{"id":"https://openalex.org/W7134986434","doi":"https://doi.org/10.1145/3779212.3790154","title":"DIP: Efficient Large Multimodal Model Training with Dynamic Interleaved Pipeline","display_name":"DIP: Efficient Large Multimodal Model Training with Dynamic Interleaved Pipeline","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134986434","doi":"https://doi.org/10.1145/3779212.3790154"},"language":null,"primary_location":{"id":"doi:10.1145/3779212.3790154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790154","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 2","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3779212.3790154","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128715357","display_name":"Zhenliang Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenliang Xue","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128726902","display_name":"Hanpeng Hu","orcid":null},"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":"Hanpeng Hu","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/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/A5079353641","display_name":"Yimin Jiang","orcid":"https://orcid.org/0009-0001-0049-873X"},"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":"Yimin Jiang","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/A5081084638","display_name":"Yixin Song","orcid":"https://orcid.org/0009-0001-4605-7382"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Song","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051857167","display_name":"Zeyu Mi","orcid":"https://orcid.org/0000-0001-8395-1319"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Mi","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"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/A5128741473","display_name":"Daxin Jiang","orcid":null},"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":"middle","author":{"id":null,"display_name":"Yubin Xia","orcid":"https://orcid.org/0000-0001-6558-5298"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yubin Xia","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":null,"display_name":"Haibo Chen","orcid":"https://orcid.org/0000-0002-9720-0361"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Chen","raw_affiliation_strings":["Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5128715357"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60535932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"618","last_page":"632"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.2578999996185303,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.2578999996185303,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.07660000026226044,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07249999791383743,"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/training","display_name":"Training (meteorology)","score":0.7946000099182129},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7592999935150146},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.438400000333786},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.3564000129699707},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.34439998865127563}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7946000099182129},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7592999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7567999958992004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.491100013256073},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3779212.3790154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790154","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 2","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.14145","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.14145","pdf_url":"https://arxiv.org/pdf/2504.14145","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3779212.3790154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3779212.3790154","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 2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.45223337411880493,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8819344089","display_name":null,"funder_award_id":"U24A2023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1993814189","https://openalex.org/W2425121537","https://openalex.org/W3206832494","https://openalex.org/W4252345548","https://openalex.org/W4384705353","https://openalex.org/W4386348101","https://openalex.org/W4394923298","https://openalex.org/W4398796293","https://openalex.org/W4407197044","https://openalex.org/W4408893341","https://openalex.org/W4415798317"],"related_works":[],"abstract_inverted_index":{"Large":[0],"multimodal":[1,52],"models":[2,19],"(LMMs)":[3],"have":[4],"demonstrated":[5],"excellent":[6],"capabilities":[7],"in":[8],"both":[9],"understanding":[10],"and":[11,43],"generation":[12],"tasks":[13],"with":[14],"various":[15],"modalities.":[16],"While":[17],"these":[18],"can":[20],"accept":[21],"flexible":[22],"combinations":[23],"of":[24,51],"input":[25],"data,":[26],"their":[27],"training":[28,44],"efficiency":[29],"suffers":[30],"from":[31,48],"two":[32],"major":[33],"issues:":[34],"pipeline":[35],"stage":[36],"imbalance":[37],"caused":[38],"by":[39],"heterogeneous":[40],"model":[41],"architectures,":[42],"data":[45],"dynamicity":[46],"stemming":[47],"the":[49],"diversity":[50],"data.":[53]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2026-03-12T00:00:00"}