{"id":"https://openalex.org/W7161546138","doi":"https://doi.org/10.48550/arxiv.2605.15492","title":"FLASH: Efficient Visuomotor Policy via Sparse Sampling","display_name":"FLASH: Efficient Visuomotor Policy via Sparse Sampling","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161546138","doi":"https://doi.org/10.48550/arxiv.2605.15492"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.15492","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15492","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.2605.15492","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136367865","display_name":"Jiaqi Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Jiaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004534196","display_name":"Jindou Jia","orcid":"https://orcid.org/0000-0002-1866-6180"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Jindou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136378766","display_name":"Yuxuan Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136403458","display_name":"Gen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Gen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136364084","display_name":"Xiangyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xiangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136430041","display_name":"Tuo An","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"An, Tuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027489502","display_name":"Kuangji Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuo, Kuangji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136394075","display_name":"Jianfei Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jianfei","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/T10653","display_name":"Robot Manipulation and Learning","score":0.29269999265670776,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.29269999265670776,"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/T10982","display_name":"Motor Control and Adaptation","score":0.16539999842643738,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.13609999418258667,"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/inference","display_name":"Inference","score":0.5521000027656555},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.5041000247001648},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.47920000553131104},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4397999942302704},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4339999854564667},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4165000021457672},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4138000011444092},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.40720000863075256},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.40610000491142273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6074000000953674},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5521000027656555},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44760000705718994},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4397999942302704},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.40720000863075256},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.38760000467300415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3797000050544739},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.337799996137619},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32280001044273376},{"id":"https://openalex.org/C111458787","wikidata":"https://www.wikidata.org/wiki/Q215405","display_name":"Legendre polynomials","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3075999915599823},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2727000117301941},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.15492","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15492","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.2605.15492","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15492","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":0.4016791582107544}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"models":[1],"such":[2],"as":[3],"diffusion":[4,153],"and":[5,98,125,155,171],"flow":[6,40,82,160],"matching":[7,83,161],"have":[8],"become":[9],"dominant":[10],"paradigms":[11],"for":[12],"visuomotor":[13],"policy":[14,36],"learning,":[15],"yet":[16],"their":[17],"reliance":[18],"on":[19,122],"iterative":[20],"denoising":[21],"incurs":[22],"high":[23],"inference":[24,67,144],"latency":[25],"incompatible":[26],"with":[27,48],"real-time":[28],"robotic":[29],"control.":[30],"We":[31],"present":[32],"Fast":[33],"Legendre-polynomial":[34],"Action":[35],"via":[37],"Sparse":[38],"History-anchored":[39],"(FLASH":[41],"Policy),":[42],"which":[43],"replaces":[44],"discrete":[45],"action-chunk":[46],"generation":[47],"continuous":[49],"Legendre":[50],"polynomial":[51,87,105],"trajectory":[52],"representation.":[53],"Specifically,":[54],"by":[55],"fitting":[56],"expert":[57],"demonstrations":[58],"under":[59],"sparse":[60],"temporal":[61],"sampling,":[62],"FLASH":[63,79,132],"enables":[64],"a":[65,70,142],"single":[66],"to":[68,113,149,164,173,181],"cover":[69],"significantly":[71],"extended":[72],"action":[73],"horizon.":[74],"To":[75],"further":[76],"accelerate":[77],"generation,":[78],"initiates":[80],"the":[81,95,114],"process":[84],"from":[85],"history":[86],"coefficients":[88],"rather":[89],"than":[90,152,158,169],"uninformative":[91],"Gaussian":[92],"noise,":[93],"shortening":[94],"transport":[96],"distance":[97],"enabling":[99],"accurate":[100],"single-step":[101],"inference.":[102],"Moreover,":[103],"analytic":[104],"differentiation":[106],"directly":[107],"provides":[108],"desired":[109],"velocity":[110],"feed-forward":[111],"signals":[112],"torque":[115],"controller":[116,177],"without":[117],"numerical":[118],"approximation.":[119],"Extensive":[120],"experiments":[121],"five":[123],"simulated":[124],"two":[126],"real-world":[127],"manipulation":[128],"tasks":[129],"demonstrate":[130],"that":[131],"achieves":[133],"state-of-the-art":[134],"success":[135],"rates":[136],"($\\ge":[137],"92\\%$":[138],"across":[139],"all":[140],"tasks),":[141],"per-episode":[143],"time":[145],"of":[146],"$31.40\\,ms$":[147],"(up":[148],"$175\\times$":[150],"faster":[151,157,166],"policies":[154],"$18\\times$":[156],"prior":[159],"policies),":[162],"up":[163],"$4\\times$":[165],"training":[167],"convergence":[168],"ACT,":[170],"$5\\times$":[172],"$7\\times$":[174],"reduction":[175],"in":[176],"tracking":[178],"error":[179],"compared":[180],"discrete-action":[182],"baselines.":[183]},"counts_by_year":[],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2026-05-19T00:00:00"}