{"id":"https://openalex.org/W7138389737","doi":"https://doi.org/10.1609/aaai.v40i28.39532","title":"RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language Models","display_name":"RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language Models","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138389737","doi":"https://doi.org/10.1609/aaai.v40i28.39532"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i28.39532","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i28.39532","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39532/43493","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39532/43493","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129713664","display_name":"Xiang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Lin","raw_affiliation_strings":["SKLCCSE, Beihang University\nSchool of Computer Science and Engineering, Beihang University"],"affiliations":[{"raw_affiliation_string":"SKLCCSE, Beihang University\nSchool of Computer Science and Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129714485","display_name":"Weixin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixin Li","raw_affiliation_strings":["SKLCCSE, Beihang University\nSchool of Computer Science and Engineering, Beihang University"],"affiliations":[{"raw_affiliation_string":"SKLCCSE, Beihang University\nSchool of Computer Science and Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129738498","display_name":"Shu Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Guo","raw_affiliation_strings":["National Computer Network Emergency Response Technical Team/Coordination Center of China"],"affiliations":[{"raw_affiliation_string":"National Computer Network Emergency Response Technical Team/Coordination Center of China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129732989","display_name":"Lihong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihong Wang","raw_affiliation_strings":["National Computer Network Emergency Response Technical Team/Coordination Center of China"],"affiliations":[{"raw_affiliation_string":"National Computer Network Emergency Response Technical Team/Coordination Center of China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129700902","display_name":"Di Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Huang","raw_affiliation_strings":["SKLCCSE, Beihang University\nSchool of Computer Science and Engineering, Beihang University"],"affiliations":[{"raw_affiliation_string":"SKLCCSE, Beihang University\nSchool of Computer Science and Engineering, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5129713664"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75372024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"28","first_page":"23594","last_page":"23602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6459000110626221,"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":0.6459000110626221,"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":0.2533000111579895,"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/T10028","display_name":"Topic Modeling","score":0.012199999764561653,"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/adaptation","display_name":"Adaptation (eye)","score":0.5267999768257141},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4885999858379364},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.42669999599456787},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4253999888896942},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3628999888896942},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.35530000925064087},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.3463999927043915},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.32749998569488525},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.3260999917984009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773000001907349},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5267999768257141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5004000067710876},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43059998750686646},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.35530000925064087},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.3158999979496002},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2727000117301941},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i28.39532","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i28.39532","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39532/43493","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i28.39532","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i28.39532","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39532/43493","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6626022458076477,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G130652162","display_name":null,"funder_award_id":"202304","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/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"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/G3642141518","display_name":null,"funder_award_id":"20230484297","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4232962833","display_name":null,"funder_award_id":"82441024","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/G696463282","display_name":null,"funder_award_id":"2023048","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138389737.pdf","grobid_xml":"https://content.openalex.org/works/W7138389737.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Pre-trained":[0],"Vision-Language":[1],"Models":[2],"(VLMs),":[3],"e.g.":[4],"CLIP,":[5],"have":[6,36],"become":[7],"essential":[8],"tools":[9],"in":[10,17,23,29],"multimodal":[11],"transfer":[12],"learning.":[13],"However,":[14],"fine-tuning":[15],"VLMs":[16],"few-shot":[18],"scenarios":[19],"poses":[20],"significant":[21],"challenges":[22],"balancing":[24],"task-specific":[25,82,116],"adaptation":[26,41,78],"and":[27,47,87,115,141,165,187],"generalization":[28,178,182],"the":[30,103,145,161,170],"obtained":[31],"model.":[32],"Meanwhile,":[33],"current":[34],"researches":[35],"predominantly":[37],"focused":[38],"on":[39,174,192],"prompt-based":[40],"methods,":[42],"leaving":[43],"adapter-based":[44],"approaches":[45,204],"underexplored":[46],"revealing":[48],"notable":[49],"performance":[50],"gaps.":[51],"To":[52],"address":[53],"these":[54],"challenges,":[55],"we":[56],"introduce":[57],"a":[58,66,89,110],"novel":[59],"Reconstruction-based":[60],"Multimodal":[61],"Adapter":[62],"(RMAdapter),":[63],"which":[64],"leverages":[65],"dual-branch":[67],"architecture.":[68],"Unlike":[69],"conventional":[70],"single-branch":[71],"adapters,":[72],"RMAdapter":[73,120,173,200],"consists":[74],"of:":[75],"(1)":[76],"an":[77,122],"branch":[79,91],"that":[80,92],"injects":[81],"knowledge":[83,95],"through":[84],"parameter-efficient":[85],"fine-tuning,":[86],"(2)":[88],"reconstruction":[90,124,135],"preserves":[93],"general":[94,114],"by":[96],"reconstructing":[97],"latent":[98],"space":[99],"features":[100],"back":[101],"into":[102],"original":[104],"feature":[105],"space.":[106],"This":[107],"design":[108],"facilitates":[109],"dynamic":[111],"balance":[112],"between":[113,163],"knowledge.":[117],"Importantly,":[118],"although":[119],"introduces":[121],"additional":[123],"branch,":[125],"it":[126],"is":[127,149,155],"carefully":[128],"optimized":[129],"to":[130,158,179,183],"remain":[131],"lightweight.":[132],"By":[133],"computing":[134],"loss":[136],"locally":[137],"at":[138],"each":[139],"layer":[140],"sharing":[142],"projection":[143],"modules,":[144],"overall":[146],"computational":[147],"overhead":[148],"kept":[150],"minimal.":[151],"A":[152],"consistency":[153],"constraint":[154],"also":[156],"incorporated":[157],"better":[159],"regulate":[160],"trade-off":[162],"discriminability":[164],"generalization.":[166,189],"We":[167],"comprehensively":[168],"evaluate":[169],"effectiveness":[171],"of":[172],"three":[175],"representative":[176],"tasks:":[177],"new":[180,184],"categories,":[181],"target":[185],"datasets,":[186],"domain":[188],"Without":[190],"relying":[191],"data":[193],"augmentation":[194],"or":[195],"duplicate":[196],"prompt":[197],"designs,":[198],"our":[199],"consistently":[201],"outperforms":[202],"state-of-the-art":[203],"across":[205],"all":[206],"evaluation":[207],"metrics.":[208]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-18T00:00:00"}