{"id":"https://openalex.org/W7125942996","doi":"https://doi.org/10.1109/smc58881.2025.11342688","title":"On the Taxonomy, Tasks, and Open-Challenges for Multimodal Large Language Models","display_name":"On the Taxonomy, Tasks, and Open-Challenges for Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125942996","doi":"https://doi.org/10.1109/smc58881.2025.11342688"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":null,"display_name":"Lecheng Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lecheng Yan","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101525635","display_name":"Ruizhe Li","orcid":"https://orcid.org/0000-0003-4697-8947"},"institutions":[{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ruizhe Li","raw_affiliation_strings":["University of Aberdeen,Aberdeen,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Aberdeen,Aberdeen,United Kingdom","institution_ids":["https://openalex.org/I195460627"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124071340","display_name":"Jiahui Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Jiahui Geng","raw_affiliation_strings":["MBZUAI,Abu Dhabi,United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MBZUAI,Abu Dhabi,United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049102542","display_name":"Qing Li","orcid":"https://orcid.org/0000-0001-8249-7791"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["MBZUAI,Abu Dhabi,United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MBZUAI,Abu Dhabi,United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032003031","display_name":"Minghao Wu","orcid":"https://orcid.org/0000-0002-5717-9318"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Minghao Wu","raw_affiliation_strings":["Monash University,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,Melbourne,Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124142179","display_name":"Zhanyu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhanyu Wang","raw_affiliation_strings":["University of Sydney,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122927726","display_name":"Wenxi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxi Li","raw_affiliation_strings":["Tsinghua University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071808662","display_name":"Tianbo Ji","orcid":"https://orcid.org/0000-0003-0143-6220"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianbo Ji","raw_affiliation_strings":["Nantong University,Nantong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nantong University,Nantong,China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072497955","display_name":"Shaochen Jiang","orcid":"https://orcid.org/0000-0002-7896-1026"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaochen Jiang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093130749","display_name":"Chenyang Lyu","orcid":"https://orcid.org/0009-0002-6733-5879"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Lyu","raw_affiliation_strings":["Alibaba Group,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80459692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2518","last_page":"2525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.20280000567436218,"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":0.20280000567436218,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11320000141859055,"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/T13629","display_name":"Text Readability and Simplification","score":0.049400001764297485,"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/transformative-learning","display_name":"Transformative learning","score":0.6304000020027161},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5293999910354614},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4982999861240387},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4936000108718872},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.4708000123500824},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4641999900341034},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.32089999318122864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6661999821662903},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.6304000020027161},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5336999893188477},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5293999910354614},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4641999900341034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453000009059906},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2849000096321106},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C2986663376","wikidata":"https://www.wikidata.org/wiki/Q9465","display_name":"Ethical issues","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":47,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2108598243","https://openalex.org/W2128856065","https://openalex.org/W2560730294","https://openalex.org/W2962735233","https://openalex.org/W2963518342","https://openalex.org/W3172838779","https://openalex.org/W4210566925","https://openalex.org/W4312933868","https://openalex.org/W4324380807","https://openalex.org/W4389519587","https://openalex.org/W4389523832","https://openalex.org/W4390874580","https://openalex.org/W4392669753","https://openalex.org/W4393157467","https://openalex.org/W4393160204","https://openalex.org/W4396681775","https://openalex.org/W4401416853","https://openalex.org/W4402670791","https://openalex.org/W4402671548","https://openalex.org/W4402672034","https://openalex.org/W4402704633","https://openalex.org/W4402726973","https://openalex.org/W4402727490","https://openalex.org/W4402727699","https://openalex.org/W4402727736","https://openalex.org/W4402727851","https://openalex.org/W4402727888","https://openalex.org/W4403780613","https://openalex.org/W4403906510","https://openalex.org/W4404356490","https://openalex.org/W4404584849","https://openalex.org/W4404781695","https://openalex.org/W4404782209","https://openalex.org/W4404782964","https://openalex.org/W4404784276","https://openalex.org/W4406523182","https://openalex.org/W4406800380","https://openalex.org/W4409348010","https://openalex.org/W4413849607","https://openalex.org/W4415709366","https://openalex.org/W4415796627","https://openalex.org/W4416251786","https://openalex.org/W4416707474","https://openalex.org/W7108068597","https://openalex.org/W7125812135"],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1,186],"years,":[2],"the":[3,10,22,81,134,147,170,185,189],"field":[4],"of":[5,12,36,84,96,113,137,172,177,188,192],"Artificial":[6,85],"Intelligence":[7,87],"has":[8],"witnessed":[9],"emergence":[11],"Multimodal":[13],"Large":[14],"Language":[15],"Models":[16],"(MLLMs)":[17],"that":[18],"have":[19,47],"significantly":[20],"advanced":[21],"state-of-the-art":[23,103],"in":[24,151,169,208],"understanding":[25],"and":[26,38,45,53,61,72,105,121,162,175,183],"generating":[27],"content":[28],"across":[29],"various":[30],"data":[31,156],"modalities.":[32,127],"These":[33],"models,":[34],"capable":[35],"processing":[37],"integrating":[39],"information":[40,63],"from":[41],"text,":[42,69],"images,":[43],"audio,":[44],"video,":[46],"opened":[48],"new":[49],"avenues":[50],"for":[51,124,204],"research":[52,206],"applications.":[54],"Distinguished":[55],"by":[56,115],"their":[57,99,116,196],"ability":[58],"to":[59,118,140],"understand":[60],"generation":[62],"with":[64],"diverse":[65],"modalities,":[66],"such":[67,154],"as":[68,155],"image,":[70],"audio":[71],"many":[73],"others,":[74],"MLLMs":[75,114,193],"mark":[76],"a":[77,201],"significant":[78],"step":[79],"towards":[80],"final":[82],"aim":[83],"General":[86],"(AGI).":[88],"This":[89],"comprehensive":[90],"survey":[91,180],"provides":[92],"an":[93],"in-depth":[94],"examination":[95],"MLLMs,":[97],"highlighting":[98],"evolutionary":[100],"trajectory,":[101],"current":[102],"developments,":[104],"prospective":[106,202],"future":[107,205],"directions.":[108],"Specifically,":[109],"we":[110,129],"show":[111],"taxonomy":[112],"modalities":[117],"be":[119],"processed":[120],"model":[122],"architecture":[123],"aligning":[125],"multiple":[126],"Besides,":[128],"also":[130],"present":[131],"discussion":[132],"regarding":[133],"different":[135],"types":[136],"tasks":[138],"related":[139],"MLLMs.":[141,178],"The":[142,179],"paper":[143],"further":[144],"delves":[145],"into":[146],"pressing":[148],"challenges":[149],"confronted":[150],"this":[152,209],"domain,":[153],"scarcity,":[157],"computational":[158],"complexity,":[159],"ethical":[160],"dilemmas,":[161],"privacy":[163],"considerations.":[164],"We":[165],"analyze":[166],"these":[167],"issues":[168],"context":[171],"both":[173],"development":[174],"deployment":[176],"comprehensively":[181],"demonstrate":[182],"summarise":[184],"advances":[187],"transformative":[190],"influence":[191],"while":[194],"acknowledging":[195],"potential":[197],"limitations,":[198],"thereby":[199],"outlining":[200],"roadmap":[203],"endeavors":[207],"rapidly":[210],"developing":[211],"field.":[212]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-29T00:00:00"}
