{"id":"https://openalex.org/W7204828645","doi":"https://doi.org/10.48550/arxiv.2608.27763","title":"Fast Weight Attention for Continual Learning","display_name":"Fast Weight Attention for Continual Learning","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204828645","doi":"https://doi.org/10.48550/arxiv.2608.27763"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.27763","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27763","pdf_url":"https://arxiv.org/pdf/2608.27763","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.27763","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126253353","display_name":"Yifan Zhang","orcid":"https://orcid.org/0009-0001-3030-9960","observed_orcids":["https://orcid.org/0009-0001-3030-9960"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Yifan","raw_affiliation_strings":["Princeton University ,","UCLA ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University ,","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"UCLA ,","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148781208","display_name":"Steve Ta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ta, Steve","raw_affiliation_strings":["Princeton University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University ,","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148793236","display_name":"Jasper Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jasper","raw_affiliation_strings":["Hyperbolic Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hyperbolic Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121634720","display_name":"Jichen Feng","orcid":"https://orcid.org/0009-0005-5497-6943","observed_orcids":["https://orcid.org/0009-0005-5497-6943"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng, Jichen","raw_affiliation_strings":["Princeton University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University ,","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148800983","display_name":"Shuzhen Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Shuzhen","raw_affiliation_strings":["Princeton University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University ,","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148768490","display_name":"Yongxin Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Yongxin","raw_affiliation_strings":["Princeton University ,","UCLA ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University ,","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"UCLA ,","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104138222","display_name":"Yifeng LIU","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Yifeng","raw_affiliation_strings":["UCLA ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA ,","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013438281","display_name":"Huizhuo Yuan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan, Huizhuo","raw_affiliation_strings":["UCLA ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA ,","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125037424","display_name":"Mengdi Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Mengdi","raw_affiliation_strings":["Princeton University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University ,","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120284571","display_name":"Quanquan Gu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gu, Quanquan","raw_affiliation_strings":["UCLA ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCLA ,","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076560802","display_name":"Andrew Chi-Chih Yao","orcid":"https://orcid.org/0000-0002-3648-5594","observed_orcids":["https://orcid.org/0000-0002-3648-5594"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Andrew Chi-Chih","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10028","display_name":"Topic Modeling","score":0.20250000059604645,"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/T10028","display_name":"Topic Modeling","score":0.20250000059604645,"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/T10320","display_name":"Neural Networks and Applications","score":0.19949999451637268,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.15919999778270721,"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/continual-learning","display_name":"continual learning","score":0.9160000085830688},{"id":"https://openalex.org/keywords/recurrent-state-space-models","display_name":"recurrent state-space models","score":0.6819999814033508},{"id":"https://openalex.org/keywords/normalized-least-mean-square-algorithm","display_name":"normalized least mean square","score":0.7910000085830688},{"id":"https://openalex.org/keywords/forgetting","display_name":"forgetting","score":0.4410000145435333},{"id":"https://openalex.org/keywords/language-modeling","display_name":"language modeling","score":0.6819999814033508},{"id":"https://openalex.org/keywords/length-extrapolation","display_name":"length extrapolation","score":0.7860000133514404}],"concepts":[{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.6305999755859375},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5953999757766724},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5231000185012817},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5055000185966492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5052000284194946},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.446399986743927},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37400001287460327},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31540000438690186},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.30230000615119934},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C2779127903","wikidata":"https://www.wikidata.org/wiki/Q6510194","display_name":"Learning rule","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.2531000077724457},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.27763","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27763","pdf_url":"https://arxiv.org/pdf/2608.27763","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.27763","doi":"https://doi.org/10.48550/arxiv.2608.27763","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.27763","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,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.27763","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27763","pdf_url":"https://arxiv.org/pdf/2608.27763","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204828645.pdf","grobid_xml":"https://content.openalex.org/works/W7204828645.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7168024256","https://openalex.org/W7118324814","https://openalex.org/W2089217417","https://openalex.org/W3100614937","https://openalex.org/W4399657692","https://openalex.org/W4412889804","https://openalex.org/W2604641217","https://openalex.org/W7160994919","https://openalex.org/W7155494918","https://openalex.org/W2952494384"],"abstract_inverted_index":{"Recurrent":[0],"fast-weight":[1],"memories":[2],"and":[3,72,89,105,121,135],"selective":[4],"state-space":[5],"models":[6],"compress":[7],"an":[8,20],"expanding":[9],"context":[10],"into":[11],"a":[12,60],"fixed-size":[13],"recurrent":[14,139],"state,":[15],"making":[16],"the":[17,33,38,47,97],"state":[18],"transition":[19],"online":[21],"learning":[22],"rule.":[23],"We":[24,64,101],"study":[25],"this":[26],"rule":[27],"under":[28],"read-after-write":[29],"autoregressive":[30],"semantics.":[31],"For":[32],"prefix-prediction":[34],"objective":[35],"considered":[36],"here,":[37],"local":[39],"fast-memory":[40],"example":[41],"revealed":[42],"at":[43],"step":[44],"$t$":[45],"is":[46],"prefix-aligned":[48],"pair":[49],"$(\\mathbf{x}_t,\\mathbf{y}_t)=(\u03d5(\\mathbf{k}_{t-1}),\\mathbf{v}_t)$.":[50],"The":[51,76],"common":[52],"same-step":[53],"association":[54],"$(\u03d5(\\mathbf{k}_t),\\mathbf{v}_t)$":[55],"remains":[56],"causal,":[57],"but":[58],"optimizes":[59],"different":[61],"internal":[62],"objective.":[63],"derive":[65],"normalized":[66],"first-order":[67],"updates":[68],"for":[69],"squared-error":[70],"regression":[71,77],"negative":[73],"inner-product":[74,99],"objectives.":[75],"family":[78],"comprises":[79],"Falcon-1":[80],"(a":[81,91],"scalar":[82],"NLMS":[83],"update),":[84],"Falcon-2":[85],"(its":[86],"per-column":[87],"extension),":[88],"Falcon-3":[90],"sliding-window":[92],"mini-batch":[93],"update);":[94],"Falcon-1A/Falcon-2A/Falcon-3A":[95],"are":[96],"corresponding":[98],"variants.":[100],"provide":[102],"recurrent,":[103],"masked-parallel,":[104],"chunk-parallel":[106],"forms,":[107],"together":[108],"with":[109],"numerically":[110],"stable":[111],"positive-decay":[112],"renormalization.":[113],"Representative":[114],"variants":[115],"remain":[116],"competitive":[117],"in":[118,138],"language":[119],"modeling":[120],"improve":[122],"length":[123],"extrapolation":[124],"on":[125],"variable-digit":[126],"addition.":[127],"This":[128],"framework":[129],"separates":[130],"temporal":[131],"alignment,":[132],"plasticity,":[133],"forgetting,":[134],"bounded":[136],"rehearsal":[137],"sequence":[140],"models.":[141]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-09-01T00:00:00"}