{"id":"https://openalex.org/W7135222925","doi":"https://doi.org/10.48550/arxiv.2603.11211","title":"A Simple Efficiency Incremental Learning Framework via Vision-Language Model with Nonlinear Multi-Adapters","display_name":"A Simple Efficiency Incremental Learning Framework via Vision-Language Model with Nonlinear Multi-Adapters","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7135222925","doi":"https://doi.org/10.48550/arxiv.2603.11211"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.11211","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11211","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.11211","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129041968","display_name":"Haihua Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Haihua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129051571","display_name":"Xuming Ran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ran, Xuming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007758616","display_name":"Jiangrong Shen","orcid":"https://orcid.org/0000-0003-3683-3779"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Jiangrong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102937415","display_name":"Timo D. H\u00e4m\u00e4l\u00e4inen","orcid":"https://orcid.org/0000-0002-7867-0800"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H\u00e4m\u00e4l\u00e4inen, Timo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129018883","display_name":"Zhonghua Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhonghua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129082899","display_name":"Qi Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128976107","display_name":"Fengyu Cong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong, Fengyu","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8564000129699707,"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":0.8564000129699707,"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":0.05139999836683273,"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":0.016599999740719795,"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/transformer","display_name":"Transformer","score":0.6317999958992004},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.6237999796867371},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.557699978351593},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5267999768257141},{"id":"https://openalex.org/keywords/incremental-learning","display_name":"Incremental learning","score":0.4359999895095825},{"id":"https://openalex.org/keywords/nonlinear-model","display_name":"Nonlinear model","score":0.3497999906539917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063000202178955},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6317999958992004},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.6237999796867371},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.557699978351593},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5267999768257141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5220999717712402},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47130000591278076},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C2984755018","wikidata":"https://www.wikidata.org/wiki/Q17118374","display_name":"Nonlinear model","level":3,"score":0.3497999906539917},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.11211","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11211","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.11211","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11211","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Incremental":[0],"Learning":[1],"(IL)":[2],"aims":[3],"to":[4,50,62,173],"learn":[5],"new":[6],"tasks":[7],"while":[8],"preserving":[9],"previously":[10],"acquired":[11],"knowledge.":[12],"Integrating":[13],"the":[14,38,56,64,88,102,109,141,175,178],"zero-shot":[15,179],"learning":[16],"capabilities":[17,180],"of":[18,58,104,177,181],"pre-trained":[19],"vision-language":[20,81],"models":[21],"into":[22],"IL":[23,89,111,143],"methods":[24,32,153,162],"has":[25],"marked":[26],"a":[27,47,59,73,80,93,98,170,189],"significant":[28],"advancement.":[29],"However,":[30],"these":[31],"face":[33],"three":[34],"primary":[35],"challenges:":[36],"(1)":[37],"need":[39],"for":[40,87],"improved":[41],"training":[42],"efficiency;":[43],"(2)":[44],"reliance":[45],"on":[46,156,165,193],"memory":[48],"bank":[49],"store":[51],"previous":[52],"data;":[53],"and":[54,75,108,137,158,198],"(3)":[55],"necessity":[57],"strong":[60],"backbone":[61],"augment":[63],"model's":[65,110,142],"capabilities.":[66,112],"In":[67],"this":[68],"paper,":[69],"we":[70,168],"propose":[71],"SimE,":[72],"Simple":[74],"Efficient":[76],"framework":[77],"that":[78,149],"employs":[79],"model":[82,121,191],"with":[83,188],"adapters":[84],"designed":[85],"specifically":[86],"task.":[90],"We":[91,183],"report":[92],"remarkable":[94],"phenomenon:":[95],"there":[96],"is":[97],"nonlinear":[99],"correlation":[100],"between":[101,117],"number":[103],"adaptive":[105,125],"adapter":[106,115],"connections":[107,116,126],"While":[113],"increasing":[114],"transformer":[118,128],"blocks":[119,129],"improves":[120],"performance,":[122],"adding":[123],"more":[124],"within":[127],"during":[130],"smaller":[131],"incremental":[132],"steps":[133],"does":[134],"not":[135],"enhance,":[136],"may":[138],"even":[139],"degrade":[140],"ability.":[144],"Extensive":[145],"experimental":[146],"results":[147],"show":[148],"SimE":[150],"surpasses":[151],"traditional":[152],"by":[154,163],"9.6%":[155],"TinyImageNet":[157],"outperforms":[159],"other":[160],"CLIP-based":[161],"5.3%":[164],"CIFAR-100.":[166],"Furthermore,":[167],"conduct":[169],"systematic":[171],"study":[172],"enhance":[174],"utilization":[176],"CLIP.":[182],"suggest":[184],"replacing":[185],"SimE's":[186],"encoder":[187],"CLIP":[190],"trained":[192],"larger":[194],"datasets":[195],"(e.g.,":[196,201],"LAION2B)":[197],"stronger":[199],"architectures":[200],"ViT-L/14).":[202]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-14T00:00:00"}