{"id":"https://openalex.org/W7160652975","doi":"https://doi.org/10.48550/arxiv.2605.05975","title":"Physical Fidelity Reconstruction via Improved Consistency-Distilled Flow Matching for Dynamical Systems","display_name":"Physical Fidelity Reconstruction via Improved Consistency-Distilled Flow Matching for Dynamical Systems","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160652975","doi":"https://doi.org/10.48550/arxiv.2605.05975"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.05975","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05975","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.05975","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135712148","display_name":"Sicheng Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Sicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135683216","display_name":"Tianyue Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Tianyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135709803","display_name":"Xiuzhe Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xiuzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135692046","display_name":"Xiao Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Xiao","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.49000000953674316,"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":0.49000000953674316,"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":0.36910000443458557,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.01940000057220459,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5972999930381775},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5006999969482422},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.49549999833106995},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.48190000653266907},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4724000096321106},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4406000077724457},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.396699994802475},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3898000121116638},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.38940000534057617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6485999822616577},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5972999930381775},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.48190000653266907},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4406000077724457},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.400299996137619},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.396699994802475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39469999074935913},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.38940000534057617},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38350000977516174},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3012000024318695},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.05975","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05975","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.05975","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05975","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"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":{"Reconstructing":[0],"high-fidelity":[1,45,96],"flow":[2,60,97],"fields":[3],"from":[4,85,188],"low-fidelity":[5],"observations":[6,75],"is":[7],"a":[8,44,53,70,86,128,164,182,209],"central":[9],"problem":[10],"in":[11,192],"scientific":[12,59,216],"machine":[13],"learning,":[14],"yet":[15],"recent":[16],"diffusion":[17],"and":[18,38,121,162,231],"flow-matching":[19,46,67,170],"models":[20,218,222],"typically":[21],"rely":[22],"on":[23,112,152],"iterative":[24],"sampling,":[25],"making":[26],"them":[27],"costly":[28],"for":[29,57,212],"latency-sensitive":[30],"workflows":[31],"such":[32],"as":[33,127,159],"ensemble":[34],"forecasting,":[35],"real-time":[36],"visualization,":[37],"simulation-in-the-loop":[39],"inference.":[40],"We":[41,107],"study":[42],"whether":[43],"generative":[47,83,217],"model":[48,56,98,151,185],"can":[49],"be":[50],"compressed":[51],"into":[52,69,219],"compact":[54,220],"one-step":[55,71,183],"fast":[58],"reconstruction.":[61],"Our":[62],"approach":[63],"distills":[64],"an":[65,94],"optimal-transport":[66],"teacher":[68,196],"consistency":[72,184],"model.":[73],"Low-fidelity":[74],"are":[76,224],"incorporated":[77],"at":[78,131],"inference":[79,166],"by":[80,190],"initializing":[81],"the":[82,90,105,142,149,169,173,177],"trajectory":[84],"noised":[87],"observation":[88],"along":[89],"transport":[91],"path,":[92],"allowing":[93],"unconditional":[95],"to":[99,135,226,229,233],"perform":[100],"conditional":[101],"reconstruction":[102,126,221],"without":[103],"retraining":[104],"teacher.":[106,171],"evaluate":[108],"this":[109],"distillation":[110,197],"strategy":[111],"three":[113],"fluid":[114],"benchmarks,":[115],"Smoke":[116],"Buoyancy,":[117],"Turbulent":[118],"Channel":[119],"Flow,":[120,123],"Kolmogorov":[122],"using":[124,156],"coarse-to-fine":[125],"controlled":[129],"testbed":[130],"field":[132],"sizes":[133],"up":[134],"$256":[136],"\\times":[137],"256$.":[138],"Across":[139],"these":[140],"settings,":[141],"distilled":[143,178],"student":[144,179],"retains":[145],"similar":[146],"performance":[147],"of":[148],"teacher's":[150],"spectrum":[153],"metrics,":[154],"while":[155],"roughly":[157],"half":[158],"many":[160],"parameters":[161],"achieving":[163],"$12\\times$":[165],"speedup":[167],"over":[168],"Under":[172],"same":[174],"training":[175,199],"budget,":[176],"also":[180],"outperforms":[181],"trained":[186],"directly":[187],"scratch":[189],"$23.1\\%$":[191],"SSIM,":[193],"showing":[194],"that":[195,223],"improves":[198],"efficiency":[200],"rather":[201],"than":[202],"merely":[203],"accelerating":[204],"sampling.":[205],"These":[206],"results":[207],"suggest":[208],"promising":[210],"route":[211],"turning":[213],"future":[214],"high-capacity":[215],"faster":[225],"train,":[227],"cheaper":[228],"run,":[230],"easier":[232],"deploy.":[234]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-09T00:00:00"}