{"id":"https://openalex.org/W4415345588","doi":null,"title":"Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data","display_name":"Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data","publication_year":2025,"publication_date":"2025-07-05","ids":{"openalex":"https://openalex.org/W4415345588"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.03971","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.03971","pdf_url":"https://arxiv.org/pdf/2507.03971","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","is_traditional":true,"indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.03971","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078236933","display_name":"Anurag Garg","orcid":"https://orcid.org/0000-0001-9448-3960","observed_orcids":["https://orcid.org/0000-0001-9448-3960","https://orcid.org/0000-0003-1515-6799"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Garg, Anurag","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088317577","display_name":"Muhammad Zeeshan Ali","orcid":"https://orcid.org/0000-0002-3947-8250","observed_orcids":["https://orcid.org/0000-0002-3947-8250"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali, Muhammad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081550394","display_name":"Noah Hollmann","orcid":"https://orcid.org/0000-0001-8556-518X","observed_orcids":["https://orcid.org/0000-0001-8556-518X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hollmann, Noah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016560150","display_name":"Lennart Purucker","orcid":"https://orcid.org/0009-0001-1181-0549","observed_orcids":["https://orcid.org/0009-0001-1181-0549"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Purucker, Lennart","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036942322","display_name":"Samuel M\u00fcller","orcid":"https://orcid.org/0009-0002-2907-0961","observed_orcids":["https://orcid.org/0009-0002-2907-0961"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M\u00fcller, Samuel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031002895","display_name":"Frank Hutter","orcid":"https://orcid.org/0000-0002-2037-3694","observed_orcids":["https://orcid.org/0000-0002-2037-3694"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hutter, Frank","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":true,"cited_by_count":42,"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":0.8076000213623047,"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":0.8076000213623047,"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":0.053199999034404755,"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":0.02370000071823597,"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/tabular-foundation-models","display_name":"tabular foundation models","score":0.9509999752044678},{"id":"https://openalex.org/keywords/tabpfn","display_name":"TabPFN","score":0.8560000061988831},{"id":"https://openalex.org/keywords/continual-pre-training","display_name":"continual pre-training","score":0.9750000238418579},{"id":"https://openalex.org/keywords/real-world-data","display_name":"real-world data","score":0.8629999756813049},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"synthetic data","score":0.7940000295639038},{"id":"https://openalex.org/keywords/model-performance-improvement","display_name":"model performance improvement","score":0.3370000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664000153541565},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6243000030517578},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46799999475479126},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4065999984741211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3824000060558319},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.24480000138282776},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2442999929189682}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2507.03971","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.03971","pdf_url":"https://arxiv.org/pdf/2507.03971","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.03971","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.03971","pdf_url":"https://arxiv.org/pdf/2507.03971","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":[{"id":"https://openalex.org/G2320638626","display_name":"Deep Learning Rechencluster (Teilfinanzierung)","funder_award_id":"539134284","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G3547540627","display_name":null,"funder_award_id":"SFB1597","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G3562914802","display_name":"European Lighthouse on Secure and Safe AI","funder_award_id":"101070617","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4855614693","display_name":null,"funder_award_id":"101045765","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8615871816","display_name":"SFB 1597: Small Data","funder_award_id":"499552394","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320331321","display_name":"Hector Stiftung","ror":"https://ror.org/0427ycx88"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415345588.pdf","grobid_xml":"https://content.openalex.org/works/W4415345588.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2132862423","https://openalex.org/W2560647685","https://openalex.org/W2798476254","https://openalex.org/W2981852735","https://openalex.org/W4302009014","https://openalex.org/W4387635083","https://openalex.org/W4390833695","https://openalex.org/W4406170795","https://openalex.org/W6910681941"],"related_works":["https://openalex.org/W7196931918","https://openalex.org/W7164590380","https://openalex.org/W4416237452","https://openalex.org/W7214710076","https://openalex.org/W7128723349","https://openalex.org/W4412345347","https://openalex.org/W7213974525","https://openalex.org/W4416234289","https://openalex.org/W7164310520","https://openalex.org/W7161262295"],"abstract_inverted_index":{"Foundation":[0],"models":[1],"for":[2,47],"tabular":[3],"data,":[4],"like":[5,62],"TabPFN,":[6],"achieve":[7],"strong":[8],"performance":[9,23,72],"on":[10,16,74],"small":[11],"datasets":[12,46,76],"when":[13],"pre-trained":[14],"solely":[15],"synthetic":[17],"data.":[18],"We":[19],"show":[20],"that":[21,37],"this":[22],"can":[24],"be":[25],"significantly":[26],"boosted":[27],"by":[28],"a":[29,39],"targeted":[30],"continued":[31,48],"pre-training":[32,49],"phase.":[33],"Specifically,":[34],"we":[35],"demonstrate":[36],"leveraging":[38],"small,":[40],"curated":[41],"collection":[42],"of":[43],"large,":[44],"real-world":[45],"yields":[50],"superior":[51],"downstream":[52],"predictive":[53],"accuracy":[54],"compared":[55],"to":[56],"using":[57],"broader,":[58],"potentially":[59],"noisier":[60],"corpora":[61],"CommonCrawl":[63],"or":[64],"GitTables.":[65],"Our":[66],"resulting":[67],"model,":[68],"Real-TabPFN,":[69],"achieves":[70],"substantial":[71],"gains":[73],"29":[75],"from":[77],"the":[78],"OpenML":[79],"AutoML":[80],"Benchmark.":[81]},"counts_by_year":[{"year":2026,"cited_by_count":37},{"year":2025,"cited_by_count":5}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2025-10-20T00:00:00"}