{"id":"https://openalex.org/W7139021839","doi":"https://doi.org/10.48550/arxiv.2603.17850","title":"ProbeFlow: Training-Free Adaptive Flow Matching for Vision-Language-Action Models","display_name":"ProbeFlow: Training-Free Adaptive Flow Matching for Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-03-18","ids":{"openalex":"https://openalex.org/W7139021839","doi":"https://doi.org/10.48550/arxiv.2603.17850"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.17850","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.17850","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.2603.17850","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130081544","display_name":"Zhou Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130009080","display_name":"Jiaqi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130207371","display_name":"Yi Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052030441","display_name":"Qiongfeng Shi","orcid":"https://orcid.org/0000-0002-5979-1420"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Qiongfeng","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":0.27649998664855957,"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":0.27649998664855957,"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":0.1753000020980835,"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":0.11259999871253967,"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":0.6220999956130981},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5239999890327454},{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.4936999976634979},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4869000017642975},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4627000093460083},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.40139999985694885},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.38670000433921814},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.3727000057697296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245000004768372},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6220999956130981},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5239999890327454},{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3741999864578247},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3610999882221222},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3125},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.17850","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.17850","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.2603.17850","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.17850","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"Vision-Language-Action":[1],"(VLA)":[2],"models":[3],"equipped":[4],"with":[5],"Flow":[6],"Matching":[7],"(FM)":[8],"action":[9,46,100,156],"heads":[10],"achieve":[11],"state-of-the-art":[12],"performance":[13],"in":[14],"complex":[15],"robot":[16],"manipulation.":[17],"However,":[18],"the":[19,40,45,74,95,122,127,131,144],"multi-step":[20],"iterative":[21],"ODE":[22],"solving":[23],"required":[24],"by":[25,102,118],"FM":[26],"introduces":[27],"inference":[28,60],"latency":[29,117,158],"that":[30,152],"precludes":[31],"responsive":[32],"physical":[33,149],"control.":[34,67],"While":[35],"current":[36],"acceleration":[37],"efforts":[38],"optimize":[39],"Vision-Language":[41],"Model":[42],"(VLM)":[43],"backbone,":[44],"head":[47],"bottleneck":[48],"remains":[49],"overlooked.":[50],"To":[51],"address":[52],"this,":[53],"we":[54],"propose":[55],"ProbeFlow,":[56],"a":[57,135,164],"training-free":[58],"adaptive":[59],"framework":[61],"tai-":[62],"lored":[63],"for":[64,168],"continuous":[65,170],"robotic":[66],"By":[68],"evaluating":[69],"geometric":[70],"trajectory":[71],"complexity":[72],"via":[73],"cosine":[75],"similarity":[76],"between":[77],"initial":[78],"and":[79,113],"lookahead":[80],"velocity":[81],"vectors,":[82],"ProbeFlow":[83,153],"dynamically":[84],"sched-":[85],"ules":[86],"integration":[87],"steps":[88,106],"to":[89,111,138],"prune":[90],"redundant":[91],"network":[92],"evaluations.":[93],"On":[94,126],"MetaWorld":[96],"benchmark,":[97,130],"it":[98],"accelerates":[99],"decoding":[101,157],"14.8x":[103],"(reducing":[104],"average":[105],"from":[107],"N":[108],"=":[109],"50":[110],"2.6)":[112],"cuts":[114],"end-to-end":[115],"system":[116],"2.8x":[119],"without":[120],"compromising":[121],"manipulation":[123],"success":[124],"rate.":[125],"long-horizon":[128],"LIBERO":[129],"probe":[132],"automatically":[133],"allocates":[134],"denser":[136],"schedule":[137],"navigate":[139],"semantic":[140],"bottlenecks,":[141],"effectively":[142],"resolving":[143],"flow":[145],"solver":[146],"delay.":[147],"Real-world":[148],"deployments":[150],"confirm":[151],"successfully":[154],"mitigates":[155],"while":[159],"ensuring":[160],"execution":[161],"stability,":[162],"offering":[163],"highly":[165],"practical":[166],"solution":[167],"low-latency":[169],"generative":[171],"policies.":[172]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-20T00:00:00"}