{"id":"https://openalex.org/W4417147545","doi":"https://doi.org/10.1007/s44267-025-00099-6","title":"Efficient multimodal large language models: a survey","display_name":"Efficient multimodal large language models: a survey","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W4417147545","doi":"https://doi.org/10.1007/s44267-025-00099-6"},"language":"en","primary_location":{"id":"doi:10.1007/s44267-025-00099-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00099-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00099-6.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00099-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113052534","display_name":"Yizhang Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yizhang Jin","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402508","display_name":"Jian Li","orcid":"https://orcid.org/0000-0002-0242-6481"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Li","raw_affiliation_strings":["Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113222156","display_name":"Tianjun Gu","orcid":"https://orcid.org/0009-0001-4757-2685"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianjun Gu","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021084391","display_name":"Yexin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yexin Liu","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069245621","display_name":"Bo Zhao","orcid":"https://orcid.org/0000-0002-7834-6672"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhao","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057352675","display_name":"Jinxiang Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jinxiang Lai","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075598739","display_name":"Zhenye Gan","orcid":"https://orcid.org/0000-0002-2431-1159"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenye Gan","raw_affiliation_strings":["Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028731909","display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabiao Wang","raw_affiliation_strings":["Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023834700","display_name":"Chengjie Wang","orcid":"https://orcid.org/0000-0003-4216-8090"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjie Wang","raw_affiliation_strings":["Tencent, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080281882","display_name":"Xin Tan","orcid":"https://orcid.org/0000-0001-9346-1196"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Tan","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084218062","display_name":"Lizhuang Ma","orcid":"https://orcid.org/0000-0003-1653-4341"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhuang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5113052534"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":8.9487,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98025309,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"3","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8755999803543091,"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":0.8755999803543091,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.008200000040233135,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00800000037997961,"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/timeline","display_name":"Timeline","score":0.6498000025749207},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5310999751091003},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4812999963760376},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.41609999537467957},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.3937999904155731},{"id":"https://openalex.org/keywords/open-research","display_name":"Open research","score":0.34549999237060547},{"id":"https://openalex.org/keywords/current","display_name":"Current (fluid)","score":0.3443000018596649}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742000222206116},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.6498000025749207},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41589999198913574},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40709999203681946},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3537999987602234},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44267-025-00099-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00099-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00099-6.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9fb2409052134545b76200c8c180e57f","is_oa":true,"landing_page_url":"https://doaj.org/article/9fb2409052134545b76200c8c180e57f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Visual Intelligence, Vol 3, Iss 1, Pp 1-33 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44267-025-00099-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00099-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00099-6.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1014109120","display_name":null,"funder_award_id":"72192821","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4616993040","display_name":null,"funder_award_id":"U23A2034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5691570638","display_name":null,"funder_award_id":"U23A20343","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6676365692","display_name":null,"funder_award_id":"U23A203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8137067846","display_name":null,"funder_award_id":"62302167","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4417147545.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W4304080501","https://openalex.org/W4307504011","https://openalex.org/W4312453883","https://openalex.org/W4327519267","https://openalex.org/W4389518760","https://openalex.org/W4389523832","https://openalex.org/W4389524317","https://openalex.org/W4389524555","https://openalex.org/W4389977645","https://openalex.org/W4396681775","https://openalex.org/W4401386967","https://openalex.org/W4402401372","https://openalex.org/W4402716381","https://openalex.org/W4402727885","https://openalex.org/W4402753980","https://openalex.org/W4403793633","https://openalex.org/W4403842477","https://openalex.org/W4403842540","https://openalex.org/W4404002404","https://openalex.org/W4404356490","https://openalex.org/W4404782963","https://openalex.org/W4404784276","https://openalex.org/W4405248620","https://openalex.org/W4405399726","https://openalex.org/W4409356606","https://openalex.org/W4413344259","https://openalex.org/W4414693319","https://openalex.org/W4416707474","https://openalex.org/W7092629194"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"In":[1,62],"the":[2,27,39,73,83,89,99,102],"past":[3],"years,":[4],"multimodal":[5],"large":[6],"language":[7],"models":[8],"(MLLMs)":[9],"have":[10,37],"demonstrated":[11],"remarkable":[12],"performance":[13],"in":[14,44,58,94],"tasks":[15],"such":[16],"as":[17],"visual":[18,22],"question":[19],"answering":[20],"and":[21,24,31,34,46,51,69,96,98,109],"understanding":[23],"reasoning.":[25],"However,":[26],"extensive":[28],"model":[29],"size":[30],"high":[32],"training":[33],"inference":[35],"costs":[36],"hindered":[38],"widespread":[40],"application":[41],"of":[42,72,76,85,92,104],"MLLMs":[43,53],"academia":[45],"industry.":[47],"Thus,":[48],"studying":[49],"efficient":[50,77,87,106],"lightweight":[52],"has":[54],"enormous":[55],"potential,":[56],"especially":[57],"edge":[59],"computing":[60],"scenarios.":[61],"this":[63,80],"survey,":[64],"we":[65],"provide":[66],"a":[67],"comprehensive":[68],"systematic":[70],"review":[71],"current":[74,90,105],"state":[75,91],"MLLMs.":[78],"Specifically,":[79],"survey":[81],"summarizes":[82],"timeline":[84],"representative":[86],"MLLMs,":[88],"research":[93,108],"structures":[95],"strategies,":[97],"applications.":[100],"Finally,":[101],"limitations":[103],"MLLM":[107],"promising":[110],"future":[111],"directions":[112],"are":[113],"discussed.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-12-09T00:00:00"}