{"id":"https://openalex.org/W7140227948","doi":"https://doi.org/10.48550/arxiv.2603.21348","title":"Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution","display_name":"Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution","publication_year":2026,"publication_date":"2026-03-22","ids":{"openalex":"https://openalex.org/W7140227948","doi":"https://doi.org/10.48550/arxiv.2603.21348"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.21348","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21348","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.2603.21348","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tai, Yu-Shan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tai, Yu-Shan","raw_affiliation_strings":["Andy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Andy","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"An-Yeu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"An-Yeu","raw_affiliation_strings":["Andy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Andy","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu","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":0.5705000162124634,"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":0.5705000162124634,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.055399999022483826,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.0494999997317791,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7613000273704529},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6935999989509583},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5878000259399414},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.501800000667572},{"id":"https://openalex.org/keywords/diffusion-process","display_name":"Diffusion process","score":0.4961000084877014},{"id":"https://openalex.org/keywords/time-sequence","display_name":"Time sequence","score":0.4336000084877014},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4108000099658966},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.38530001044273376}],"concepts":[{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7613000273704529},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6935999989509583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6582000255584717},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6062999963760376},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5878000259399414},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.4961000084877014},{"id":"https://openalex.org/C3020136221","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time sequence","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38019999861717224},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.328900009393692},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2953000068664551},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.2782999873161316},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C74080474","wikidata":"https://www.wikidata.org/wiki/Q7305975","display_name":"Redistribution (election)","level":3,"score":0.25380000472068787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.21348","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21348","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.2603.21348","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21348","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":{"Recently,":[0],"diffusion":[1],"models":[2,36],"(DMs)":[3],"have":[4],"made":[5],"significant":[6],"strides":[7],"in":[8,19,119],"high-quality":[9],"image":[10],"generation.":[11,82],"However,":[12,43],"the":[13,39,107],"multi-step":[14],"denoising":[15],"process":[16],"often":[17],"results":[18,104],"considerable":[20],"computational":[21],"overhead,":[22],"impeding":[23],"deployment":[24],"on":[25,121],"resource-constrained":[26],"edge":[27],"devices.":[28],"Existing":[29],"methods":[30,109],"mitigate":[31],"this":[32,54],"issue":[33],"by":[34],"compressing":[35],"and":[37,48,123],"adjusting":[38],"time":[40],"step":[41],"sequence.":[42],"they":[44],"overlook":[45],"input":[46],"redundancy":[47],"require":[49],"lengthy":[50],"search":[51],"times.":[52],"In":[53],"paper,":[55],"we":[56,71,84],"propose":[57],"Coarse-to-Fine":[58,73],"Diffusion":[59],"Models":[60],"with":[61,113],"Time":[62,86],"Step":[63,87],"Sequence":[64,88],"Redistribution.":[65],"Recognizing":[66],"indistinguishable":[67],"early-stage":[68],"generated":[69],"images,":[70],"introduce":[72],"Denoising":[74],"(C2F)":[75],"to":[76,116],"reduce":[77],"computation":[78,120],"during":[79],"coarse":[80],"feature":[81],"Furthermore,":[83],"design":[85],"Redistribution":[89],"(TRD)":[90],"for":[91,101],"efficient":[92],"sampling":[93],"trajectory":[94],"adjustment,":[95],"requiring":[96],"less":[97],"than":[98],"10":[99],"minutes":[100],"search.":[102],"Experimental":[103],"demonstrate":[105],"that":[106],"proposed":[108],"achieve":[110],"near-lossless":[111],"performance":[112],"an":[114],"80%":[115],"90%":[117],"reduction":[118],"CIFAR10":[122],"LSUN-Church.":[124]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-25T00:00:00"}