{"id":"https://openalex.org/W4415707830","doi":"https://doi.org/10.1109/icme59968.2025.11209968","title":"MAO: Efficient Model-Agnostic Optimization of Prompt Tuning for Vision-Language Models","display_name":"MAO: Efficient Model-Agnostic Optimization of Prompt Tuning for Vision-Language Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707830","doi":"https://doi.org/10.1109/icme59968.2025.11209968"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209968","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5100369545","display_name":"Haoyang Li","orcid":"https://orcid.org/0000-0003-3544-5563"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyang Li","raw_affiliation_strings":["Shanghai University,School of Mechanical Engineering and Automation,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,School of Mechanical Engineering and Automation,Shanghai,China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113431566","display_name":"Siyu Zhou","orcid":"https://orcid.org/0009-0009-9649-8061"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Siyu Zhou","raw_affiliation_strings":["University of Technology Sydney,Australian Artificial Intelligence Institute,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney,Australian Artificial Intelligence Institute,Sydney,Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456523","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0002-3771-4627"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["Shanghai University,School of Mechanical Engineering and Automation,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,School of Mechanical Engineering and Automation,Shanghai,China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I141962983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059227406","display_name":"Guodong Long","orcid":"https://orcid.org/0000-0003-3740-9515"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guodong Long","raw_affiliation_strings":["University of Technology Sydney,Australian Artificial Intelligence Institute,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney,Australian Artificial Intelligence Institute,Sydney,Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8597000241279602,"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":0.8597000241279602,"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":0.02810000069439411,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.026499999687075615,"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/regularization","display_name":"Regularization (linguistics)","score":0.5270000100135803},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4875999987125397},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.397599995136261},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.36739999055862427},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.33009999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279999852180481},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29159998893737793},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.2802000045776367}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209968","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W3198377975","https://openalex.org/W4312310776","https://openalex.org/W4312651322","https://openalex.org/W4386065763","https://openalex.org/W4386071547","https://openalex.org/W4390872773","https://openalex.org/W4392172801","https://openalex.org/W4402727025","https://openalex.org/W4402783842","https://openalex.org/W4402980933","https://openalex.org/W4413147190"],"related_works":[],"abstract_inverted_index":{"Though":[0],"CLIP-based":[1],"prompt":[2,49,57],"tuning":[3,40,58],"significantly":[4],"enhances":[5],"pre-trained":[6],"Vision-Language":[7],"Models,":[8],"existing":[9],"research":[10],"focuses":[11],"on":[12,98],"reconstructing":[13],"the":[14,36,39,56,68,71,82],"model":[15],"architecture,":[16],"e.g.,":[17],"additional":[18],"loss":[19],"calculation":[20],"and":[21,30,74,104],"meta-networks.":[22],"These":[23],"approaches":[24],"generally":[25],"lead":[26],"to":[27,66,80],"increased":[28],"complexity":[29],"extended":[31],"training":[32],"cost.":[33,95],"To":[34],"maintain":[35],"efficiency":[37],"of":[38,55,70],"process,":[41],"we":[42,60],"propose":[43],"plug-and-play":[44],"Model-Agnostic":[45],"Optimization":[46],"(MAO)":[47],"for":[48],"tuning.":[50],"Without":[51],"altering":[52],"any":[53],"components":[54],"backbone,":[59],"introduce":[61],"a":[62],"Data-Driven":[63],"Enhancement":[64],"framework":[65],"optimize":[67],"distribution":[69],"initial":[72],"data,":[73],"incorporate":[75],"an":[76],"Alterable":[77],"Regularization":[78],"module":[79],"boost":[81],"task-specific":[83],"feature":[84],"processing":[85],"pipeline,":[86],"thereby":[87],"improving":[88],"overall":[89],"performance":[90,103],"while":[91],"maintaining":[92],"low":[93],"computational":[94],"Extensive":[96],"experiments":[97],"MAO":[99],"demonstrate":[100],"its":[101],"outstanding":[102],"efficiency.":[105]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}