{"id":"https://openalex.org/W7161679050","doi":"https://doi.org/10.48550/arxiv.2605.18383","title":"TabH2O: A Unified Foundation Model for Tabular Prediction","display_name":"TabH2O: A Unified Foundation Model for Tabular Prediction","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7161679050","doi":"https://doi.org/10.48550/arxiv.2605.18383"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.18383","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18383","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.18383","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011087717","display_name":"Pascal Pfeiffer","orcid":"https://orcid.org/0000-0002-5064-1514"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pfeiffer, Pascal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136475419","display_name":"Dmitry Gordeev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gordeev, Dmitry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136491715","display_name":"Mathias M\u00fcller","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M\u00fcller, Mathias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136481094","display_name":"Laura Fink","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fink, Laura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092856777","display_name":"Joan Salv\u00e0 Soler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soler, Joan Salv\u00e0","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136464390","display_name":"Mark Landry","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Landry, Mark","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136483009","display_name":"Branden Murray","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murray, Branden","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016588193","display_name":"Marcos V. Conde","orcid":"https://orcid.org/0000-0002-5823-4964"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Conde, Marcos V.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5093836241","display_name":"Sri Satish Ambati","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ambati, Sri Satish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.3792000114917755,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.3792000114917755,"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":0.14409999549388885,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.07429999858140945,"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/robustness","display_name":"Robustness (evolution)","score":0.6545000076293945},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5497000217437744},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49380001425743103},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.48840001225471497},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4772000014781952},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.43790000677108765},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4350000023841858},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41179999709129333}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6545000076293945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6247000098228455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6207000017166138},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6139000058174133},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5497000217437744},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49380001425743103},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4851999878883362},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4772000014781952},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C61722155","wikidata":"https://www.wikidata.org/wiki/Q6667643","display_name":"Logistic model tree","level":3,"score":0.3416000008583069},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C70259352","wikidata":"https://www.wikidata.org/wiki/Q1847839","display_name":"Robust regression","level":3,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.18383","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18383","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.18383","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18383","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.7131854295730591,"display_name":"Quality Education","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":{"We":[0,107],"present":[1],"TabH2O,":[2],"a":[3,15,35,44],"foundation":[4],"model":[5,37,102],"for":[6,50,77],"tabular":[7],"data":[8],"that":[9],"performs":[10],"classification":[11,40,164],"and":[12,41,53,89,139,147,165],"regression":[13,42,166],"in":[14,154],"single":[16,36],"forward":[17],"pass":[18],"via":[19,43],"in-context":[20],"learning.":[21],"TabH2O":[22,109],"builds":[23],"on":[24,113,157],"the":[25,48,75,87,101,114,155,160],"TabICL":[26,149],"architecture":[27],"with":[28,83,143],"several":[29],"key":[30],"modifications:":[31],"(1)":[32],"unified":[33],"training,":[34],"handles":[38],"both":[39],"dual-head":[45],"architecture,":[46],"eliminating":[47],"need":[49,76],"separate":[51],"models":[52],"reducing":[54],"total":[55],"pretraining":[56],"cost;":[57],"(2)":[58],"single-stage":[59],"pretraining,":[60,92],"training":[61,82],"stability":[62],"improvements":[63],"(bounded":[64],"scalable":[65],"softmax,":[66],"inter-stage":[67],"normalization,":[68],"learnable":[69],"residual":[70],"scaling,":[71],"logit":[72],"soft-capping)":[73],"eliminate":[74],"multi-stage":[78],"curriculum":[79],"learning,":[80],"enabling":[81],"full-length":[84],"sequences":[85],"from":[86],"start;":[88],"(3)":[90],"noise-aware":[91],"synthetic":[93],"datasets":[94,162],"include":[95],"explicit":[96],"noise":[97],"dimensions":[98],"to":[99,104],"teach":[100],"robustness":[103],"irrelevant":[105],"features.":[106],"evaluate":[108],"v1":[110],"(29.2M":[111],"parameters)":[112],"TALENT":[115],"benchmark":[116],"(300":[117],"datasets),":[118],"where":[119],"it":[120],"achieves":[121],"an":[122],"average":[123],"rank":[124],"of":[125,128,159],"2.55":[126],"out":[127],"6":[129],"evaluated":[130],"methods,":[131],"outperforming":[132],"tuned":[133],"CatBoost":[134],"(4.07),":[135],"H2O":[136],"AutoML":[137],"(4.18),":[138],"LightGBM":[140],"(5.08),":[141],"competitive":[142],"TabPFN":[144],"v2.6":[145],"(2.74),":[146],"behind":[148],"v2":[150],"(2.12),":[151],"while":[152],"placing":[153],"top-3":[156],"81%":[158],"testing":[161],"across":[163],"tasks.":[167]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-20T00:00:00"}