{"id":"https://openalex.org/W7164805836","doi":"https://doi.org/10.1145/3805622.3810881","title":"MixCache: Mixture-of-Cache for Video Diffusion Transformer Acceleration","display_name":"MixCache: Mixture-of-Cache for Video Diffusion Transformer Acceleration","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164805836","doi":"https://doi.org/10.1145/3805622.3810881"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810881","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810881","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810881","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110558003","display_name":"Yuanxin Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanxin Wei","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-6551-9274","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020574416","display_name":"Lansong Diao","orcid":"https://orcid.org/0009-0000-6193-6126"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lansong Diao","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-6193-6126","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044801468","display_name":"Bujiao Chen","orcid":"https://orcid.org/0009-0009-0443-570X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bujiao Chen","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-5704-9861","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037038779","display_name":"Shenggan Cheng","orcid":"https://orcid.org/0000-0002-7966-2941"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shenggan Cheng","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7966-2941","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101227501","display_name":"Zhengping Qian","orcid":"https://orcid.org/0000-0002-0741-9918"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengping Qian","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0741-9918","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018856303","display_name":"Wenyuan Yu","orcid":"https://orcid.org/0009-0006-5641-2452"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyuan Yu","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-5641-2452","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023506057","display_name":"Nong Xiao","orcid":"https://orcid.org/0000-0002-2166-977X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nong Xiao","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2166-977X","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636012","display_name":"Wei Lin","orcid":"https://orcid.org/0000-0002-3003-0150"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Lin","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3003-0150","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024085713","display_name":"Jiangsu Du","orcid":"https://orcid.org/0000-0003-4707-9492"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangsu Du","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4707-9492","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93919172,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1608","last_page":"1617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.5763000249862671,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11478","display_name":"Caching and Content Delivery","score":0.5763000249862671,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11165","display_name":"Image and Video Quality Assessment","score":0.18870000541210175,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.043800000101327896,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/speedup","display_name":"Speedup","score":0.8258000016212463},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5938000082969666},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5871000289916992},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.46459999680519104},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.44670000672340393},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4002000093460083},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.36329999566078186},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.33090001344680786}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8258000016212463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8192999958992004},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5938000082969666},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5871000289916992},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.46459999680519104},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4611999988555908},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44670000672340393},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4090000092983246},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4002000093460083},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.36329999566078186},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34290000796318054},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.3183000087738037},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C134535813","wikidata":"https://www.wikidata.org/wiki/Q1888734","display_name":"Transcoding","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810881","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810881","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810881","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810881","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2962785568","https://openalex.org/W4308167501","https://openalex.org/W4312933868","https://openalex.org/W4386071831","https://openalex.org/W4389911278","https://openalex.org/W4390872297","https://openalex.org/W4390872556","https://openalex.org/W4390873135","https://openalex.org/W4399400846","https://openalex.org/W4400342687","https://openalex.org/W4402660110","https://openalex.org/W4402778510","https://openalex.org/W4402816687","https://openalex.org/W4403346100","https://openalex.org/W4403798778","https://openalex.org/W4404311645","https://openalex.org/W4404388595","https://openalex.org/W4405030055","https://openalex.org/W4414565121","https://openalex.org/W4414585734","https://openalex.org/W4415288099","https://openalex.org/W4416053328"],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"video":[1,20,31,116,171],"generation":[2,95,172,187],"models":[3,22,164],"are":[4,87],"increasingly":[5],"vital":[6],"for":[7,29,114,153],"multimedia":[8,55],"synthetic":[9],"content":[10],"generation.":[11,32],"Leveraging":[12],"the":[13,17,67,70,122,156],"Transformer":[14],"architecture":[15],"and":[16,43,53,97,124,130,189],"diffusion":[18,71],"process,":[19],"DiT":[21,64,117],"have":[23],"emerged":[24],"as":[25],"a":[26,58,101,110,133],"dominant":[27],"approach":[28],"high-quality":[30],"However,":[33],"their":[34,48],"multi-step":[35],"iterative":[36],"denoising":[37],"process":[38,72],"incurs":[39],"high":[40],"computational":[41],"cost":[42],"inference":[44,98,190],"latency,":[45],"which":[46],"limits":[47],"practical":[49],"deployment":[50],"in":[51,63,69,76,100],"large-scale":[52],"interactive":[54],"applications.":[56],"Caching,":[57],"widely":[59],"adopted":[60],"optimization":[61],"method":[62],"models,":[65],"leverages":[66],"redundancy":[68],"to":[73,89,93,138,193],"skip":[74],"computations":[75],"different":[77,127],"granularities":[78],"(e.g.,":[79,173],"step,":[80],"cfg,":[81],"block).":[82],"Nevertheless,":[83],"existing":[84],"caching":[85,128,141,158],"methods":[86],"limited":[88],"single-granularity":[90],"strategies,":[91,129],"struggling":[92],"balance":[94],"quality":[96,188],"speed":[99],"flexible":[102],"manner.":[103],"In":[104],"this":[105],"work,":[106],"we":[107],"propose":[108],"MixCache,":[109],"training-free":[111],"caching-based":[112],"framework":[113],"efficient":[115],"inference.":[118],"MixCache":[119,167],"first":[120],"distinguishes":[121],"interference":[123],"boundary":[125],"between":[126],"then":[131],"introduces":[132],"context-aware":[134],"cache":[135,150],"triggering":[136],"strategy":[137,152],"determine":[139],"when":[140],"should":[142],"be":[143],"enabled,":[144],"along":[145],"with":[146],"an":[147],"adaptive":[148],"hybrid":[149],"decision":[151],"dynamically":[154],"selecting":[155],"optimal":[157],"granularity.":[159],"Extensive":[160],"experiments":[161],"on":[162,176,181],"diverse":[163],"demonstrate":[165],"that":[166],"can":[168],"significantly":[169],"accelerate":[170],"1.94\u00d7":[174],"speedup":[175,180],"Wan":[177],"14B,":[178],"1.97\u00d7":[179],"HunyuanVideo)":[182],"while":[183],"delivering":[184],"both":[185],"superior":[186],"efficiency":[191],"compared":[192],"baseline":[194],"methods.":[195]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}
