{"id":"https://openalex.org/W7160267753","doi":"https://doi.org/10.48550/arxiv.2605.00941","title":"Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching","display_name":"Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7160267753","doi":"https://doi.org/10.48550/arxiv.2605.00941"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.00941","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00941","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.2605.00941","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053371530","display_name":"Jiarui Xing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing, Jiarui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135339594","display_name":"Song Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135348793","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-1543-2434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jian","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":0.8396000266075134,"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":0.8396000266075134,"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":0.023900000378489494,"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":0.013500000350177288,"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/covariance","display_name":"Covariance","score":0.6966000199317932},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6220999956130981},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.5412999987602234},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5335999727249146},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4097000062465668},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4072999954223633},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.37959998846054077},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.34709998965263367},{"id":"https://openalex.org/keywords/semimartingale","display_name":"Semimartingale","score":0.34040001034736633}],"concepts":[{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.6966000199317932},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6564000248908997},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6220999956130981},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5412999987602234},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5335999727249146},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4262000024318695},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38989999890327454},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.34709998965263367},{"id":"https://openalex.org/C39943821","wikidata":"https://www.wikidata.org/wiki/Q506346","display_name":"Semimartingale","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C83042196","wikidata":"https://www.wikidata.org/wiki/Q5178898","display_name":"Covariance intersection","level":4,"score":0.33730000257492065},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.32820001244544983},{"id":"https://openalex.org/C137250428","wikidata":"https://www.wikidata.org/wiki/Q5178897","display_name":"Covariance function","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C153024298","wikidata":"https://www.wikidata.org/wiki/Q3030678","display_name":"Hellinger distance","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C177384507","wikidata":"https://www.wikidata.org/wiki/Q1149000","display_name":"Multivariate normal distribution","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.00941","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00941","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.2605.00941","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00941","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Flow":[0],"matching":[1,69,112],"has":[2],"become":[3],"a":[4,92,136],"leading":[5],"framework":[6],"for":[7,77],"generative":[8,86],"modeling,":[9],"but":[10],"quantifying":[11],"the":[12,24,63,67,78,85,96,99,127,131,141,155,174],"uncertainty":[13,134,158,176],"of":[14,53,98],"its":[15],"samples":[16],"remains":[17],"an":[18,73],"open":[19],"problem.":[20],"Existing":[21],"approaches":[22],"retrain":[23],"model":[25],"with":[26],"auxiliary":[27],"variance":[28,143],"heads,":[29],"maintain":[30],"costly":[31],"ensembles,":[32],"or":[33,47,192],"propagate":[34],"approximate":[35],"covariance":[36,80],"through":[37],"many":[38],"integration":[39],"steps,":[40],"trading":[41],"off":[42],"training":[43],"cost,":[44,46],"inference":[45],"accuracy.":[48],"We":[49],"show":[50],"that":[51,154,173],"none":[52],"these":[54],"trade-offs":[55],"is":[56,170],"necessary.":[57],"By":[58],"extending":[59],"Tweedie's":[60],"formula":[61,129],"from":[62],"denoising":[64],"setting":[65],"to":[66],"flow":[68,111],"interpolant,":[70],"we":[71],"derive":[72],"exact,":[74],"closed-form":[75],"expression":[76],"posterior":[79],"at":[81,183],"every":[82],"point":[83],"along":[84],"trajectory.":[87],"The":[88],"result":[89],"depends":[90],"on":[91,108,151,164],"single":[93,137],"quantity,":[94],"namely":[95],"divergence":[97],"learned":[100],"velocity":[101],"field,":[102],"which":[103],"can":[104],"be":[105],"computed":[106],"post-hoc":[107],"any":[109],"pre-trained":[110],"model,":[113],"requiring":[114],"no":[115,118],"retraining":[116],"and":[117,172],"architectural":[119],"modification.":[120],"For":[121],"one-step":[122],"generators":[123],"such":[124],"as":[125],"MeanFlow,":[126],"same":[128],"yields":[130],"end-to-end":[132],"generation":[133],"in":[135],"forward":[138],"pass,":[139],"eliminating":[140],"multi-step":[142],"propagation":[144],"required":[145],"by":[146],"all":[147,182],"prior":[148],"methods.":[149],"Experiments":[150],"MNIST":[152],"confirm":[153],"resulting":[156],"per-pixel":[157],"maps":[159],"are":[160],"semantically":[161],"meaningful,":[162],"concentrating":[163],"digit":[165],"boundaries":[166],"where":[167],"inter-sample":[168],"variation":[169],"highest,":[171],"scalar":[175],"score":[177],"tracks":[178],"actual":[179],"prediction":[180],"error,":[181],"roughly":[184],"$10^4":[185],"\\times$":[186],"less":[187],"total":[188],"compute":[189],"than":[190],"ensembling":[191],"Monte":[193],"Carlo":[194],"dropout.":[195]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-06T00:00:00"}