{"id":"https://openalex.org/W7140207329","doi":"https://doi.org/10.48550/arxiv.2603.21928","title":"The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation","display_name":"The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7140207329","doi":"https://doi.org/10.48550/arxiv.2603.21928"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.21928","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21928","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":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.2603.21928","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lai, Guannan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lai, Guannan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou, Da-Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Da-Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Zhenguo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhenguo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Ye, Han-Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Han-Jia","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":0.5648000240325928,"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":0.5648000240325928,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.2775000035762787,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.016899999231100082,"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/subspace-topology","display_name":"Subspace topology","score":0.7989000082015991},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5882999897003174},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5055999755859375},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4887000024318695},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4620000123977661},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4260999858379364},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.3628999888896942},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.3617999851703644},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3416999876499176}],"concepts":[{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7989000082015991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6811000108718872},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5882999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5358999967575073},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4595000147819519},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.3628999888896942},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34389999508857727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31380000710487366},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C2778701210","wikidata":"https://www.wikidata.org/wiki/Q28130034","display_name":"Constructive","level":3,"score":0.25429999828338623},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.21928","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21928","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.21928","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21928","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":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":{"Continual":[0],"Test-Time":[1],"Adaptation":[2],"(CTTA)":[3],"aims":[4],"to":[5,8,11,44,126],"enable":[6,83],"models":[7],"adapt":[9],"online":[10,37,84],"unlabeled":[12],"data":[13],"streams":[14],"under":[15],"distribution":[16],"shift":[17],"without":[18,107],"accessing":[19],"source":[20],"data.":[21],"Existing":[22],"CTTA":[23],"methods":[24],"face":[25],"an":[26,99],"efficiency-generalization":[27],"trade-off:":[28],"updating":[29],"more":[30],"parameters":[31],"improves":[32],"adaptation":[33,47,67,119],"but":[34],"severely":[35],"reduces":[36],"inference":[38],"efficiency.":[39],"An":[40],"ideal":[41],"solution":[42],"is":[43,142,169],"achieve":[45],"comparable":[46],"with":[48,74],"minimal":[49,55],"feature":[50],"updates;":[51],"we":[52,89,113],"call":[53],"this":[54,87],"subspace":[56,132,141],"the":[57,75,79,91,104,130,140],"golden":[58,131],"subspace.":[59],"We":[60],"prove":[61],"its":[62],"existence":[63],"in":[64],"a":[65,123,135],"single-step":[66],"setting":[68],"and":[69,133,151,164],"show":[70],"that":[71,158],"it":[72],"coincides":[73],"row":[76],"space":[77],"of":[78,86],"pretrained":[80],"classifier.":[81],"To":[82],"maintenance":[85],"subspace,":[88],"introduce":[90],"sample-wise":[92],"Average":[93],"Gradient":[94],"Outer":[95],"Product":[96],"(AGOP)":[97],"as":[98],"efficient":[100],"proxy":[101],"for":[102],"estimating":[103],"classifier":[105],"weights":[106],"retraining.":[108],"Building":[109],"on":[110,149],"these":[111],"insights,":[112],"propose":[114],"Guided":[115],"Online":[116],"Low-rank":[117],"Directional":[118],"(GOLD),":[120],"which":[121],"uses":[122],"lightweight":[124],"adapter":[125],"project":[127],"features":[128],"onto":[129],"learns":[134],"compact":[136],"scaling":[137],"vector":[138],"while":[139],"dynamically":[143],"updated":[144],"via":[145],"AGOP.":[146],"Extensive":[147],"experiments":[148],"classification":[150],"segmentation":[152],"benchmarks,":[153],"including":[154],"autonomous-driving":[155],"scenarios,":[156],"demonstrate":[157],"GOLD":[159],"attains":[160],"superior":[161],"efficiency,":[162],"stability,":[163],"overall":[165],"performance.":[166],"Our":[167],"code":[168],"available":[170],"at":[171],"https://github.com/AIGNLAI/GOLD.":[172]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-25T00:00:00"}