{"id":"https://openalex.org/W7138147947","doi":"https://doi.org/10.48550/arxiv.2603.15279","title":"Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling","display_name":"Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7138147947","doi":"https://doi.org/10.48550/arxiv.2603.15279"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.15279","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15279","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.15279","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102900404","display_name":"Aram Davtyan","orcid":"https://orcid.org/0000-0001-5156-3741"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Davtyan, Aram","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057849336","display_name":"Leello Tadesse Dadi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dadi, Leello Tadesse","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129670456","display_name":"Volkan Cevher","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cevher, Volkan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126608799","display_name":"Paolo Favaro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Favaro, Paolo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102900404"],"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8986999988555908,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8986999988555908,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.030400000512599945,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.017100000753998756,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.652899980545044},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5907999873161316},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5519999861717224},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5414000153541565},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5406000018119812},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.48890000581741333},{"id":"https://openalex.org/keywords/coupling","display_name":"Coupling (piping)","score":0.41200000047683716},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.39649999141693115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7120000123977661},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.652899980545044},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5907999873161316},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5519999861717224},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5414000153541565},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5406000018119812},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4542999863624573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41600000858306885},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39989998936653137},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3693999946117401},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.3433000147342682},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.32120001316070557},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.2867000102996826},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2809999883174896},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27570000290870667},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.15279","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15279","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.15279","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15279","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"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":{"Conditional":[0],"Flow":[1],"Matching":[2],"(CFM),":[3],"a":[4,93],"simulation-free":[5],"method":[6,95],"for":[7,19],"training":[8,58,112],"continuous":[9],"normalizing":[10],"flows,":[11],"provides":[12],"an":[13],"efficient":[14],"alternative":[15],"to":[16,52,60,73,96],"diffusion":[17],"models":[18],"key":[20],"tasks":[21,34],"like":[22],"image":[23],"and":[24,64,105,132],"video":[25],"generation.":[26],"The":[27],"performance":[28],"of":[29,100],"CFM":[30],"in":[31,56,119,136],"solving":[32],"these":[33,107],"depends":[35],"on":[36,79],"the":[37,98,120],"way":[38],"data":[39],"is":[40,71],"coupled":[41],"with":[42],"noise.":[43],"A":[44],"recent":[45],"approach":[46,115],"uses":[47],"minibatch":[48,101],"optimal":[49],"transport":[50],"(OT)":[51],"reassign":[53],"noise-data":[54],"pairs":[55],"each":[57],"step":[59],"streamline":[61],"sampling":[62,121],"trajectories":[63],"thus":[65],"accelerate":[66],"inference.":[67],"However,":[68],"its":[69,77],"optimization":[70],"restricted":[72],"individual":[74],"minibatches,":[75],"limiting":[76],"effectiveness":[78],"large":[80],"datasets.":[81,126],"To":[82],"address":[83],"this":[84],"shortcoming,":[85],"we":[86],"introduce":[87],"LOOM-CFM":[88,127],"(Looking":[89],"Out":[90],"Of":[91],"Minibatch-CFM),":[92],"novel":[94],"extend":[97],"scope":[99],"OT":[102],"by":[103],"preserving":[104],"optimizing":[106],"assignments":[108],"across":[109,124],"minibatches":[110],"over":[111],"time.":[113],"Our":[114],"demonstrates":[116],"consistent":[117],"improvements":[118],"speed-quality":[122],"trade-off":[123],"multiple":[125],"also":[128],"enhances":[129],"distillation":[130],"initialization":[131],"supports":[133],"high-resolution":[134],"synthesis":[135],"latent":[137],"space":[138],"training.":[139]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}