{"id":"https://openalex.org/W4416036056","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.105","title":"Self-Improvement in Multimodal Large Language Models: A Survey","display_name":"Self-Improvement in Multimodal Large Language Models: A Survey","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036056","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.105"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.105","pdf_url":"https://aclanthology.org/2025.findings-emnlp.105.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.105.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028337614","display_name":"Shijian Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shijian Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051068120","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0001-7845-8028"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101998583","display_name":"Tianyu Yang","orcid":"https://orcid.org/0000-0001-5645-7059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyu Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063517427","display_name":"Harsh Singh","orcid":"https://orcid.org/0009-0006-3251-4622"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harsh Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5071520794","display_name":"Yapeng Tian","orcid":"https://orcid.org/0000-0003-4271-5293"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yapeng Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1987","last_page":"2006"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.29910001158714294,"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":0.29910001158714294,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.09319999814033508,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.06700000166893005,"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/natural-language","display_name":"Natural language","score":0.3321000039577484},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28690001368522644},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.24639999866485596},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.24060000479221344},{"id":"https://openalex.org/keywords/staring","display_name":"Staring","score":0.23849999904632568}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5763999819755554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4020000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37599998712539673},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.37209999561309814},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.24639999866485596},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.24060000479221344},{"id":"https://openalex.org/C2778949103","wikidata":"https://www.wikidata.org/wiki/Q600717","display_name":"Staring","level":2,"score":0.23849999904632568},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2371000051498413}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.105","pdf_url":"https://aclanthology.org/2025.findings-emnlp.105.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.105","pdf_url":"https://aclanthology.org/2025.findings-emnlp.105.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036056.pdf","grobid_xml":"https://content.openalex.org/works/W4416036056.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,19,61,96],"self-improvement":[3,60,95],"for":[4,39],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"have":[9],"efficiently":[10],"enhanced":[11],"model":[12,87],"capabilities":[13],"without":[14],"significantly":[15],"increasing":[16],"costs,":[17],"particularly":[18],"terms":[20],"of":[21,59,69,94],"human":[22],"effort.While":[23],"this":[24],"area":[25],"is":[26,51],"still":[27],"relatively":[28],"young,":[29],"its":[30],"extension":[31],"to":[32,54,89],"the":[33,52,70,91],"multimodal":[34],"domain":[35],"holds":[36],"immense":[37],"potential":[38],"leveraging":[40],"diverse":[41],"data":[42,80,83],"sources":[43],"and":[44,73,85,103,112],"developing":[45],"more":[46],"general":[47],"self-improving":[48],"models.This":[49],"survey":[50],"first":[53],"provide":[55,65],"a":[56,66],"comprehensive":[57],"overview":[58,68],"Multimodal":[62],"LLMs":[63],"(MLLMs).We":[64],"structured":[67],"current":[71],"literature":[72],"discuss":[74],"methods":[75],"from":[76],"three":[77],"perspectives:":[78],"1)":[79],"collection,":[81],"2)":[82],"organization,":[84],"3)":[86],"optimization,":[88],"facilitate":[90],"further":[92],"development":[93],"MLLMs.We":[97],"also":[98],"include":[99],"commonly":[100],"used":[101],"evaluations":[102],"downstream":[104],"applications.Finally,":[105],"we":[106],"conclude":[107],"by":[108],"outlining":[109],"open":[110],"challenges":[111],"future":[113],"research":[114],"directions.1.":[115]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}