{"id":"https://openalex.org/W7160634598","doi":"https://doi.org/10.48550/arxiv.2605.06501","title":"Cubit: Token Mixer with Kernel Ridge Regression","display_name":"Cubit: Token Mixer with Kernel Ridge Regression","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160634598","doi":"https://doi.org/10.48550/arxiv.2605.06501"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.06501","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06501","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.2605.06501","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135658069","display_name":"Chuanyang Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Chuanyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135689943","display_name":"Jiankai Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Jiankai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135687585","display_name":"Yihang Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Yihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135682644","display_name":"Yuehao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuehao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135702482","display_name":"Liangchen Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Liangchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135672156","display_name":"Mac Schwager","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schwager, Mac","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135695213","display_name":"Anderson Schneider","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schneider, Anderson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135649265","display_name":"Yuriy Nevmyvaka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nevmyvaka, Yuriy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135711515","display_name":"Xiaodong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xiaodong","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/T10036","display_name":"Advanced Neural Network Applications","score":0.5483999848365784,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5483999848365784,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.12470000237226486,"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":0.05130000039935112,"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":0.6486999988555908},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6010000109672546},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.49470001459121704},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.4650000035762787},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45500001311302185},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.41999998688697815},{"id":"https://openalex.org/keywords/rectification","display_name":"Rectification","score":0.3675000071525574},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.33709999918937683}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6486999988555908},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6010000109672546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.527999997138977},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.49470001459121704},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4666999876499176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4657999873161316},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.4650000035762787},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45500001311302185},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.3675000071525574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3497999906539917},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.3336000144481659},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C38976095","wikidata":"https://www.wikidata.org/wiki/Q752641","display_name":"Asymmetry","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C200695384","wikidata":"https://www.wikidata.org/wiki/Q1739319","display_name":"Kernel regression","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C32277403","wikidata":"https://www.wikidata.org/wiki/Q740445","display_name":"Ridge","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.06501","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06501","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.2605.06501","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06501","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Since":[0],"its":[1,190],"introduction":[2],"in":[3,16,36,49],"2017,":[4],"the":[5,11,32,46,66,88,98,104,118,121,126,132,138,159,194,200],"Transformer":[6,90,195],"has":[7],"become":[8],"one":[9],"of":[10,107,120],"most":[12],"widely":[13],"adopted":[14],"architectures":[15],"modern":[17],"deep":[18],"learning.":[19],"Despite":[20],"extensive":[21],"efforts":[22],"to":[23,166,197],"improve":[24,125],"positional":[25],"encoding,":[26],"attention":[27,47,100,163],"mechanisms,":[28],"and":[29,64],"feed-forward":[30],"networks,":[31],"core":[33],"token-mixing":[34],"mechanism":[35,164],"Transformers":[37,50],"remains":[38],"attention.":[39],"In":[40,188],"this":[41,72,171],"work,":[42],"we":[43,74,129],"show":[44],"that":[45,81,147,180],"module":[48],"can":[51],"be":[52],"interpreted":[53],"as":[54,149,199],"performing":[55],"Nadaraya-Watson":[56,93,167],"regression,":[57],"where":[58],"it":[59],"computes":[60],"similarities":[61,114],"between":[62],"tokens":[63],"aggregates":[65],"corresponding":[67],"values":[68],"accordingly.":[69],"Motivated":[70],"by":[71,102],"perspective,":[73],"propose":[75,131],"Cubit,":[76,148],"a":[77,142,150,154],"potential":[78],"next-generation":[79],"architecture":[80],"leverages":[82],"Kernel":[83],"Ridge":[84],"Regression":[85],"(KRR),":[86],"while":[87],"vanilla":[89,160],"relies":[91],"on":[92],"regression.":[94,168],"Specifically,":[95],"Cubit":[96,181],"modifies":[97],"classical":[99],"computation":[101],"incorporating":[103],"closed-form":[105],"solution":[106],"KRR,":[108],"combining":[109],"value":[110,139],"aggregation":[111],"through":[112,173],"kernel":[113,122],"with":[115],"normalization":[116],"via":[117],"inverse":[119],"matrix.":[123],"To":[124],"training":[127,201],"stability,":[128],"further":[130],"Limited-Range":[133],"Rescale":[134],"(LRR),":[135],"which":[136],"rescales":[137],"layer":[140],"within":[141],"controlled":[143],"range.":[144],"We":[145,169],"argue":[146],"KRR-based":[151],"architecture,":[152],"provides":[153],"stronger":[155,184],"mathematical":[156],"foundation":[157],"than":[158],"Transformer,":[161],"whose":[162],"corresponds":[165],"validate":[170],"claim":[172],"comprehensive":[174],"experiments.":[175],"The":[176],"experimental":[177],"results":[178],"suggest":[179],"may":[182],"exhibit":[183],"long-sequence":[185],"modeling":[186],"capability.":[187],"particular,":[189],"performance":[191],"gain":[192],"over":[193],"appears":[196],"increase":[198],"sequence":[202],"length":[203],"grows.":[204]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-09T00:00:00"}