{"id":"https://openalex.org/W4415235512","doi":"https://doi.org/10.1109/iccv51701.2025.01562","title":"Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis","display_name":"Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415235512","doi":"https://doi.org/10.1109/iccv51701.2025.01562"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.18569","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052439728","display_name":"Yanzuo Lu","orcid":"https://orcid.org/0000-0002-5554-8706"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanzuo Lu","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013516109","display_name":"Yuxi Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I1295703814","display_name":"World Vision","ror":"https://ror.org/01s0tbj55","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1295703814","https://openalex.org/I4210093867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxi Ren","raw_affiliation_strings":["ByteDance Seed Vision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed Vision","institution_ids":["https://openalex.org/I1295703814"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006669765","display_name":"Xin Xia","orcid":"https://orcid.org/0000-0002-6302-3256"},"institutions":[{"id":"https://openalex.org/I1295703814","display_name":"World Vision","ror":"https://ror.org/01s0tbj55","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1295703814","https://openalex.org/I4210093867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Xia","raw_affiliation_strings":["ByteDance Seed Vision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed Vision","institution_ids":["https://openalex.org/I1295703814"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048135392","display_name":"Shanchuan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I1295703814","display_name":"World Vision","ror":"https://ror.org/01s0tbj55","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1295703814","https://openalex.org/I4210093867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanchuan Lin","raw_affiliation_strings":["ByteDance Seed Vision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed Vision","institution_ids":["https://openalex.org/I1295703814"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100754893","display_name":"Xing Wang","orcid":"https://orcid.org/0000-0002-5810-2697"},"institutions":[{"id":"https://openalex.org/I1295703814","display_name":"World Vision","ror":"https://ror.org/01s0tbj55","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1295703814","https://openalex.org/I4210093867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xing Wang","raw_affiliation_strings":["ByteDance Seed Vision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed Vision","institution_ids":["https://openalex.org/I1295703814"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101051966","display_name":"Xuefeng Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I1295703814","display_name":"World Vision","ror":"https://ror.org/01s0tbj55","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1295703814","https://openalex.org/I4210093867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuefeng Xiao","raw_affiliation_strings":["ByteDance Seed Vision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed Vision","institution_ids":["https://openalex.org/I1295703814"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074765871","display_name":"Andy J. Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andy J. Ma","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018298892","display_name":"Xiaohua Xie","orcid":"https://orcid.org/0000-0002-0310-4679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohua Xie","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034685928","display_name":"Jianhuang Lai","orcid":"https://orcid.org/0000-0003-3883-2024"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian-Huang Lai","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"16818","last_page":"16829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9911999702453613,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9911999702453613,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9911999702453613,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9797999858856201,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.666100025177002},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.585099995136261},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5175999999046326},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5149000287055969},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.501800000667572},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4900999963283539},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.46230000257492065},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45840001106262207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7129999995231628},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.666100025177002},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.585099995136261},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5175999999046326},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44749999046325684},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33869999647140503},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33730000257492065},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2624000012874603}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.18569","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.18569","pdf_url":"https://arxiv.org/pdf/2507.18569","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.18569","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.18569","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":"pmh:oai:arXiv.org:2507.18569","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.18569","pdf_url":"https://arxiv.org/pdf/2507.18569","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6000880025","display_name":null,"funder_award_id":"U22A2095,12326618,62276281","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Distribution":[0,50],"Matching":[1,51],"Distillation":[2],"(DMD)":[3],"is":[4],"a":[5,53,131,152,187],"promising":[6],"score":[7,69,72,135],"distillation":[8,73,94,136,146,180],"technique":[9],"that":[10,56,176],"compresses":[11],"pre-trained":[12,90],"teacher":[13,126],"diffusion":[14],"models":[15],"into":[16,151],"efficient":[17,191],"one-step":[18,84,162],"or":[19],"multi-step":[20,178],"student":[21],"generators.":[22],"Nevertheless,":[23],"its":[24],"reliance":[25],"on":[26,120,164,181],"the":[27,62,79,89,106,117,125,139,144],"reverse":[28],"Kullback-Leibler":[29],"(KL)":[30],"divergence":[31],"minimization":[32],"potentially":[33],"induces":[34],"mode":[35],"collapse":[36],"(or":[37],"mode-seeking)":[38],"in":[39,74,98,111,138],"certain":[40],"applications.":[41],"To":[42],"circumvent":[43],"this":[44],"inherent":[45],"drawback,":[46],"we":[47,86],"propose":[48],"Adversarial":[49],"(ADM),":[52],"novel":[54],"framework":[55],"leverages":[57],"diffusion-based":[58],"discriminators":[59,97],"to":[60,167],"align":[61],"latent":[63,100],"predictions":[64],"between":[65],"real":[66],"and":[67,101,128,184,193],"fake":[68],"estimators":[70],"for":[71,134],"an":[75],"adversarial":[76,93,145],"manner.":[77],"In":[78],"context":[80],"of":[81],"extremely":[82],"challenging":[83],"distillation,":[85],"further":[87],"improve":[88],"generator":[91],"by":[92],"with":[95,148],"hybrid":[96],"both":[99],"pixel":[102],"spaces.":[103],"Different":[104],"from":[105,124],"mean":[107],"squared":[108],"error":[109],"used":[110],"DMD2":[112,168],"pre-training,":[113],"our":[114,157],"method":[115,159],"incorporates":[116],"distributional":[118],"loss":[119],"ODE":[121],"pairs":[122],"collected":[123],"model,":[127],"thus":[129],"providing":[130],"better":[132],"initialization":[133],"fine-tuning":[137,150],"next":[140],"stage.":[141],"By":[142],"combining":[143],"pre-training":[147],"ADM":[149,179],"unified":[153],"pipeline":[154],"termed":[155],"DMDX,":[156],"proposed":[158],"achieves":[160],"superior":[161],"performance":[163],"SDXL":[165],"compared":[166],"while":[169],"consuming":[170],"less":[171],"GPU":[172],"time.":[173],"Additional":[174],"experiments":[175],"apply":[177],"SD3-Medium,":[182],"SD3.5-Large,":[183],"CogVideoX":[185],"set":[186],"new":[188],"benchmark":[189],"towards":[190],"image":[192],"video":[194],"synthesis.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-16T00:00:00"}