{"id":"https://openalex.org/W4415535483","doi":"https://doi.org/10.1145/3746027.3762242","title":"Large Generative Models Meet Multimodal Applications (LGM <sup>3</sup> A)","display_name":"Large Generative Models Meet Multimodal Applications (LGM <sup>3</sup> A)","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415535483","doi":"https://doi.org/10.1145/3746027.3762242"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100401111","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0002-7064-6267"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["Huawei Technologies, Co., Ltd., Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7064-6267","affiliations":[{"raw_affiliation_string":"Huawei Technologies, Co., Ltd., Singapore, Singapore","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qianqian Chen","orcid":"https://orcid.org/0000-0003-0801-3378"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qianqian Chen","raw_affiliation_strings":["Huawei Technologies, Co., Ltd., Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-0801-3378","affiliations":[{"raw_affiliation_string":"Huawei Technologies, Co., Ltd., Singapore, Singapore","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015188473","display_name":"Yiyang Luo","orcid":"https://orcid.org/0000-0002-8542-9054"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yiyang Luo","raw_affiliation_strings":["Huawei Technologies, Co., Ltd., Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-8542-9054","affiliations":[{"raw_affiliation_string":"Huawei Technologies, Co., Ltd., Singapore, Singapore","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078226742","display_name":"Zhiqiu Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhiqiu Ye","raw_affiliation_strings":["Huawei Technologies, Co., Ltd., Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0006-0817-6184","affiliations":[{"raw_affiliation_string":"Huawei Technologies, Co., Ltd., Singapore, Singapore","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110364786","display_name":"Wei Shi","orcid":"https://orcid.org/0009-0003-0208-6012"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shi Wei","raw_affiliation_strings":["Huawei Technologies, Co., Ltd., Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0003-0208-6012","affiliations":[{"raw_affiliation_string":"Huawei Technologies, Co., Ltd., Singapore, Singapore","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7374-8739","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"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":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6097-7807","affiliations":[{"raw_affiliation_string":"National University of Singapore, 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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14320","last_page":"14322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.195700004696846,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.195700004696846,"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/T12031","display_name":"Speech and dialogue systems","score":0.17479999363422394,"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/generative-grammar","display_name":"Generative grammar","score":0.7684000134468079},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5408999919891357},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44830000400543213},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41690000891685486},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4099000096321106},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.36399999260902405},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.36329999566078186}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7684000134468079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6549000144004822},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5408999919891357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48890000581741333},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44830000400543213},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.36399999260902405},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.295199990272522},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.25859999656677246},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3762242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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":2,"referenced_works":["https://openalex.org/W4388187146","https://openalex.org/W4403781510"],"related_works":[],"abstract_inverted_index":{"This":[0,195],"workshop":[1,196,241,269],"aims":[2],"to":[3,11,33,105,148,154,190,207,234,276],"explore":[4,208],"the":[5,13,75,86,100,209,216,229,235,247,268],"potential":[6,285],"of":[7,29,102,218,221,237,251],"large":[8,192,222,253],"generative":[9,193,223],"models":[10,53,255],"revolutionize":[12],"way":[14],"we":[15],"interact":[16],"with":[17,131,151,256],"multimodal":[18,78,107,159,219],"information.":[19],"A":[20],"Large":[21,89],"Language":[22],"Model":[23],"(LLM)":[24],"represents":[25],"a":[26,156,272],"sophisticated":[27],"form":[28],"artificial":[30],"intelligence":[31],"engineered":[32],"comprehend":[34],"and":[35,49,70,83,133,139,161,172,181,204,212,249,264,283],"produce":[36],"natural":[37],"language":[38,65,254],"text,":[39],"exemplified":[40],"by":[41,165],"technologies":[42,259],"such":[43,238,260],"as":[44,111,191,261],"GPT,":[45],"LLaMA,":[46],"Flan-T5,":[47],"ChatGLM,":[48],"Qwen,":[50],"etc.":[51,120],"These":[52,97],"undergo":[54],"training":[55],"on":[56,136,141,245],"extensive":[57],"text":[58,180],"datasets,":[59],"exhibiting":[60],"commendable":[61],"attributes":[62],"including":[63],"robust":[64],"generation,":[66,138],"zeroshot":[67],"transfer":[68],"capabilities,":[69],"In-Context":[71],"Learning":[72],"(ICL).":[73],"With":[74],"surge":[76],"in":[77,113,215],"content-encompassing":[79],"images,":[80],"videos,":[81],"audio,":[82],"3D":[84],"models-over":[85],"recent":[87],"period,":[88],"MultiModal":[90],"Models":[91],"(LMMs)":[92],"have":[93,125],"seen":[94,112],"significant":[95],"enhancements.":[96],"improvements":[98],"enable":[99],"augmentation":[101],"conventional":[103],"LLMs":[104,150],"accommodate":[106],"inputs":[108],"or":[109],"outputs,":[110],"BLIP,":[114],"Flamingo,":[115],"KOSMOS,":[116],"LLaVA,":[117],"Gemini,":[118],"GPT-4,":[119],"Concurrently,":[121],"certain":[122],"research":[123],"initiatives":[124],"delved":[126],"into":[127],"generating":[128],"specific":[129],"modalities,":[130,187],"Kosmos2":[132],"MiniGPT-5":[134],"focusing":[135],"image":[137,182],"SpeechGPT":[140],"speech":[142,265],"production.":[143],"There":[144],"are":[145,188,231],"also":[146,185,226,243],"endeavors":[147],"integrate":[149],"external":[152],"tools":[153],"achieve":[155],"near":[157],"'any-to-any'":[158],"comprehension":[160],"generation":[162,183],"capacity,":[163],"illustrated":[164],"projects":[166],"like":[167],"Visual-ChatGPT,":[168],"ViperGPT,":[169],"MMREACT,":[170],"HuggingGPT,":[171],"AudioGPT.":[173],"Collectively,":[174],"these":[175],"models,":[176],"spanning":[177],"not":[178,232],"only":[179],"but":[184],"other":[186,257],"referred":[189],"models.":[194,224,239],"will":[197,242,270],"provide":[198,271],"an":[199],"opportunity":[200],"for":[201,274],"researchers,":[202],"practitioners,":[203],"industry":[205],"professionals":[206],"latest":[210],"trends":[211],"best":[213],"practices":[214],"field":[217],"applications":[220],"We":[225],"remark":[227],"that":[228],"submissions":[230],"limited":[233],"use":[236],"The":[240],"focus":[244],"exploring":[246],"challenges":[248],"opportunities":[250],"integrating":[252],"AI":[258],"computer":[262],"vision":[263],"recognition.":[266],"Additionally,":[267],"platform":[273],"participants":[275],"present":[277],"their":[278,281],"research,":[279],"share":[280],"experiences,":[282],"discuss":[284],"collaborations.":[286]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}