{"id":"https://openalex.org/W7128472237","doi":"https://doi.org/10.48550/arxiv.2602.07940","title":"MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning","display_name":"MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning","publication_year":2026,"publication_date":"2026-02-08","ids":{"openalex":"https://openalex.org/W7128472237","doi":"https://doi.org/10.48550/arxiv.2602.07940"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.07940","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":"article","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/A5124957911","display_name":"Guanglong Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Guanglong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124906887","display_name":"Hongwei Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Hongwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125488911","display_name":"Liyuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Liyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044584521","display_name":"Zhiqi Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Zhiqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125587910","display_name":"Shuang Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Shuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125478245","display_name":"Hang Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Hang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125584546","display_name":"Jun Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125542724","display_name":"Yi Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Yi","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16685037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9818000197410583,"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":0.9818000197410583,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.003000000026077032,"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":0.0020000000949949026,"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/exploit","display_name":"Exploit","score":0.718999981880188},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6980999708175659},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5932000279426575},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5530999898910522},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5494999885559082},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.414900004863739},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3935000002384186},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3828999996185303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487000226974487},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.718999981880188},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6980999708175659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6255000233650208},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5932000279426575},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5873000025749207},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.414900004863739},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3828999996185303},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.36629998683929443},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29159998893737793},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2680000066757202}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.07940","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.2602.07940","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.07940","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":"pmh:doi:10.48550/arxiv.2602.07940","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":[{"display_name":"Quality Education","score":0.4027371108531952,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"To":[0],"cope":[1],"with":[2],"uncertain":[3],"changes":[4],"of":[5,129,147,175],"the":[6,61,114,144],"external":[7],"world,":[8],"intelligent":[9],"systems":[10],"must":[11],"continually":[12],"learn":[13],"from":[14,103],"complex,":[15],"evolving":[16],"environments":[17],"and":[18,39,63,79,106,178,188,193],"respond":[19],"in":[20,59,72,82,181],"real":[21],"time.":[22],"This":[23,97],"ability,":[24],"collectively":[25],"known":[26],"as":[27,36,119,143,163],"general":[28],"continual":[29,52],"learning":[30,53,131],"(GCL),":[31],"encapsulates":[32],"practical":[33],"challenges":[34],"such":[35],"online":[37],"datastreams":[38],"blurry":[40],"task":[41,101],"boundaries.":[42],"Although":[43],"leveraging":[44],"pretrained":[45,115,148,179],"models":[46],"(PTMs)":[47],"has":[48],"greatly":[49,125],"advanced":[50],"conventional":[51],"(CL),":[54],"these":[55],"methods":[56],"remain":[57],"limited":[58],"reconciling":[60],"diverse":[62],"temporally":[64],"mixed":[65],"information":[66],"along":[67],"a":[68,108,120,139,164,173,182],"single":[69],"pass,":[70],"resulting":[71],"sub-optimal":[73],"GCL":[74,134,152,176],"performance.":[75],"Inspired":[76],"by":[77],"meta-plasticity":[78],"reconstructive":[80],"memory":[81],"neuroscience,":[83],"we":[84],"introduce":[85],"here":[86],"an":[87],"innovative":[88],"approach":[89,98],"named":[90],"Meta":[91],"Post-Refinement":[92],"(MePo)":[93],"for":[94,157],"PTMs-based":[95],"GCL.":[96],"constructs":[99],"pseudo":[100],"sequences":[102],"pretraining":[104,122],"data":[105],"develops":[107],"bi-level":[109],"meta-learning":[110],"paradigm":[111],"to":[112,132,153],"refine":[113],"backbone,":[116],"which":[117],"serves":[118,162],"prolonged":[121],"phase":[123],"but":[124],"facilitates":[126],"rapid":[127],"adaptation":[128],"representation":[130,149],"downstream":[133],"tasks.":[135],"MePo":[136,161],"further":[137],"initializes":[138],"meta":[140],"covariance":[141],"matrix":[142],"reference":[145],"geometry":[146],"space,":[150],"enabling":[151],"exploit":[154],"second-order":[155],"statistics":[156],"robust":[158],"output":[159],"alignment.":[160],"plug-in":[165],"strategy":[166],"that":[167],"achieves":[168],"significant":[169],"performance":[170],"gains":[171],"across":[172],"variety":[174],"benchmarks":[177],"checkpoints":[180],"rehearsal-free":[183],"manner":[184],"(e.g.,":[185],"15.10\\%,":[186],"13.36\\%,":[187],"12.56\\%":[189],"on":[190],"CIFAR-100,":[191],"ImageNet-R,":[192],"CUB-200":[194],"under":[195],"Sup-21/1K).":[196],"Our":[197],"source":[198],"code":[199],"is":[200],"available":[201],"at":[202],"\\href{https://github.com/SunGL001/MePo}{MePo}":[203]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-02-11T00:00:00"}