{"id":"https://openalex.org/W4416960648","doi":"https://doi.org/10.1109/tpami.2025.3639602","title":"USF++: A Unified Sampling Framework for Solver Searching of Diffusion Probabilistic Models","display_name":"USF++: A Unified Sampling Framework for Solver Searching of Diffusion Probabilistic Models","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416960648","doi":"https://doi.org/10.1109/tpami.2025.3639602","pmid":"https://pubmed.ncbi.nlm.nih.gov/41336159"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3639602","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3639602","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tpami.2025.3639602","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017214725","display_name":"Dehui Zou","orcid":"https://orcid.org/0000-0002-8135-4913"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dongyun Zou","raw_affiliation_strings":["Department of EE, Tsinghua University, Beijing, China","Department of EE, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of EE, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of EE, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052918296","display_name":"Enshu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enshu Liu","raw_affiliation_strings":["Department of EE, Tsinghua University, Beijing, China","Department of EE, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of EE, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of EE, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086217226","display_name":"Xuefei Ning","orcid":"https://orcid.org/0000-0003-2209-8312"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefei Ning","raw_affiliation_strings":["Department of EE, Tsinghua University, Beijing, China","Department of EE, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of EE, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of EE, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103867707","display_name":"Huazhong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huazhong Yang","raw_affiliation_strings":["Department of EE, Tsinghua University, Beijing, China","Department of EE, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of EE, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of EE, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445079","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6908-508X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Department of EE, Tsinghua University, Beijing, China","Department of EE, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of EE, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of EE, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017214725"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30389653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"3","first_page":"3640","last_page":"3651"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.2818000018596649,"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"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.2818000018596649,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.27810001373291016,"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/T12303","display_name":"Tensor decomposition and applications","score":0.15389999747276306,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7398999929428101},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6468999981880188},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4620000123977661},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.4607999920845032},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.4503999948501587},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.41040000319480896},{"id":"https://openalex.org/keywords/adaptive-sampling","display_name":"Adaptive sampling","score":0.39149999618530273},{"id":"https://openalex.org/keywords/truncation","display_name":"Truncation (statistics)","score":0.39100000262260437}],"concepts":[{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7398999929428101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940000057220459},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6468999981880188},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4505999982357025},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4503999948501587},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44690001010894775},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.39149999618530273},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3411000072956085},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32109999656677246},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.27129998803138733},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C104942944","wikidata":"https://www.wikidata.org/wiki/Q3434686","display_name":"Truncation error","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3639602","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3639602","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41336159","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41336159","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":{"id":"doi:10.1109/tpami.2025.3639602","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3639602","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1991111872","https://openalex.org/W2108598243","https://openalex.org/W2950220059","https://openalex.org/W2965658867","https://openalex.org/W3107453328","https://openalex.org/W4229944339","https://openalex.org/W4247080625","https://openalex.org/W4312933868","https://openalex.org/W4386071831","https://openalex.org/W4411528087"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2,52],"witnessed":[3],"the":[4,29,32,42,54,63,87,110,120,124,140,159,173,204,223,233],"rapid":[5],"progress":[6],"and":[7,113,154,180,194,215],"broad":[8],"application":[9],"of":[10,34,45,148,220,225],"diffusion":[11],"probabilistic":[12],"models":[13],"(DPMs).":[14],"Sampling":[15],"from":[16],"DPMs":[17,35],"can":[18,71],"be":[19,73],"viewed":[20],"as":[21],"solving":[22,101],"an":[23,217],"ordinary":[24],"differential":[25],"equation":[26],"(ODE).":[27],"Despite":[28],"promising":[30],"performance,":[31],"generation":[33],"usually":[36],"consumes":[37],"much":[38],"time":[39],"due":[40],"to":[41,56,85,122,166,212],"large":[43,129],"number":[44],"function":[46],"evaluations":[47],"(NFE).":[48],"Though":[49],"recent":[50],"works":[51],"accelerated":[53],"sampling":[55,82,136,175,226],"around":[57],"20":[58],"steps":[59,230],"with":[60,66,188,197],"high-order":[61],"solvers,":[62],"sample":[64,125],"quality":[65,126],"less":[67],"than":[68],"10":[69],"NFE":[70,190,199],"still":[72],"improved.":[74],"In":[75],"this":[76,93],"paper,":[77],"we":[78,95,132,162,184],"propose":[79,133],"a":[80,114,128,134],"unified":[81],"framework":[83,137],"(USF++)":[84],"study":[86],"optional":[88],"strategies":[89,102],"for":[90,158],"solver.":[91],"Under":[92],"framework,":[94],"further":[96,108,209],"reveal":[97],"that":[98,144],"taking":[99],"different":[100,104],"at":[103,151],"timesteps":[105],"may":[106],"help":[107],"decrease":[109],"truncation":[111],"error,":[112],"carefully":[115],"designed":[116],"solver":[117,149,169],"schedule":[118],"has":[119],"potential":[121],"improve":[123],"by":[127],"margin.":[130],"Therefore,":[131],"new":[135],"based":[138],"on":[139,177,191,200],"exponential":[141],"integral":[142],"formulation":[143],"allows":[145],"free":[146],"choices":[147],"strategy":[150],"each":[152],"step":[153],"design":[155],"specific":[156],"decisions":[157],"framework.":[160],"Moreover,":[161],"apply":[163,210],"evolutionary":[164],"search":[165],"find":[167],"outstanding":[168],"schedules":[170],"which":[171],"outperform":[172],"state-of-the-art":[174],"methods":[176],"CIFAR-10,":[178],"ImageNet,":[179],"LSUN-Bedroom":[181,201],"datasets.":[182],"Specifically,":[183],"achieve":[185],"3.89":[186],"FID":[187,196],"5":[189],"CIFAR-10":[192],"dataset":[193],"8.62":[195],"3":[198],"dataset,":[202],"outperforming":[203],"SOTA":[205],"method":[206],"significantly.":[207],"We":[208],"searching":[211],"Stable-Diffusion":[213],"model":[214],"get":[216],"acceleration":[218],"ratio":[219],"2\u00d7,":[221],"showing":[222],"feasibility":[224],"in":[227],"very":[228],"few":[229],"without":[231],"retraining":[232],"neural":[234],"network.":[235]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-03T00:00:00"}