{"id":"https://openalex.org/W7161721491","doi":"https://doi.org/10.48550/arxiv.2605.18190","title":"Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network","display_name":"Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7161721491","doi":"https://doi.org/10.48550/arxiv.2605.18190"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.18190","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18190","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.18190","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044813646","display_name":"Grigory Bartosh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bartosh, Grigory","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071161029","display_name":"David Ruhe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruhe, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016363084","display_name":"Emiel Hoogeboom","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoogeboom, Emiel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136469102","display_name":"Jonathan Heek","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heek, Jonathan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056112540","display_name":"Thomas Mensink","orcid":"https://orcid.org/0000-0002-5730-713X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mensink, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082512329","display_name":"Tim Salimans","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salimans, Tim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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":0.8582000136375427,"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":0.8582000136375427,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.028599999845027924,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.02449999935925007,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.614300012588501},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6115999817848206},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5512999892234802},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5428000092506409},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.482699990272522},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4814000129699707},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.48100000619888306},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.47909998893737793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092999815940857},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.614300012588501},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6115999817848206},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5512999892234802},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4814000129699707},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.48100000619888306},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4368000030517578},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41659998893737793},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4083000123500824},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.33739998936653137},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2709999978542328},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.18190","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18190","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.18190","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18190","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":"article"},"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":{"Diffusion":[0,92],"models":[1],"achieve":[2],"state-of-the-art":[3],"generative":[4],"performance":[5,95],"but":[6],"suffer":[7],"from":[8],"high":[9],"computational":[10,101],"costs":[11],"during":[12],"inference":[13,83],"due":[14],"to":[15,33,58,74],"the":[16,38,67,76,94],"repeated":[17],"evaluation":[18],"of":[19,40,96,106],"a":[20,31,41,47,104],"heavy":[21,42],"neural":[22],"network.":[23],"In":[24],"this":[25],"work,":[26],"we":[27,109],"propose":[28],"Dual-Rate":[29,91],"Diffusion,":[30],"method":[32,113],"accelerate":[34],"sampling":[35],"by":[36,66,103],"interleaving":[37],"execution":[39],"high-capacity":[43],"context":[44,53],"encoder":[45,54],"and":[46],"light":[48,68],"efficient":[49],"denoising":[50,69],"model.":[51],"The":[52],"is":[55,114],"evaluated":[56],"sparsely":[57],"extract":[59],"high-dimensional":[60],"features,":[61],"which":[62],"are":[63],"effectively":[64],"reused":[65],"model":[70],"at":[71],"every":[72],"step":[73],"refine":[75],"sample":[77,86],"efficiently.":[78],"This":[79],"approach":[80],"significantly":[81],"accelerates":[82],"without":[84],"compromising":[85],"quality.":[87],"On":[88],"ImageNet":[89],"benchmarks,":[90],"matches":[93],"standard":[97],"baselines":[98],"while":[99],"reducing":[100],"cost":[102],"factor":[105],"$2$-$4$.":[107],"Furthermore,":[108],"demonstrate":[110],"that":[111],"our":[112],"compatible":[115],"with":[116],"distillation":[117],"techniques,":[118],"such":[119],"as":[120],"Moment":[121],"Matching":[122],"Distillation,":[123],"enabling":[124],"further":[125],"efficiency":[126],"gains":[127],"in":[128],"few-step":[129],"generation.":[130]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-20T00:00:00"}