{"id":"https://openalex.org/W7140145832","doi":"https://doi.org/10.1109/tit.2026.3676355","title":"Local Flow Matching Generative Models","display_name":"Local Flow Matching Generative Models","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7140145832","doi":"https://doi.org/10.1109/tit.2026.3676355"},"language":null,"primary_location":{"id":"doi:10.1109/tit.2026.3676355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2026.3676355","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chen Xu","orcid":"https://orcid.org/0000-0001-6623-7084"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Xu","raw_affiliation_strings":["H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6623-7084","affiliations":[{"raw_affiliation_string":"H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101514536","display_name":"Xiuyuan Cheng","orcid":"https://orcid.org/0000-0002-1034-6019"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiuyuan Cheng","raw_affiliation_strings":["Department of Mathematics, Duke University, Durham, NC, USA"],"raw_orcid":"https://orcid.org/0000-0002-1034-6019","affiliations":[{"raw_affiliation_string":"Department of Mathematics, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yao Xie","orcid":"https://orcid.org/0000-0001-6777-2951"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yao Xie","raw_affiliation_strings":["H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6777-2951","affiliations":[{"raw_affiliation_string":"H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42197987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"72","issue":"5","first_page":"3339","last_page":"3358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.05779999867081642,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.05779999867081642,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.05350000038743019,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.05119999870657921,"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/generative-model","display_name":"Generative model","score":0.5690000057220459},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5663999915122986},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.5378999710083008},{"id":"https://openalex.org/keywords/invertible-matrix","display_name":"Invertible matrix","score":0.4318000078201294},{"id":"https://openalex.org/keywords/contraction","display_name":"Contraction (grammar)","score":0.4293000102043152},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3772999942302704},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.37610000371932983},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.375}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5776000022888184},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5690000057220459},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5663999915122986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5616999864578247},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5378999710083008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43959999084472656},{"id":"https://openalex.org/C96442724","wikidata":"https://www.wikidata.org/wiki/Q242188","display_name":"Invertible matrix","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C163415756","wikidata":"https://www.wikidata.org/wiki/Q126473","display_name":"Contraction (grammar)","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39430001378059387},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.37610000371932983},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.375},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C167879884","wikidata":"https://www.wikidata.org/wiki/Q727568","display_name":"Balanced flow","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.3111000061035156},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tit.2026.3676355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2026.3676355","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Theory","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1600291198","display_name":"Bridging Statistical Hypothesis Tests and Deep Learning for Reliability and Computational Efficiency","funder_award_id":"2134037","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Flow":[0,45],"Matching":[1,46],"(FM)":[2],"is":[3,154],"a":[4,9,35,40,51,58,113],"simulation-free":[5],"method":[6],"for":[7,117],"learning":[8],"continuous,":[10],"invertible":[11],"flow":[12,120],"that":[13,173],"interpolates":[14,93],"between":[15,132],"two":[16,74],"distributions,":[17,97,138],"and":[18,135,160,187,190],"in":[19,66,87,122,127],"particular":[20],"generates":[21],"data":[22,94,137],"from":[23],"noise.":[24],"Inspired":[25],"by":[26,79],"the":[27,31,63,67,73,80,88,118,125,130,133,140,144,149],"variational":[28,106],"nature":[29],"of":[30,53,124,129,143,152,185,194],"diffusion":[32,59,145],"process":[33,60],"as":[34],"gradient":[36],"flow,":[37],"we":[38],"introduce":[39],"stepwise":[41,150],"FM":[42,54,181],"model,":[43,91],"Local":[44],"(LFM),":[47],"which":[48,92],"sequentially":[49],"learns":[50],"sequence":[52],"submodels,":[55],"each":[56,71],"matching":[57,90],"up":[61],"to":[62,76,95,111,157,167,180],"time-step":[64],"size":[65],"data-to-noise":[68],"direction.":[69],"In":[70,147],"step,":[72],"distributions":[75],"be":[77,165],"interpolated":[78],"sub-flow":[81],"model":[82,121,126,158],"are":[83],"closer":[84],"than":[85],"those":[86],"full-flow":[89],"noise":[96],"enabling":[98],"smaller":[99],"models":[100],"with":[101],"more":[102],"efficient":[103],"training.":[104],"This":[105],"perspective":[107],"also":[108],"allows":[109],"us":[110],"prove":[112],"theoretical":[114],"generation":[115,184,193],"guarantee":[116],"proposed":[119],"terms":[123,128],"\u03c72-divergence":[131],"generated":[134],"true":[136],"leveraging":[139],"contraction":[141],"property":[142],"process.":[146],"practice,":[148],"structure":[151],"LFM":[153,174],"naturally":[155],"amenable":[156],"distillation,":[159],"various":[161],"distillation":[162],"techniques":[163],"can":[164],"applied":[166],"accelerate":[168],"generation.":[169],"We":[170],"empirically":[171],"demonstrate":[172],"achieves":[175],"competitive":[176],"generative":[177],"performance":[178],"compared":[179],"on":[182,191],"unconditional":[183],"tabular":[186],"image":[188],"datasets,":[189],"conditional":[192],"robotic":[195],"manipulation":[196],"policies.":[197]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2026-03-24T00:00:00"}