chen (5892)","orcid":"https://orcid.org/0009-0006-2222-3020"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137910621","display_name":"Gang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Gang","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":0.5479999780654907,"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":0.5479999780654907,"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":0.19509999454021454,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.05700000002980232,"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/estimator","display_name":"Estimator","score":0.6626999974250793},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5174999833106995},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4887000024318695},{"id":"https://openalex.org/keywords/a-weighting","display_name":"A-weighting","score":0.4487000107765198},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43880000710487366},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4097000062465668},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.3806000053882599},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.3749000132083893},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.36890000104904175}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6626999974250793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6132000088691711},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.4487000107765198},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40540000796318054},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.04968","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04968","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.2606.04968","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04968","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":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4127380847930908}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"vision-language-action":[1],"(VLA)":[2],"policies":[3],"are":[4],"increasingly":[5],"trained":[6],"as":[7],"conditional":[8,148],"generative":[9],"models":[10],"over":[11,172],"action":[12,63,133],"chunks.":[13],"Yet":[14],"deployment":[15],"produces":[16],"mixed-quality":[17],"experience-successful":[18],"demonstrations,":[19],"partial":[20],"completions,":[21],"recoverable":[22],"mistakes,":[23],"and":[24,44,74,92,115,165,186,205],"failures-that":[25],"is":[26,88],"difficult":[27],"to":[28,109,132],"use":[29],"with":[30,65,122,154],"standard":[31],"imitation.":[32],"Full":[33],"behavior":[34],"cloning":[35],"(BC)":[36],"imitates":[37],"failures,":[38],"filtered":[39],"BC":[40],"discards":[41],"useful":[42],"sub-trajectories,":[43],"offline":[45],"reinforcement":[46],"learning":[47],"adds":[48],"a":[49,55,66,143,155],"large":[50],"critic.":[51,84],"We":[52,119,140],"introduce":[53],"ForesightFlow,":[54],"self-guided":[56,206],"flow-matching":[57],"policy":[58,90],"that":[59,89,194],"augments":[60],"each":[61],"generated":[62],"chunk":[64],"learned":[67],"success-potential":[68],"trajectory.":[69],"The":[70,85],"same":[71,107],"flow":[72,125,149],"proposes":[73],"scores":[75],"candidate":[76],"actions,":[77,103],"enabling":[78],"best-of-$K$":[79],"inference":[80],"without":[81],"an":[82],"external":[83],"key":[86],"issue":[87],"improvement":[91],"value":[93,197],"calibration":[94],"require":[95],"different":[96],"supervision:":[97],"advantage":[98,129,152],"weighting":[99],"should":[100],"emphasize":[101],"high-quality":[102],"but":[104],"applying":[105,127],"the":[106,176,199],"weights":[108,130],"potential":[110,137],"coordinates":[111],"suppresses":[112],"failure":[113],"gradients":[114],"creates":[116],"overconfident":[117],"scores.":[118],"address":[120],"this":[121],"decoupled":[123],"advantage-weighted":[124],"matching,":[126,150],"exponentiated":[128],"only":[131],"velocities":[134,138],"while":[135],"training":[136,188],"uniformly.":[139],"further":[141],"derive":[142],"one-step":[144,200],"boundary":[145],"estimator":[146,201],"for":[147],"allowing":[151],"computation":[153],"single":[156],"stop-gradient":[157],"forward":[158],"pass.":[159],"Across":[160],"five":[161,166],"BEHAVIOR-1K":[162],"simulation":[163,181],"tasks":[164],"real-world":[167,184],"bimanual":[168],"tasks,":[169],"ForesightFlow":[170],"improves":[171,183,208],"imitation":[173],"baselines,":[174],"matches":[175],"strongest":[177],"separate-critic":[178],"baseline":[179],"in":[180],"success,":[182,185],"reduces":[187],"compute":[189],"by":[190],"$38\\%$.":[191],"Ablations":[192],"show":[193],"decoupling":[195],"prevents":[196],"hallucination,":[198],"preserves":[202],"candidate-ranking":[203],"fidelity,":[204],"sampling":[207],"long-horizon":[209],"execution.":[210]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-05T00:00:00"}