{"id":"https://openalex.org/W7134816215","doi":"https://doi.org/10.48550/arxiv.2603.07787","title":"Vision Transformers that Never Stop Learning","display_name":"Vision Transformers that Never Stop Learning","publication_year":2026,"publication_date":"2026-03-08","ids":{"openalex":"https://openalex.org/W7134816215","doi":"https://doi.org/10.48550/arxiv.2603.07787"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.07787","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044784805","display_name":"Caihao Sun","orcid":"https://orcid.org/0000-0002-8164-489X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Caihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110921988","display_name":"Mingqi Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Mingqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112274140","display_name":"S S Wang","orcid":"https://orcid.org/0009-0004-6616-5892"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128653809","display_name":"Jiayu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jiayu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.4074000120162964,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.4074000120162964,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.17190000414848328,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.1445000022649765,"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/plasticity","display_name":"Plasticity","score":0.8011999726295471},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5037999749183655},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4853000044822693},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4837999939918518},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.353300005197525}],"concepts":[{"id":"https://openalex.org/C79186407","wikidata":"https://www.wikidata.org/wiki/Q472074","display_name":"Plasticity","level":2,"score":0.8011999726295471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6378999948501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5267000198364258},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5037999749183655},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4837999939918518},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C47611674","wikidata":"https://www.wikidata.org/wiki/Q849491","display_name":"Neuroplasticity","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2831999957561493}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.07787","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.07787","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.07787","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.07787","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Loss":[0],"of":[1,8,61,63],"plasticity":[2,64,92,110,124,150,172],"refers":[3],"to":[4,11,13,122],"the":[5,132,162],"progressive":[6],"inability":[7],"a":[9,18,58,68,145],"model":[10],"adapt":[12],"new":[14],"tasks":[15],"and":[16,78,173],"poses":[17],"fundamental":[19],"challenge":[20],"for":[21,108,161],"continual":[22],"learning.":[23],"While":[24],"this":[25,54,140],"phenomenon":[26],"has":[27],"been":[28],"extensively":[29],"studied":[30],"in":[31,41,65,125],"homogeneous":[32],"neural":[33],"architectures,":[34],"such":[35,46],"as":[36,47],"multilayer":[37],"perceptrons,":[38],"its":[39],"mechanisms":[40],"structurally":[42],"heterogeneous,":[43],"attention-based":[44],"models":[45],"Vision":[48],"Transformers":[49],"(ViTs)":[50],"remain":[51],"underexplored.":[52],"In":[53],"work,":[55],"we":[56,104,142],"present":[57],"systematic":[59],"investigation":[60],"loss":[62],"ViTs,":[66,126],"including":[67],"fine-grained":[69],"diagnosis":[70],"using":[71,156],"local":[72],"metrics":[73],"that":[74,83,90,115,129,148,168],"capture":[75],"parameter":[76,119],"diversity":[77],"utilization.":[79],"Our":[80],"analysis":[81],"reveals":[82],"stacked":[84],"attention":[85,163],"modules":[86,97],"exhibit":[87],"increasing":[88],"instability":[89],"exacerbates":[91],"loss,":[93],"while":[94],"feed-forward":[95],"network":[96],"suffer":[98],"even":[99],"more":[100,136],"pronounced":[101],"degradation.":[102],"Furthermore,":[103],"evaluate":[105],"several":[106],"approaches":[107,128],"mitigating":[109],"loss.":[111],"The":[112],"results":[113],"indicate":[114],"methods":[116],"based":[117],"on":[118,177],"re-initialization":[120],"fail":[121],"recover":[123],"whereas":[127],"explicitly":[130],"regulate":[131],"update":[133],"process":[134],"are":[135],"effective.":[137],"Motivated":[138],"by":[139,151],"insight,":[141],"propose":[143],"ARROW,":[144],"geometry-aware":[146],"optimizer":[147],"preserves":[149],"adaptively":[152],"reshaping":[153],"gradient":[154],"directions":[155],"an":[157],"online":[158],"curvature":[159],"estimate":[160],"module.":[164],"Extensive":[165],"experiments":[166],"show":[167],"ARROW":[169],"effectively":[170],"improves":[171],"maintains":[174],"better":[175],"performance":[176],"newly":[178],"encountered":[179],"tasks.":[180]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-11T00:00:00"}