{"id":"https://openalex.org/W7140792250","doi":"https://doi.org/10.48550/arxiv.2603.24260","title":"Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep","display_name":"Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7140792250","doi":"https://doi.org/10.48550/arxiv.2603.24260"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.24260","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24260","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2603.24260","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130691934","display_name":"Tianyi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Tianyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130661519","display_name":"Ye Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Ye","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130631410","display_name":"Linfeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Linfeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130644708","display_name":"Chen Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025795563","display_name":"Jianjun Gao","orcid":"https://orcid.org/0000-0002-7824-5919"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Jianjun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130669552","display_name":"Yi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130666200","display_name":"Kim-Hui Yap","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yap, Kim-Hui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130635340","display_name":"Lap-Pui Chau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chau, Lap-Pui","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5130691934"],"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":0.3630000054836273,"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":0.3630000054836273,"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/T11019","display_name":"Image Enhancement Techniques","score":0.17339999973773956,"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/T11478","display_name":"Caching and Content Delivery","score":0.10480000078678131,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7340999841690063},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5940999984741211},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5264999866485596},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5074999928474426},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4505000114440918},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4449000060558319},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.41110000014305115},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.396699994802475},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.38530001044273376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230999708175659},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7340999841690063},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5940999984741211},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5264999866485596},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5074999928474426},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.44119998812675476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4156999886035919},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.396699994802475},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.36329999566078186},{"id":"https://openalex.org/C77019957","wikidata":"https://www.wikidata.org/wiki/Q2689057","display_name":"Dependability","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3206999897956848},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.2937999963760376},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.29269999265670776},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26820001006126404},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C2779631151","wikidata":"https://www.wikidata.org/wiki/Q7883767","display_name":"Underspecification","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2578999996185303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.24260","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24260","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.24260","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24260","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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-based":[0],"video":[1,41],"editing":[2,177,206],"has":[3],"emerged":[4],"as":[5],"an":[6],"important":[7],"paradigm":[8],"for":[9,37],"high-quality":[10],"and":[11,19,107,122,148,151,162,179,194],"flexible":[12],"content":[13],"generation.":[14],"However,":[15],"despite":[16],"their":[17],"generality":[18],"strong":[20],"modeling":[21],"capacity,":[22],"Diffusion":[23],"Transformers":[24],"(DiT)":[25],"remain":[26],"computationally":[27],"expensive":[28],"due":[29],"to":[30,78,82,96],"the":[31,53,60,64,83,98,119,140,154,159],"iterative":[32],"denoising":[33,47,56],"process,":[34,57],"posing":[35],"challenges":[36],"practical":[38],"deployment.":[39],"Existing":[40],"diffusion":[42,92],"acceleration":[43,93],"methods":[44],"primarily":[45],"exploit":[46,97],"timestep-level":[48],"feature":[49],"reuse,":[50],"which":[51],"mitigates":[52],"redundancy":[54,62],"in":[55,101,130,143,205],"but":[58],"overlooks":[59],"architectural":[61],"within":[63],"DiT":[65,144],"that":[66,157,183],"many":[67],"attention":[68,173],"operations":[69,174],"over":[70,197],"spatio-temporal":[71],"tokens":[72,129,142,156],"are":[73],"redundantly":[74],"executed,":[75],"offering":[76],"little":[77],"no":[79],"incremental":[80],"contribution":[81],"model":[84,145],"output.":[85],"This":[86,169],"work":[87],"introduces":[88],"HetCache,":[89],"a":[90,186,190],"training-free":[91],"framework":[94],"designed":[95],"inherent":[99],"heterogeneity":[100],"diffusion-based":[102],"masked":[103],"video-to-video":[104],"(MV2V)":[105],"generation":[106],"editing.":[108],"Instead":[109],"of":[110,128],"uniformly":[111],"reuse":[112],"or":[113],"randomly":[114],"sampling":[115],"tokens,":[116,150],"HetCache":[117,184],"assesses":[118],"contextual":[120],"relevance":[121],"interaction":[123],"strength":[124],"among":[125],"various":[126],"types":[127],"designated":[131],"computing":[132],"steps.":[133],"Guided":[134],"by":[135],"spatial":[136],"priors,":[137],"it":[138],"divides":[139],"spatial-temporal":[141],"into":[146],"context":[147,155],"generative":[149,167],"selectively":[152],"caches":[153],"exhibit":[158],"strongest":[160],"correlation":[161],"most":[163],"representative":[164],"semantics":[165],"with":[166,202],"ones.":[168],"strategy":[170],"reduces":[171],"redundant":[172],"while":[175],"maintaining":[176],"consistency":[178],"fidelity.":[180],"Experiments":[181],"show":[182],"achieves":[185],"noticeable":[187],"acceleration,":[188],"including":[189],"2.67$\\times$":[191],"latency":[192],"speedup":[193],"FLOPs":[195],"reduction":[196],"commonly":[198],"used":[199],"foundation":[200],"models,":[201],"negligible":[203],"degradation":[204],"quality.":[207]},"counts_by_year":[],"updated_date":"2026-03-27T06:05:27.210665","created_date":"2026-03-27T00:00:00"}
