{"id":"https://openalex.org/W7139920986","doi":"https://doi.org/10.48550/arxiv.2603.19199","title":"FASTER: Rethinking Real-Time Flow VLAs","display_name":"FASTER: Rethinking Real-Time Flow VLAs","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7139920986","doi":"https://doi.org/10.48550/arxiv.2603.19199"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.19199","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19199","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.2603.19199","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130219877","display_name":"Yuxiang Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Yuxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130213896","display_name":"Zhe Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130249910","display_name":"Xianzhe Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Xianzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130234481","display_name":"Zhenya Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhenya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130243643","display_name":"Jinghua Hou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Jinghua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130249281","display_name":"Junyi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Junyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130224011","display_name":"Kaixin Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Kaixin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130249748","display_name":"Hengshuang Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Hengshuang","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/T10812","display_name":"Human Pose and Action Recognition","score":0.243599995970726,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.243599995970726,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10090000182390213,"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":0.07750000059604645,"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/bottleneck","display_name":"Bottleneck","score":0.6539999842643738},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5059000253677368},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.4731000065803528},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.39649999141693115},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.38760000467300415},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.38339999318122864},{"id":"https://openalex.org/keywords/guard","display_name":"Guard (computer science)","score":0.35659998655319214},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.3528999984264374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6776000261306763},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6539999842643738},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5059000253677368},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.4731000065803528},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3700999915599823},{"id":"https://openalex.org/C141141315","wikidata":"https://www.wikidata.org/wiki/Q2379942","display_name":"Guard (computer science)","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.34049999713897705},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2824999988079071},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.27309998869895935},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2709999978542328},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.26429998874664307},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.19199","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19199","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.2603.19199","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19199","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-time":[0],"execution":[1,73],"is":[2],"crucial":[3],"for":[4,122,203],"deploying":[5],"Vision-Language-Action":[6],"(VLA)":[7],"models":[8],"in":[9,26,37,87,110,149],"the":[10,23,33,48,65,72,79,95,108,140,143,159,173],"physical":[11],"world.":[12],"Existing":[13],"asynchronous":[14],"inference":[15],"methods":[16],"primarily":[17],"optimize":[18],"trajectory":[19],"smoothness,":[20],"but":[21],"neglect":[22],"critical":[24],"latency":[25,176],"reacting":[27],"to":[28,67,97],"environmental":[29],"changes.":[30],"By":[31,126],"rethinking":[32],"notion":[34],"of":[35,47,82,142,161,209],"reaction":[36,51,56,111,145,175],"action":[38],"chunking":[39],"policies,":[40,205],"this":[41,115],"paper":[42],"presents":[43],"a":[44,59,84,128,154,166,189],"systematic":[45],"analysis":[46],"factors":[49],"governing":[50],"time.":[52],"We":[53],"show":[54],"that":[55,78,196],"time":[57],"follows":[58],"uniform":[60],"distribution":[61],"determined":[62],"jointly":[63],"by":[64,146],"Time":[66],"First":[68],"Action":[69,120],"(TTFA)":[70],"and":[71,93,151,211],"horizon.":[74],"Moreover,":[75],"we":[76,117],"reveal":[77],"standard":[80],"practice":[81],"applying":[83],"constant":[85],"schedule":[86],"flow-based":[88],"VLAs":[89],"can":[90,105],"be":[91],"inefficient":[92],"forces":[94],"system":[96],"complete":[98],"all":[99],"sampling":[100],"steps":[101],"before":[102],"any":[103],"movement":[104],"start,":[106],"forming":[107],"bottleneck":[109],"latency.":[112],"To":[113],"overcome":[114],"issue,":[116],"propose":[118],"Fast":[119],"Sampling":[121],"ImmediaTE":[123],"Reaction":[124],"(FASTER).":[125],"introducing":[127],"Horizon-Aware":[129],"Schedule,":[130],"FASTER":[131,170,197],"adaptively":[132],"prioritizes":[133],"near-term":[134],"actions":[135],"during":[136],"flow":[137],"sampling,":[138],"compressing":[139],"denoising":[141],"immediate":[144],"tenfold":[147],"(e.g.,":[148],"$\u03c0_{0.5}$":[150],"X-VLA)":[152],"into":[153],"single":[155],"step,":[156],"while":[157],"preserving":[158],"quality":[160],"long-horizon":[162],"trajectory.":[163],"Coupled":[164],"with":[165],"streaming":[167],"client-server":[168],"pipeline,":[169],"substantially":[171,199],"reduces":[172],"effective":[174],"on":[177,183],"real":[178],"robots,":[179],"especially":[180],"when":[181],"deployed":[182],"consumer-grade":[184],"GPUs.":[185],"Real-world":[186],"experiments,":[187],"including":[188],"highly":[190],"dynamic":[191],"table":[192],"tennis":[193],"task,":[194],"prove":[195],"unlocks":[198],"improved":[200],"real-time":[201],"responsiveness":[202],"generalist":[204],"enabling":[206],"rapid":[207],"generation":[208],"accurate":[210],"smooth":[212],"trajectories.":[213]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-21T00:00:00"}