{"id":"https://openalex.org/W7137978004","doi":"https://doi.org/10.1609/aaai.v40i12.37976","title":"PipeDiT: Accelerating Diffusion Transformers in Video Generation with Task Pipelining and Model Decoupling","display_name":"PipeDiT: Accelerating Diffusion Transformers in Video Generation with Task Pipelining and Model Decoupling","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137978004","doi":"https://doi.org/10.1609/aaai.v40i12.37976"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i12.37976","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37976","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37976/41938","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37976/41938","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100712619","display_name":"Sijie Wang","orcid":"https://orcid.org/0000-0002-2912-0773"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sijie Wang","raw_affiliation_strings":["Harbin Institute of Technology\uff0cShenzhen"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology\uff0cShenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129677129","display_name":"Qiang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["Harbin Institute of Technology\uff0cShenzhen"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology\uff0cShenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016836702","display_name":"Shaohuai Shi","orcid":"https://orcid.org/0000-0002-1418-5160"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohuai Shi","raw_affiliation_strings":["Harbin Institute of Technology\uff0cShenzhen"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology\uff0cShenzhen","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100712619"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24328358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"12","first_page":"10092","last_page":"10100"},"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":0.6958000063896179,"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":0.6958000063896179,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.04349999874830246,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.02160000056028366,"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/inference","display_name":"Inference","score":0.637499988079071},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5442000031471252},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5404999852180481},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5350000262260437},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.4404999911785126},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.39730000495910645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8895000219345093},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.637499988079071},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5442000031471252},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5404999852180481},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5350000262260437},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49470001459121704},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34599998593330383},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33410000801086426},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2994999885559082},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2535000145435333},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i12.37976","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37976","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37976/41938","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i12.37976","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37976","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37976/41938","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.597317099571228}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137978004.pdf","grobid_xml":"https://content.openalex.org/works/W7137978004.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"generation":[1,70,139,154],"has":[2],"been":[3],"advancing":[4],"rapidly,":[5],"and":[6,27,71,93,112,148,156,172,184],"diffusion":[7,91],"transformer":[8],"(DiT)":[9],"based":[10],"models":[11],"have":[12],"demonstrated":[13],"remarkable":[14],"capabilities.":[15],"However,":[16],"their":[17],"practical":[18],"deployment":[19],"is":[20,47],"often":[21],"hindered":[22],"by":[23],"slow":[24],"inference":[25,82,113],"speeds":[26],"high":[28],"memory":[29,110],"consumption.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,54,85,126],"propose":[35,86,127],"a":[36,56],"novel":[37],"pipelining":[38,57],"framework":[39],"named":[40],"PipeDiT":[41,144,176],"to":[42,64,76,88,107,116,133,179],"accelerate":[43],"video":[44,138,153],"generation,":[45],"which":[46],"equipped":[48],"with":[49],"three":[50],"main":[51],"innovations.":[52],"First,":[53],"design":[55],"algorithm":[58],"(PipeSP)":[59],"for":[60],"sequence":[61],"parallelism":[62],"(SP)":[63],"enable":[65],"the":[66,81,90,94,109,119,123,136],"computation":[67],"of":[68],"latent":[69],"communication":[72],"among":[73],"multiple":[74],"GPUs":[75],"be":[77,105],"pipelined,":[78],"thus":[79],"reducing":[80],"latency.":[83,114,140],"Second,":[84],"DeDiVAE":[87],"decouple":[89],"module":[92,96],"VAE":[95,124],"into":[97,145],"two":[98,150,161],"GPU":[99,120],"groups":[100],"whose":[101],"executions":[102],"can":[103],"also":[104],"pipelined":[106],"reduce":[108,135],"consumption":[111],"Third,":[115],"better":[117],"utilize":[118],"resources":[121],"in":[122],"group,":[125],"an":[128],"attention":[129],"co-processing":[130],"(Aco)":[131],"method":[132],"further":[134],"overall":[137],"We":[141],"integrate":[142],"our":[143,175],"both":[146],"OpenSoraPlan":[147,183],"HunyuanVideo,":[149],"state-of-the-art":[151],"open-source":[152],"frameworks,":[155],"conduct":[157],"extensive":[158],"experiments":[159],"on":[160],"8-GPU":[162],"systems.":[163],"Experimental":[164],"results":[165],"show":[166],"that,":[167],"under":[168],"many":[169],"common":[170],"resolution":[171],"timestep":[173],"configurations,":[174],"achieves":[177],"1.06\u00d7":[178],"4.02\u00d7":[180],"speedups":[181],"over":[182],"HunyuanVideo.":[185]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}