{"id":"https://openalex.org/W7165386527","doi":"https://doi.org/10.48550/arxiv.2606.19662","title":"Learning When to Denoise: Optimizing Asynchronous Schedules for Latent Diffusion","display_name":"Learning When to Denoise: Optimizing Asynchronous Schedules for Latent Diffusion","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W7165386527","doi":"https://doi.org/10.48550/arxiv.2606.19662"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.19662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19662","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.2606.19662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113196808","display_name":"Bingshuo Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Bingshuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138963610","display_name":"Xiang Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Xiang","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":0.9174000024795532,"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":0.9174000024795532,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.014000000432133675,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.01080000028014183,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7211999893188477},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.7067000269889832},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5566999912261963},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5271999835968018},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.48809999227523804},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.46860000491142273},{"id":"https://openalex.org/keywords/monotone-polygon","display_name":"Monotone polygon","score":0.42289999127388},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.39809998869895935}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7211999893188477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124000191688538},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.7067000269889832},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5566999912261963},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38589999079704285},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37709999084472656},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3472999930381775},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.32670000195503235},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2890999913215637},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.19662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19662","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.2606.19662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19662","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-representation":[0],"diffusion":[1],"models":[2],"can":[3],"improve":[4],"visual":[5],"synthesis":[6],"by":[7,77],"denoising":[8],"complementary":[9],"views":[10],"of":[11,145],"an":[12],"image,":[13],"but":[14],"their":[15],"performance":[16],"depends":[17],"critically":[18],"on":[19],"the":[20,60,65,97,123,141,154,165],"asynchronous":[21,39],"schedule":[22,61,66,99],"that":[23,51,72],"determines":[24],"when":[25],"each":[26,53],"representation":[27,44],"is":[28,73,184],"denoised.":[29],"We":[30,63],"propose":[31],"to":[32,132,137,177],"learn":[33,80],"this":[34],"schedule.":[35],"Our":[36],"method":[37],"formulates":[38],"flow":[40],"matching":[41,122],"over":[42],"multiple":[43],"spaces":[45],"and":[46,75,79,105,175],"uses":[47],"a":[48,68,83,109,150],"schedule-corrected":[49],"objective":[50],"keeps":[52],"representation's":[54],"local":[55],"noising-time":[56],"weights":[57],"fixed":[58],"as":[59],"changes.":[62],"instantiate":[64],"with":[67,87,127],"flexible":[69],"parametric":[70],"class":[71],"convex":[74],"monotone":[76],"construction,":[78],"it":[81],"using":[82,149],"fast":[84],"joint":[85],"probe":[86],"less":[88,129,173],"than":[89],"1%":[90],"additional":[91],"training":[92],"compute.":[93],"On":[94],"ImageNet":[95],"256x256,":[96],"learned":[98],"substantially":[100],"improves":[101,136,176],"both":[102],"convergence":[103],"speed":[104],"final":[106],"quality":[107],"under":[108],"matched":[110],"675M-parameter":[111],"XL":[112],"backbone.":[113],"With":[114],"AutoGuidance,":[115],"our":[116,157],"200-epoch":[117,158],"model":[118,159],"reaches":[119,160],"FID":[120,138,146,161,178],"1.05,":[121],"800-epoch":[124,167],"SFD-XL":[125,168],"baseline":[126],"4x":[128,172],"training.":[130],"Training":[131],"600":[133,181],"epochs":[134],"further":[135],"1.02,":[139],"outperforming":[140],"1B-parameter":[142],"SFD-XXL":[143],"result":[144,169],"1.04":[147],"while":[148],"smaller":[151],"model.":[152],"In":[153],"unguided":[155],"setting,":[156],"2.37,":[162],"already":[163],"below":[164],"best":[166],"(2.54)":[170],"at":[171,180,186],"training,":[174],"2.14":[179],"epochs.":[182],"Code":[183],"available":[185],"https://github.com/bsq532087/LWD":[187]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-20T00:00:00"}