{"id":"https://openalex.org/W4414199045","doi":"https://doi.org/10.1109/dac63849.2025.11132632","title":"SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity","display_name":"SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414199045","doi":"https://doi.org/10.1109/dac63849.2025.11132632"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11132632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008585508","display_name":"Zichen Fan","orcid":"https://orcid.org/0000-0002-8181-2996"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zichen Fan","raw_affiliation_strings":["University of Michigan,Ann Arbor,MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Ann Arbor,MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055597446","display_name":"Steve Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steve Dai","raw_affiliation_strings":["NVIDIA,Santa Clara,CA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045219356","display_name":"Rangharajan Venkatesan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rangharajan Venkatesan","raw_affiliation_strings":["NVIDIA,Santa Clara,CA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000767141","display_name":"Dennis Sylvester","orcid":"https://orcid.org/0000-0003-2598-0458"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dennis Sylvester","raw_affiliation_strings":["University of Michigan,Ann Arbor,MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Ann Arbor,MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010156116","display_name":"Brucek Khailany","orcid":"https://orcid.org/0000-0002-7584-3489"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brucek Khailany","raw_affiliation_strings":["NVIDIA,Santa Clara,CA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,CA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008585508"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2039439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.46959999203681946,"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/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.46959999203681946,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.7526999711990356},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5831999778747559},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5478000044822693},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.48330000042915344},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.44020000100135803},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.3698999881744385}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7526999711990356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6342999935150146},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5831999778747559},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5717999935150146},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5478000044822693},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.48330000042915344},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40299999713897705},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2711000144481659},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.26570001244544983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11132632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11132632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2606722458","https://openalex.org/W2618530766","https://openalex.org/W2790925711","https://openalex.org/W2950656546","https://openalex.org/W2962770929","https://openalex.org/W2962834855","https://openalex.org/W2979310060","https://openalex.org/W2979439447","https://openalex.org/W2997929983","https://openalex.org/W3016542674","https://openalex.org/W3016735325","https://openalex.org/W3034600949","https://openalex.org/W3210117238","https://openalex.org/W4240168186","https://openalex.org/W4285335127","https://openalex.org/W4386065704","https://openalex.org/W4386071957","https://openalex.org/W4390874074","https://openalex.org/W4402475781","https://openalex.org/W4402716152","https://openalex.org/W4402716225"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"models":[1],"have":[2],"gained":[3],"significant":[4,43],"popularity":[5],"in":[6],"image":[7],"generation":[8,104],"tasks.":[9],"However,":[10],"generating":[11],"high-quality":[12],"content":[13],"remains":[14],"notably":[15],"slow":[16],"because":[17],"it":[18],"requires":[19],"running":[20],"model":[21,75],"inference":[22],"over":[23],"many":[24],"time":[25,61],"steps.":[26,62],"To":[27,63],"accelerate":[28],"these":[29],"models,":[30],"we":[31,70],"propose":[32],"to":[33,107,123],"aggressively":[34],"quantize":[35],"both":[36],"weights":[37],"and":[38,58,67,86,118],"activations,":[39],"while":[40],"simultaneously":[41],"promoting":[42],"activation":[44],"sparsity.":[45],"We":[46],"further":[47],"observe":[48],"that":[49],"the":[50,95],"stated":[51],"sparsity":[52,68,89,96],"pattern":[53],"varies":[54],"among":[55],"different":[56],"channels":[57],"evolves":[59],"across":[60],"support":[64],"this":[65],"quantization":[66,100],"scheme,":[69],"present":[71],"a":[72,78,87],"novel":[73],"diffusion":[74],"accelerator":[76,113],"featuring":[77],"heterogeneous":[79],"mixed-precision":[80],"dense-sparse":[81],"architecture,":[82],"channel-last":[83],"address":[84],"mapping,":[85],"time-step-aware":[88],"detector":[90],"for":[91],"efficient":[92],"handling":[93],"of":[94],"pattern.":[97],"Our":[98,111],"4-bit":[99],"technique":[101],"demonstrates":[102],"superior":[103],"quality":[105],"compared":[106,122],"existing":[108],"$\\mathbf{4}$-bit":[109],"methods.":[110],"custom":[112],"achieves":[114],"$6.91":[115],"\\times$":[116],"speed-up":[117],"51.5%":[119],"energy":[120],"reduction":[121],"traditional":[124],"dense":[125],"accelerators.":[126]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}