{"id":"https://openalex.org/W7165666963","doi":"https://doi.org/10.48550/arxiv.2606.22752","title":"One-Step Flow Matching for Generative Modeling of Path-Dependent Physical Fields","display_name":"One-Step Flow Matching for Generative Modeling of Path-Dependent Physical Fields","publication_year":2026,"publication_date":"2026-06-22","ids":{"openalex":"https://openalex.org/W7165666963","doi":"https://doi.org/10.48550/arxiv.2606.22752"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.22752","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22752","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":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.2606.22752","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139205130","display_name":"Yijing Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yijing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139191287","display_name":"Jasmin Jelovica","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jelovica, Jasmin","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":0.5552999973297119,"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":0.5552999973297119,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.17949999868869781,"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"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.0568000003695488,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.718500018119812},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5615000128746033},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.5296000242233276},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4722000062465668},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4325000047683716},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.4099000096321106},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4020000100135803},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.3772999942302704}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.718500018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6657000184059143},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5615000128746033},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5361999869346619},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.5296000242233276},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4722000062465668},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3772999942302704},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3700000047683716},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33640000224113464},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C2778414698","wikidata":"https://www.wikidata.org/wiki/Q7623438","display_name":"Stress field","level":3,"score":0.326200008392334},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.302700012922287},{"id":"https://openalex.org/C91188154","wikidata":"https://www.wikidata.org/wiki/Q186247","display_name":"Vector field","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C130187892","wikidata":"https://www.wikidata.org/wiki/Q133327","display_name":"Spacetime","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.22752","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22752","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":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.2606.22752","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22752","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":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":{"Physical":[0],"simulations":[1],"for":[2,52,94,147],"intricate":[3],"geometries":[4],"with":[5,100,201],"path-dependent":[6,96,194,212],"constitutive":[7],"models":[8,47,68],"face":[9],"difficulties":[10],"due":[11],"to":[12,38,69,165,187,229],"the":[13,20,111,121,133,190],"enormous":[14],"computational":[15],"cost":[16],"they":[17,57],"require.":[18],"Recently,":[19],"emergence":[21],"of":[22,61,66,114,123,227,240],"generative":[23,67],"AI":[24],"models,":[25],"which":[26],"succeed":[27],"in":[28,169,193],"image":[29],"and":[30,64,104,119,183,236],"video":[31,128],"synthesis":[32,129],"tasks,":[33],"has":[34],"provided":[35],"a":[36,83,91,115,127,143,202,225],"promise":[37],"further":[39,188],"improve":[40],"simulations.":[41],"Although":[42],"U-Net-based":[43],"denoising":[44],"diffusion":[45],"probabilistic":[46],"(DDPMs)":[48],"have":[49],"been":[50],"adopted":[51],"elastic":[53],"stress":[54,73,97,134],"field":[55,98],"generation,":[56],"typically":[58],"require":[59],"hundreds":[60],"sampling":[62],"steps,":[63],"applications":[65],"path-dependent,":[70],"e.g.":[71],"plastic,":[72],"fields":[74,125,135],"remain":[75],"very":[76],"limited.":[77],"In":[78,176],"this":[79],"work,":[80],"we":[81,141,178],"propose":[82],"novel":[84],"flow":[85,148],"matching":[86],"(FM)":[87],"model":[88,108,164,191,207],"based":[89],"on":[90,174,234,243],"transformer":[92],"backbone":[93],"high-resolution":[95,211],"generation":[99],"stochastic":[101],"loading-unloading":[102],"paths":[103,156],"geometry.":[105],"The":[106,196],"proposed":[107],"operates":[109],"within":[110],"latent":[112],"space":[113],"variational":[116],"autoencoder":[117],"(VAE)":[118],"formulates":[120],"simulation":[122],"plastic":[124],"as":[126],"task,":[130],"directly":[131],"generating":[132],"across":[136],"all":[137],"time":[138],"steps.":[139],"Meanwhile,":[140],"design":[142],"non-Gaussian":[144],"source":[145],"distribution":[146],"matching,":[149],"such":[150],"that":[151],"crossings":[152],"among":[153],"conditional":[154],"transport":[155],"are":[157],"reduced":[158],"during":[159],"training.":[160],"This":[161],"enables":[162],"our":[163,206],"generate":[166,210],"satisfactory":[167],"samples":[168],"one":[170],"step":[171],"without":[172],"relying":[173],"distillation.":[175],"addition,":[177],"introduce":[179],"token-level":[180],"loading":[181],"embeddings":[182],"two":[184,238],"auxiliary":[185],"networks":[186],"enhance":[189],"performance":[192],"simulation.":[195],"results":[197],"demonstrate":[198],"that,":[199],"even":[200],"limited":[203],"training":[204],"dataset,":[205],"can":[208],"accurately":[209],"fields.":[213],"It":[214],"is":[215],"much":[216],"more":[217],"computationally":[218],"efficient":[219],"than":[220],"finite":[221],"element":[222],"analysis,":[223],"providing":[224],"speedup":[226,242],"6":[228],"7":[230],"times":[231],"over":[232],"FEM":[233],"CPUs":[235],"approximately":[237],"orders":[239],"magnitude":[241],"consumer-grade":[244],"GPUs.":[245]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-24T00:00:00"}