{"id":"https://openalex.org/W7094967983","doi":"https://doi.org/10.1145/3746027.3755520","title":"EvoVLMA: Evolutionary Vision-Language Model Adaptation","display_name":"EvoVLMA: Evolutionary Vision-Language Model Adaptation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W7094967983","doi":"https://doi.org/10.1145/3746027.3755520"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755520","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755520","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755520","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kun Ding","orcid":"https://orcid.org/0000-0002-2256-8815"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kun Ding","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ying Wang","orcid":"https://orcid.org/0000-0003-1385-3224"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shiming Xiang","orcid":"https://orcid.org/0000-0002-2089-9733"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiming Xiang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7826312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4619","last_page":"4628"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.619700014591217,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.619700014591217,"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":0.18970000743865967,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.033900000154972076,"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/adaptation","display_name":"Adaptation (eye)","score":0.6323999762535095},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.5715000033378601},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5128999948501587},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5113000273704529},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.5085999965667725},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.43650001287460327},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.412200003862381},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.39169999957084656},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.382999986410141}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7669000029563904},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6323999762535095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.59170001745224},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5335999727249146},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5128999948501587},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5113000273704529},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.5085999965667725},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C123189799","wikidata":"https://www.wikidata.org/wiki/Q6045380","display_name":"Interactive evolutionary computation","level":4,"score":0.33980000019073486},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C2780502288","wikidata":"https://www.wikidata.org/wiki/Q28838156","display_name":"Expansive","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C199505168","wikidata":"https://www.wikidata.org/wiki/Q3267529","display_name":"Evolutionary robotics","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C121835503","wikidata":"https://www.wikidata.org/wiki/Q2596288","display_name":"Evolutionary programming","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C207002847","wikidata":"https://www.wikidata.org/wiki/Q2912857","display_name":"Evolution strategy","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755520","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755520","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3746027.3755520","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755520","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2166049352","https://openalex.org/W2964194231","https://openalex.org/W3198377975","https://openalex.org/W4382468999","https://openalex.org/W4388660746","https://openalex.org/W4393155041","https://openalex.org/W4401274577","https://openalex.org/W4402897562"],"related_works":[],"abstract_inverted_index":{"Pre-trained":[0],"Vision-Language":[1,55],"Models":[2,46],"(VLMs)":[3],"have":[4],"been":[5],"exploited":[6],"in":[7,43,80,95,164,180],"various":[8],"Computer":[9],"Vision":[10],"tasks":[11],"(e.g.,":[12],"few-shot":[13],"recognition)":[14],"via":[15],"model":[16],"adaptation,":[17,83],"such":[18],"as":[19,76],"prompt":[20],"tuning":[21],"and":[22,37,73,84,118,132],"adapters.":[23],"However,":[24],"existing":[25],"adaptation":[26,65,193],"methods":[27],"are":[28],"designed":[29],"by":[30,40,104,151,177],"human":[31],"experts,":[32],"requiring":[33],"significant":[34],"time":[35],"cost":[36],"experience.":[38],"Inspired":[39],"recent":[41],"advances":[42],"Large":[44],"Language":[45],"(LLMs)":[47],"based":[48,129],"code":[49,126,130],"generation,":[50],"we":[51,123],"propose":[52,85,124],"an":[53],"Evolutionary":[54],"Model":[56],"Adaptation":[57],"(EvoVLMA)":[58],"method":[59],"to":[60,114,136,158],"automatically":[61],"search":[62,107],"training-free":[63,81],"efficient":[64],"algorithms":[66,149,194],"for":[67,91,188],"VLMs.":[68],"We":[69],"recognize":[70],"feature":[71],"selection":[72],"logits":[74],"computation":[75],"the":[77,101,105,116,148,165,170,190],"key":[78],"functions":[79],"VLM":[82],"a":[86,96,110,137],"two-stage":[87],"LLM-assisted":[88],"evolutionary":[89],"algorithm":[90,141,173],"optimizing":[92],"these":[93],"parts":[94],"sequential":[97],"manner,":[98],"effectively":[99],"addressing":[100],"challenge":[102],"posed":[103],"expansive":[106],"space":[108],"through":[109],"divide-and-conquer":[111],"strategy.":[112],"Besides,":[113],"enhance":[115],"stability":[117],"efficiency":[119],"of":[120,192,195],"searching":[121],"process,":[122],"low-precision":[125],"conversion,":[127],"web":[128],"execution":[131],"process":[133],"monitoring,":[134],"leading":[135],"highly":[138],"effective":[139],"automatic":[140],"design":[142],"system.":[143],"Extensive":[144],"experiments":[145],"demonstrate":[146],"that":[147],"found":[150],"EvoVLMA":[152],"can":[153,174],"obtain":[154],"promising":[155],"results":[156],"compared":[157],"previous":[159],"manually-designed":[160],"ones.":[161],"More":[162],"specifically,":[163],"8-shot":[166],"image":[167],"classification":[168],"setting,":[169],"classical":[171],"APE":[172],"be":[175],"improved":[176],"1.91":[178],"points":[179],"recognition":[181],"accuracy.":[182],"This":[183],"research":[184],"opens":[185],"new":[186],"possibilities":[187],"automating":[189],"optimization":[191],"pre-trained":[196],"multimodal":[197],"models.":[198],"Code":[199],"is":[200],"available":[201],"at:":[202],"https://github.com/kding1225/EvoVLMA":[203]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}