{"id":"https://openalex.org/W4413757119","doi":"https://doi.org/10.1145/3718958.3750472","title":"DistTrain: Addressing Model and Data Heterogeneity with Disaggregated Training for Multimodal Large Language Models","display_name":"DistTrain: Addressing Model and Data Heterogeneity with Disaggregated Training for Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-08-27","ids":{"openalex":"https://openalex.org/W4413757119","doi":"https://doi.org/10.1145/3718958.3750472"},"language":"en","primary_location":{"id":"doi:10.1145/3718958.3750472","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3718958.3750472","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3718958.3750472","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGCOMM 2025 Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3718958.3750472","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100603108","display_name":"Zili Zhang","orcid":"https://orcid.org/0000-0003-4209-9451"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zili Zhang","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4209-9451","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000644890","display_name":"Yinmin Zhong","orcid":"https://orcid.org/0000-0002-2504-7652"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinmin Zhong","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2504-7652","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"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 Researcher, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-0049-873X","affiliations":[{"raw_affiliation_string":"Independent Researcher, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095776670","display_name":"Hanpeng Hu","orcid":"https://orcid.org/0009-0008-5787-5226"},"institutions":[{"id":"https://openalex.org/I3019120426","display_name":"China Iron and Steel Research Institute Group","ror":"https://ror.org/02e42hc22","country_code":"CN","type":"facility","lineage":["https://openalex.org/I3019120426"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanpeng Hu","raw_affiliation_strings":["StepFun, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-5787-5226","affiliations":[{"raw_affiliation_string":"StepFun, Beijing, China","institution_ids":["https://openalex.org/I3019120426"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407569","display_name":"Jianjian Sun","orcid":"https://orcid.org/0000-0002-1216-9626"},"institutions":[{"id":"https://openalex.org/I3019120426","display_name":"China Iron and Steel Research Institute Group","ror":"https://ror.org/02e42hc22","country_code":"CN","type":"facility","lineage":["https://openalex.org/I3019120426"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianjian Sun","raw_affiliation_strings":["StepFun, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1216-9626","affiliations":[{"raw_affiliation_string":"StepFun, Beijing, China","institution_ids":["https://openalex.org/I3019120426"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106405555","display_name":"Zheng Ge","orcid":"https://orcid.org/0000-0002-8630-8270"},"institutions":[{"id":"https://openalex.org/I3019120426","display_name":"China Iron and Steel Research Institute Group","ror":"https://ror.org/02e42hc22","country_code":"CN","type":"facility","lineage":["https://openalex.org/I3019120426"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Ge","raw_affiliation_strings":["StepFun, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8630-8270","affiliations":[{"raw_affiliation_string":"StepFun, Beijing, China","institution_ids":["https://openalex.org/I3019120426"]}]},{"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/I3019120426","display_name":"China Iron and Steel Research Institute Group","ror":"https://ror.org/02e42hc22","country_code":"CN","type":"facility","lineage":["https://openalex.org/I3019120426"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibo Zhu","raw_affiliation_strings":["StepFun, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9113-2660","affiliations":[{"raw_affiliation_string":"StepFun, Beijing, China","institution_ids":["https://openalex.org/I3019120426"]}]},{"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/I3019120426","display_name":"China Iron and Steel Research Institute Group","ror":"https://ror.org/02e42hc22","country_code":"CN","type":"facility","lineage":["https://openalex.org/I3019120426"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daxin Jiang","raw_affiliation_strings":["StepFun, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6657-5806","affiliations":[{"raw_affiliation_string":"StepFun, Beijing, China","institution_ids":["https://openalex.org/I3019120426"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101882004","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0001-8741-5847"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8741-5847","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100603108"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":8.693,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97459698,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9925000071525574,"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/computer-science","display_name":"Computer science","score":0.7310000658035278},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.5154748558998108},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4654366075992584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4448928236961365},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.41480278968811035},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40838873386383057},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.11856046319007874},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09711676836013794}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7310000658035278},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5154748558998108},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4654366075992584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4448928236961365},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.41480278968811035},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40838873386383057},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.11856046319007874},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09711676836013794},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3718958.3750472","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3718958.3750472","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3718958.3750472","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGCOMM 2025 Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3718958.3750472","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3718958.3750472","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3718958.3750472","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGCOMM 2025 Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4497957390","display_name":null,"funder_award_id":"62172008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7732961354","display_name":null,"funder_award_id":"2022YFB4500700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413757119.pdf","grobid_xml":"https://content.openalex.org/works/W4413757119.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W2883830791","https://openalex.org/W3101104221","https://openalex.org/W3188065709","https://openalex.org/W3204998121","https://openalex.org/W4232611972","https://openalex.org/W4249502209","https://openalex.org/W4287083215","https://openalex.org/W4312933868","https://openalex.org/W4381786045","https://openalex.org/W4386768656","https://openalex.org/W4388182168","https://openalex.org/W4411055324"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W4412817058","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"empower":[5],"LLMs":[6],"to":[7],"ingest":[8],"inputs":[9],"and":[10,20,34],"generate":[11],"outputs":[12],"in":[13,30],"multiple":[14,26],"forms,":[15],"such":[16],"as":[17],"text,":[18],"image,":[19],"audio.":[21],"However,":[22],"the":[23,32],"integration":[24],"of":[25],"modalities":[27],"introduces":[28],"heterogeneity":[29],"both":[31],"model":[33],"training":[35],"data,":[36],"creating":[37],"unique":[38],"systems":[39],"challenges.":[40]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}