{"id":"https://openalex.org/W4404401197","doi":"https://doi.org/10.3390/computation14060125","title":"A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision\u2013Language Tasks","display_name":"A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision\u2013Language Tasks","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W4404401197","doi":"https://doi.org/10.3390/computation14060125"},"language":"en","primary_location":{"id":"doi:10.3390/computation14060125","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computation14060125","pdf_url":null,"source":{"id":"https://openalex.org/S2738402919","display_name":"Computation","issn_l":"2079-3197","issn":["2079-3197"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computation","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/computation14060125","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114664487","display_name":"Chia Xin Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I108377105","display_name":"Tainan University of Technology","ror":"https://ror.org/03967fe87","country_code":"TW","type":"education","lineage":["https://openalex.org/I108377105"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia Xin Liang","raw_affiliation_strings":["JTB Technology CO., Ltd., Tainan 701020, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JTB Technology CO., Ltd., Tainan 701020, Taiwan","institution_ids":["https://openalex.org/I108377105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058565205","display_name":"Pu Tian","orcid":"https://orcid.org/0000-0003-4791-892X"},"institutions":[{"id":"https://openalex.org/I24010308","display_name":"Stockton University","ror":"https://ror.org/0442n1j98","country_code":"US","type":"education","lineage":["https://openalex.org/I24010308"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pu Tian","raw_affiliation_strings":["Computer Science Program, School of Business, Stockton University, Galloway, NJ 08205, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Program, School of Business, Stockton University, Galloway, NJ 08205, USA","institution_ids":["https://openalex.org/I24010308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084288085","display_name":"Caitlyn Heqi Yin","orcid":"https://orcid.org/0000-0003-1950-0737"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caitlyn Heqi Yin","raw_affiliation_strings":["Department of Computer Sciences, School of Computer, Data & Information Sciences, University of Wisconsin\u2013Madison, Madison, WI 53706, USA"],"raw_orcid":"https://orcid.org/0000-0003-1950-0737","affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, School of Computer, Data & Information Sciences, University of Wisconsin\u2013Madison, Madison, WI 53706, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041927422","display_name":"Yao Yua","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091678","display_name":"Acupuncture And Massage College","ror":"https://ror.org/00gej0269","country_code":"US","type":"education","lineage":["https://openalex.org/I4210091678"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yao Yua","raw_affiliation_strings":["AppCubic, Miami, FL 33138, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AppCubic, Miami, FL 33138, USA","institution_ids":["https://openalex.org/I4210091678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114656927","display_name":"Wei An-Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090434","display_name":"LanzaTech (New Zealand)","ror":"https://ror.org/016jjeg55","country_code":"NZ","type":"company","lineage":["https://openalex.org/I4210090434"]},{"id":"https://openalex.org/I4210126914","display_name":"MedTech CoRE","ror":"https://ror.org/02p521049","country_code":"NZ","type":"facility","lineage":["https://openalex.org/I4210126914"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"An-Hou Wei","raw_affiliation_strings":["Nomad Sustaintech Ltd., Auckland 2019, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nomad Sustaintech Ltd., Auckland 2019, New Zealand","institution_ids":["https://openalex.org/I4210090434","https://openalex.org/I4210126914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108103931","display_name":"Li Ming","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, Atlanta, GA 30332, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, Atlanta, GA 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinyuan Song","orcid":"https://orcid.org/0009-0005-4209-5671"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyuan Song","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, GA 30322, USA"],"raw_orcid":"https://orcid.org/0009-0005-4209-5671","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, GA 30322, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656828","display_name":"Tianyang Wang","orcid":"https://orcid.org/0000-0002-5051-7951"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tianyang Wang","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool L69 3BX, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool L69 3BX, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108304756","display_name":"Ziqian Bi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziqian Bi","raw_affiliation_strings":["Department of Computer Science, Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington, Bloomington, IN 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington, Bloomington, IN 47408, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101988378","display_name":"Ming Liu","orcid":"https://orcid.org/0000-0003-4689-6474"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Liu","raw_affiliation_strings":["Department of Computer Science, Purdue University, West Lafayette, IN 47907, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Purdue University, West Lafayette, IN 47907, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Riyang Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Riyang Bao","raw_affiliation_strings":["Department of Computer Science, Emory University, Atlanta, GA 30322, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Emory University, Atlanta, GA 30322, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":null,"display_name":"Pengbin Feng","orcid":"https://orcid.org/0009-0001-6774-4296"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengbin Feng","raw_affiliation_strings":["Department of Mathematics, University of Southern California, Los Angeles, CA 90089, USA"],"raw_orcid":"https://orcid.org/0009-0001-6774-4296","affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Southern California, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":12,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1800,"currency":"CHF","value_usd":2172},"apc_paid":{"value":1800,"currency":"CHF","value_usd":2172},"fwci":4.3847,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88451206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"14","issue":"6","first_page":"125","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9488999843597412,"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":0.9488999843597412,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6083055138587952},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3782305419445038},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37136146426200867},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35715535283088684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6083055138587952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3782305419445038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37136146426200867},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35715535283088684}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/computation14060125","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computation14060125","pdf_url":null,"source":{"id":"https://openalex.org/S2738402919","display_name":"Computation","issn_l":"2079-3197","issn":["2079-3197"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computation","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2411.06284","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.06284","pdf_url":"https://arxiv.org/pdf/2411.06284","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"pmh:oai:doaj.org/article:79de5d01d1604dbba9bc82447795e1ba","is_oa":false,"landing_page_url":"https://doaj.org/article/79de5d01d1604dbba9bc82447795e1ba","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computation, Vol 14, Iss 6, p 125 (2026)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2411.06284","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.06284","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.3390/computation14060125","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computation14060125","pdf_url":null,"source":{"id":"https://openalex.org/S2738402919","display_name":"Computation","issn_l":"2079-3197","issn":["2079-3197"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computation","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0,75],"survey":[1,76,154],"provides":[2],"a":[3,13,122,130,140],"comprehensive":[4],"guide":[5],"to":[6],"Multimodal":[7],"Large":[8],"Language":[9],"Models":[10],"(MLLMs)":[11],"with":[12,146],"focus":[14],"on":[15,78],"vision\u2013language":[16,79],"tasks,":[17],"including":[18],"image":[19],"captioning,":[20],"visual":[21,26,44,91],"question":[22],"answering,":[23],"cross-modal":[24,118],"retrieval,":[25],"grounding,":[27],"multi-image":[28],"reasoning,":[29],"long-video":[30],"understanding,":[31],"and":[32,40,55,66,73,81,96,117,136,139,149,158,164,174],"embodied":[33],"AI.":[34],"We":[35,58,120],"examine":[36,101],"architectures,":[37],"training":[38],"pipelines,":[39],"practical":[41,159],"applications,":[42],"covering":[43],"encoders,":[45],"language":[46,172],"model":[47],"backbones,":[48],"connector":[49],"modules,":[50],"contrastive":[51],"pre-training,":[52],"instruction":[53],"tuning,":[54],"preference":[56],"alignment.":[57],"also":[59],"foreground":[60],"first-principles":[61],"constraints\u2014information":[62],"bottlenecks,":[63],"data-processing":[64],"limits,":[65],"statistical":[67],"co-occurrence":[68],"bias\u2014that":[69],"shape":[70],"architecture,":[71],"robustness,":[72,116],"evaluation.":[74],"centers":[77],"systems":[80],"does":[82],"not":[83],"cover":[84],"audio-only":[85],"models":[86,135],"or":[87],"code-generation":[88],"tools":[89],"without":[90],"inputs.":[92],"Through":[93],"task-level":[94],"analysis":[95],"system-level":[97],"case":[98],"studies,":[99],"we":[100],"prominent":[102],"MLLM":[103,127],"implementations":[104],"while":[105],"addressing":[106],"key":[107],"challenges":[108],"in":[109],"scalability,":[110],"memory,":[111],"energy":[112],"use,":[113],"inference":[114],"cost,":[115],"learning.":[119],"present":[121],"unified":[123],"taxonomy":[124],"of":[125,133,142,170],"the":[126,168],"design":[128],"space,":[129],"comparative":[131],"overview":[132],"representative":[134],"evaluation":[137],"benchmarks,":[138],"discussion":[141],"open":[143],"problems.":[144],"Concluding":[145],"ethical":[147],"considerations":[148],"responsible":[150],"AI":[151],"development,":[152],"this":[153],"offers":[155],"theoretical":[156],"frameworks":[157],"insights":[160],"for":[161],"researchers,":[162],"practitioners,":[163],"students":[165],"working":[166],"at":[167],"intersection":[169],"natural":[171],"processing":[173],"computer":[175],"vision.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
