{"id":"https://openalex.org/W4417241963","doi":"https://doi.org/10.1145/3760250.3762216","title":"Dynamic Sparsity in Large-Scale Video DiT Training","display_name":"Dynamic Sparsity in Large-Scale Video DiT Training","publication_year":2025,"publication_date":"2025-12-11","ids":{"openalex":"https://openalex.org/W4417241963","doi":"https://doi.org/10.1145/3760250.3762216"},"language":null,"primary_location":{"id":"doi:10.1145/3760250.3762216","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3760250.3762216","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 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3760250.3762216","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101037058","display_name":"Xin Tan","orcid":"https://orcid.org/0000-0003-3785-9700"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Xin Tan","raw_affiliation_strings":["Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103025161","display_name":"Yuetao Chen","orcid":"https://orcid.org/0009-0008-3818-4753"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuetao Chen","raw_affiliation_strings":["Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079353641","display_name":"Yimin Jiang","orcid":"https://orcid.org/0009-0001-0049-873X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yimin Jiang","raw_affiliation_strings":["Independent, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Independent, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040999083","display_name":"Xing Chen","orcid":"https://orcid.org/0000-0002-6453-5026"},"institutions":[{"id":"https://openalex.org/I4210140476","display_name":"Shanghai Zhaozhan Metal Materials","ror":"https://ror.org/03wtw1749","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210140476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Chen","raw_affiliation_strings":["StepFun, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"StepFun, Shanghai, China","institution_ids":["https://openalex.org/I4210140476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042318272","display_name":"Kun Yan","orcid":"https://orcid.org/0000-0001-8290-5169"},"institutions":[{"id":"https://openalex.org/I4210140476","display_name":"Shanghai Zhaozhan Metal Materials","ror":"https://ror.org/03wtw1749","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210140476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Yan","raw_affiliation_strings":["StepFun, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"StepFun, Shanghai, China","institution_ids":["https://openalex.org/I4210140476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042018181","display_name":"Nan Duan","orcid":"https://orcid.org/0000-0002-3387-4674"},"institutions":[{"id":"https://openalex.org/I4210140476","display_name":"Shanghai Zhaozhan Metal Materials","ror":"https://ror.org/03wtw1749","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210140476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Duan","raw_affiliation_strings":["StepFun, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"StepFun, Shanghai, China","institution_ids":["https://openalex.org/I4210140476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028120333","display_name":"Yibo Zhu","orcid":"https://orcid.org/0000-0002-9113-2660"},"institutions":[{"id":"https://openalex.org/I4210140476","display_name":"Shanghai Zhaozhan Metal Materials","ror":"https://ror.org/03wtw1749","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210140476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibo Zhu","raw_affiliation_strings":["StepFun, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"StepFun, Shanghai, China","institution_ids":["https://openalex.org/I4210140476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060116992","display_name":"Daxin Jiang","orcid":"https://orcid.org/0000-0002-6657-5806"},"institutions":[{"id":"https://openalex.org/I4210140476","display_name":"Shanghai Zhaozhan Metal Materials","ror":"https://ror.org/03wtw1749","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210140476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daxin Jiang","raw_affiliation_strings":["StepFun, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"StepFun, Shanghai, China","institution_ids":["https://openalex.org/I4210140476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022420830","display_name":"Hong Xu","orcid":"https://orcid.org/0000-0002-9359-9571"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hong Xu","raw_affiliation_strings":["Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101037058"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40003257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.2687999904155731,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.2687999904155731,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11996","display_name":"Random lasers and scattering media","score":0.14830000698566437,"subfield":{"id":"https://openalex.org/subfields/3102","display_name":"Acoustics and Ultrasonics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.1128000020980835,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/bottleneck","display_name":"Bottleneck","score":0.6715999841690063},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5414000153541565},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5105000138282776},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.49729999899864197},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.33070001006126404},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.2953999936580658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7014999985694885},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6715999841690063},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.49729999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.435699999332428},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.35670000314712524},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3343000113964081},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25859999656677246},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3760250.3762216","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3760250.3762216","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 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3760250.3762216","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3760250.3762216","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 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4386768656","https://openalex.org/W4402660110","https://openalex.org/W4412944812"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"Transformers":[1],"(DiTs)":[2],"have":[3],"shown":[4],"remarkable":[5],"performance":[6],"in":[7,22],"generating":[8],"high-quality":[9],"videos.":[10],"However,":[11],"the":[12],"quadratic":[13],"complexity":[14],"of":[15,38],"3D":[16],"full":[17],"attention":[18],"remains":[19],"a":[20],"bottleneck":[21],"scaling":[23],"DiT":[24],"training,":[25],"especially":[26],"with":[27],"high-definition,":[28],"lengthy":[29],"videos,":[30],"where":[31],"it":[32],"can":[33],"consume":[34],"up":[35],"to":[36],"95%":[37],"processing":[39],"time":[40],"and":[41],"demand":[42],"specialized":[43],"context":[44],"parallelism.":[45]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-11T00:00:00"}
