{"id":"https://openalex.org/W7124434768","doi":"https://doi.org/10.1109/tpami.2026.3654201","title":"DyDiT++: Diffusion Transformers With Timestep and Spatial Dynamics for Efficient Visual Generation","display_name":"DyDiT++: Diffusion Transformers With Timestep and Spatial Dynamics for Efficient Visual Generation","publication_year":2026,"publication_date":"2026-01-15","ids":{"openalex":"https://openalex.org/W7124434768","doi":"https://doi.org/10.1109/tpami.2026.3654201","pmid":"https://pubmed.ncbi.nlm.nih.gov/41538341"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3654201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3654201","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5081255558","display_name":"Wangbo Zhao","orcid":"https://orcid.org/0000-0001-9545-7991"},"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":"Wangbo Zhao","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9545-7991","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045569962","display_name":"Yizeng Han","orcid":"https://orcid.org/0000-0001-5706-8784"},"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":"Yizeng Han","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5706-8784","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123215159","display_name":"Jiasheng Tang","orcid":null},"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":"Jiasheng Tang","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-9154-8615","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123219423","display_name":"Kai Wang","orcid":null},"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":"Kai Wang","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123174934","display_name":"Hao Luo","orcid":null},"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":"Hao Luo","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6405-4011","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123233852","display_name":"Yibing Song","orcid":null},"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":"Yibing Song","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3667-531X","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013240918","display_name":"Gao Huang","orcid":"https://orcid.org/0000-0002-7251-0988"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao Huang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7251-0988","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fan Wang","orcid":"https://orcid.org/0000-0001-7320-1119"},"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":"Fan Wang","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7320-1119","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123215032","display_name":"Yang You","orcid":null},"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":"Yang You","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-2816-4384","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.06292445,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"5","first_page":"5755","last_page":"5773"},"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":0.8698999881744385,"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":0.8698999881744385,"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":0.030500000342726707,"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":0.014600000344216824,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7537999749183655},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.6129999756813049},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6086999773979187},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5519000291824341},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5123000144958496},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5016000270843506}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800599992275238},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7537999749183655},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.6129999756813049},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6086999773979187},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5519000291824341},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5016000270843506},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.49869999289512634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.426800012588501},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.413100004196167},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2603999972343445},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25859999656677246},{"id":"https://openalex.org/C2781323245","wikidata":"https://www.wikidata.org/wiki/Q1363761","display_name":"Hang","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3654201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3654201","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41538341","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41538341","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1901129140","https://openalex.org/W2108598243","https://openalex.org/W2760103357","https://openalex.org/W2962677625","https://openalex.org/W2963363373","https://openalex.org/W2963393494","https://openalex.org/W2963736817","https://openalex.org/W2964318715","https://openalex.org/W3035424951","https://openalex.org/W3100148727","https://openalex.org/W3173563887","https://openalex.org/W3204647170","https://openalex.org/W4229944339","https://openalex.org/W4297697565","https://openalex.org/W4312290555","https://openalex.org/W4312429345","https://openalex.org/W4312933868","https://openalex.org/W4385245566","https://openalex.org/W4385801014","https://openalex.org/W4386047807","https://openalex.org/W4386065404","https://openalex.org/W4386065704","https://openalex.org/W4386071831","https://openalex.org/W4390872006","https://openalex.org/W4390872066","https://openalex.org/W4390872297","https://openalex.org/W4390873054","https://openalex.org/W4390874074","https://openalex.org/W4393148714","https://openalex.org/W4395481535","https://openalex.org/W4400445270","https://openalex.org/W4402716016","https://openalex.org/W4402778510","https://openalex.org/W4402916399","https://openalex.org/W4403840763","https://openalex.org/W4403843325","https://openalex.org/W4407450948","https://openalex.org/W4411528087","https://openalex.org/W4413157503","https://openalex.org/W4413157724","https://openalex.org/W7133233455","https://openalex.org/W7133233895"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0,52],"Transformer":[1,53],"(DiT),":[2],"an":[3,55,125],"emerging":[4],"diffusion":[5,40,144],"model":[6,79],"for":[7],"visual":[8,168,216],"generation,":[9,156,176],"has":[10],"demonstrated":[11],"superior":[12],"performance":[13],"but":[14],"suffers":[15],"from":[16,28],"substantial":[17],"computational":[18],"costs.":[19],"Our":[20],"investigations":[21],"reveal":[22],"that":[23,57,77,149],"these":[24,121],"costs":[25],"primarily":[26],"stem":[27],"the":[29,83,116,138,185,197,226,240],"static":[30],"inference":[31],"paradigm,":[32],"which":[33],"inevitably":[34],"introduces":[35],"redundant":[36,98],"computation":[37,61,99],"in":[38,131,202],"certain":[39],"timesteps":[41],"and":[42,65,105,113,174,191,206,223,252],"spatial":[43,66,102],"regions.":[44],"To":[45],"overcome":[46],"this":[47],"inefficiency,":[48],"we":[49,69,88,123,161,195],"propose":[50],"Dynamic":[51,73,92],"(DyDiT),":[54],"architecture":[56],"dynamically":[58],"adjusts":[59],"its":[60,158,179],"along":[62],"both":[63],"timestep":[64],"dimensions.":[67],"Specifically,":[68],"introduce":[70,207],"a":[71,90,203,254],"Timestep-wise":[72],"Width":[74],"(TDW)":[75],"approach":[76,238],"adapts":[78],"width":[80],"conditioned":[81],"on":[82,120,214,250,260],"generation":[84,117,139,169,173,217],"timesteps.":[85],"In":[86],"addition,":[87],"design":[89],"Spatial-wise":[91],"Token":[93],"(SDT)":[94],"strategy":[95],"to":[96,145,164,183],"avoid":[97],"at":[100],"unnecessary":[101],"locations.":[103],"TDW":[104],"SDT":[106],"can":[107,152],"be":[108],"seamlessly":[109],"integrated":[110],"into":[111],"DiT":[112],"significantly":[114],"accelerate":[115,154],"process.":[118],"Building":[119],"designs,":[122],"present":[124],"extended":[126],"version,":[127],"DyDiT++,":[128],"with":[129,231],"improvements":[130],"three":[132],"key":[133],"aspects.":[134],"First,":[135],"it":[136],"extends":[137],"mechanism":[140],"of":[141,188,199,228,242,258],"DyDiT":[142,163,201],"beyond":[143],"flow":[146],"matching,":[147],"demonstrating":[148],"our":[150,237],"method":[151],"also":[153],"flow-matching-based":[155],"enhancing":[157],"versatility.":[159],"Furthermore,":[160],"enhance":[162],"tackle":[165],"more":[166],"complex":[167],"tasks,":[170],"including":[171,219],"video":[172],"text-to-image":[175],"thereby":[177],"broadening":[178],"real-world":[180],"applications.":[181],"Finally,":[182],"address":[184],"high":[186],"cost":[187],"full":[189],"fine-tuning":[190,235],"democratize":[192],"technology":[193],"access,":[194],"investigate":[196],"feasibility":[198],"training":[200],"parameter-efficient":[204],"manner":[205],"timestep-based":[208],"dynamic":[209],"LoRA":[210],"(TD-LoRA).":[211],"Extensive":[212],"experiments":[213],"diverse":[215],"models,":[218],"DiT,":[220],"SiT,":[221],"Latte,":[222],"FLUX,":[224],"demonstrate":[225],"effectiveness":[227],"DyDiT++.":[229],"Remarkably,":[230],"$<":[232],"$<3%":[233],"additional":[234],"iterations,":[236],"reduces":[239],"FLOPs":[241],"DiT-XL":[243],"by":[244],"51%,":[245],"yielding":[246],"1.73\u00d7":[247],"realistic":[248],"speedup":[249],"hardware,":[251],"achieves":[253],"competitive":[255],"FID":[256],"score":[257],"2.07":[259],"ImageNet.":[261]},"counts_by_year":[],"updated_date":"2026-05-13T06:04:23.736269","created_date":"2026-01-17T00:00:00"}