{"id":"https://openalex.org/W4403791695","doi":"https://doi.org/10.1145/3664647.3681026","title":"Collaborative Training of Tiny-Large Vision Language Models","display_name":"Collaborative Training of Tiny-Large Vision Language Models","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791695","doi":"https://doi.org/10.1145/3664647.3681026"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681026","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5062965702","display_name":"Shichen Lu","orcid":"https://orcid.org/0000-0002-1272-8723"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shichen Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040424302","display_name":"Longteng Guo","orcid":"https://orcid.org/0000-0002-4340-4000"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longteng Guo","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755188","display_name":"Wenxuan Wang","orcid":"https://orcid.org/0000-0002-9022-1370"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014609545","display_name":"Zijia Zhao","orcid":"https://orcid.org/0009-0000-7781-932X"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijia Zhao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101322148","display_name":"Tongtian Yue","orcid":"https://orcid.org/0000-0001-5774-4084"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongtian Yue","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108392430","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-0903-9131"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences & School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences & School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5062965702"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.2493,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54541563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4928","last_page":"4937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9979000091552734,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9914000034332275,"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":0.7237930297851562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7133450508117676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4728805422782898},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39006417989730835},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3533262014389038},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08748093247413635}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7237930297851562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7133450508117676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4728805422782898},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39006417989730835},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3533262014389038},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08748093247413635},{"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:10.1145/3664647.3681026","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2419501139","https://openalex.org/W2560730294","https://openalex.org/W2886641317","https://openalex.org/W2970231061","https://openalex.org/W3008374555","https://openalex.org/W3034368386","https://openalex.org/W3090449556","https://openalex.org/W3138154797","https://openalex.org/W3138516171","https://openalex.org/W3176641147","https://openalex.org/W4212774754","https://openalex.org/W4372311908","https://openalex.org/W4375843773","https://openalex.org/W4386076222","https://openalex.org/W4393054068","https://openalex.org/W4393149524","https://openalex.org/W4399766943","https://openalex.org/W4400258016","https://openalex.org/W4402753756","https://openalex.org/W4402754198"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recently,":[0],"large":[1,46,76,100,122,131],"vision":[2],"language":[3],"models":[4,49,79,123,143],"(LVLMs)":[5],"have":[6,50],"advanced":[7],"AI":[8],"by":[9,95],"integrating":[10],"visual":[11,18,23],"and":[12,22,47,53,77,84,101,150],"linguistic":[13],"data":[14],"for":[15,34,39],"tasks":[16],"like":[17],"conversation,":[19],"image":[20],"captioning,":[21],"question":[24],"answering.":[25],"Current":[26],"LVLM":[27],"research":[28],"either":[29],"scales":[30],"up":[31],"model":[32],"size":[33],"performance":[35],"or":[36],"reduces":[37],"parameters":[38],"limited":[40],"computational":[41,148],"resources.":[42],"We":[43,63],"believe":[44],"both":[45],"tiny":[48,78,102,109,136],"unique":[51],"strengths":[52],"that":[54],"collaborative":[55,140],"training":[56,88,93],"yields":[57],"better":[58,124],"results":[59],"than":[60],"independent":[61],"training.":[62],"propose":[64],"Collaborative":[65],"Training":[66],"of":[67,108],"Tiny-Large":[68],"Vision":[69],"Language":[70],"Models":[71],"(CTVLMs),":[72],"a":[73,81,86],"framework":[74,91],"connecting":[75],"via":[80],"projection":[82],"layer":[83],"leveraging":[85],"synergistic":[87],"strategy.":[89],"Our":[90],"improves":[92],"efficiency":[94,107],"strengthening":[96],"the":[97,105,130],"interconnection":[98],"between":[99],"models.":[103],"Using":[104],"parameter":[106],"models,":[110],"we":[111],"effectively":[112],"align":[113,125],"image-text":[114],"features,":[115],"then":[116],"apply":[117],"knowledge":[118,134],"distillation":[119],"to":[120,144,146],"help":[121],"cross-modal":[126],"information.":[127],"During":[128],"fine-tuning,":[129],"model's":[132,137],"extensive":[133],"enhances":[135],"performance.":[138],"This":[139],"approach":[141],"allows":[142],"adapt":[145],"various":[147],"resources":[149],"outperforms":[151],"existing":[152],"methods":[153],"in":[154],"vision-language":[155],"tasks.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}