{"id":"https://openalex.org/W7163914667","doi":"https://doi.org/10.48550/arxiv.2606.07345","title":"TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention","display_name":"TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention","publication_year":2026,"publication_date":"2026-06-05","ids":{"openalex":"https://openalex.org/W7163914667","doi":"https://doi.org/10.48550/arxiv.2606.07345"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.07345","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.07345","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.2606.07345","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124405354","display_name":"Si-Yang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Si-Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138105234","display_name":"Han-Jia Ye","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/T10036","display_name":"Advanced Neural Network Applications","score":0.47290000319480896,"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":0.47290000319480896,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.25999999046325684,"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":0.0737999975681305,"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/inference","display_name":"Inference","score":0.7042999863624573},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6801000237464905},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6098999977111816},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5591999888420105},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5357000231742859},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4194999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677000164985657},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7042999863624573},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6801000237464905},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6098999977111816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5674999952316284},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5357000231742859},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4381999969482422},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.07345","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.07345","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.2606.07345","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.07345","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":{"Tabular":[0],"foundation":[1,31,109],"models,":[2],"exemplified":[3],"by":[4],"TabPFN,":[5],"perform":[6],"prediction":[7],"via":[8],"in-context":[9,147],"learning,":[10],"inferring":[11],"test":[12],"labels":[13],"directly":[14],"from":[15],"labeled":[16],"training":[17],"examples.":[18],"They":[19],"have":[20],"demonstrated":[21],"competitive":[22,68,105],"performance,":[23],"particularly":[24],"on":[25],"small-to-medium":[26],"datasets.":[27],"However,":[28],"recent":[29],"tabular":[30,108,146],"models":[32,110],"often":[33],"improve":[34,91],"accuracy":[35],"with":[36,69,106],"increasingly":[37],"complex":[38],"architectures,":[39],"incurring":[40],"higher":[41],"inference":[42,136],"cost":[43],"and":[44,57,78,90,101,103,114,144],"limiting":[45],"practical":[46,150],"deployment.":[47],"In":[48],"this":[49],"work,":[50],"we":[51,125],"revisit":[52],"the":[53],"original":[54],"TabPFN":[55,112],"design":[56],"show":[58],"that":[59,86,133],"a":[60,73,79],"lightweight":[61],"row-wise":[62],"attention-only":[63],"backbone":[64],"can":[65],"remain":[66],"highly":[67],"two":[70],"simple":[71],"enhancements:":[72],"gated":[74],"attention":[75],"stabilization":[76],"mechanism":[77,132],"small":[80],"set":[81],"of":[82],"learnable":[83],"register":[84],"tokens":[85],"provide":[87],"global":[88],"context":[89],"pretraining":[92],"quality.":[93],"The":[94],"resulting":[95],"model,":[96],"TabSwift,":[97],"supports":[98],"both":[99],"classification":[100],"regression,":[102],"is":[104],"stronger":[107],"(e.g.,":[111],"v2":[113],"TabICL)":[115],"while":[116],"being":[117],"more":[118],"efficient":[119,143],"at":[120],"inference.":[121],"For":[122],"latency-sensitive":[123],"serving,":[124],"further":[126],"introduce":[127],"an":[128],"adaptive":[129],"layer-wise":[130],"early-exit":[131],"dynamically":[134],"adjusts":[135],"depth":[137],"per":[138],"sample.":[139],"Overall,":[140],"TabSwift":[141],"enables":[142],"anytime":[145],"learning":[148],"for":[149],"deployments.":[151]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-09T00:00:00"}