{"id":"https://openalex.org/W7154452972","doi":"https://doi.org/10.48550/arxiv.2604.12596","title":"KumoRFM-2: Scaling Foundation Models for Relational Learning","display_name":"KumoRFM-2: Scaling Foundation Models for Relational Learning","publication_year":2026,"publication_date":"2026-04-14","ids":{"openalex":"https://openalex.org/W7154452972","doi":"https://doi.org/10.48550/arxiv.2604.12596"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.12596","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12596","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.12596","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125158160","display_name":"Valter Hudovernik","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hudovernik, Valter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133714069","display_name":"Federico Elizondo Lopez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L\u00f3pez, Federico","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014343147","display_name":"Vid Kocijan","orcid":"https://orcid.org/0000-0002-2621-6390"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kocijan, Vid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080192897","display_name":"Akihiro Nitta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nitta, Akihiro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073462022","display_name":"Jan Eric Lenssen","orcid":"https://orcid.org/0000-0003-4093-9840"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lenssen, Jan Eric","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133671433","display_name":"Jure Leskovec","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leskovec, Jure","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002742256","display_name":"Matthias Fey","orcid":"https://orcid.org/0000-0002-5727-0701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fey, Matthias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5125158160"],"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.30250000953674316,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.30250000953674316,"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":0.23019999265670776,"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/T10028","display_name":"Topic Modeling","score":0.1315000057220459,"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":0.5709999799728394},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5485000014305115},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.45719999074935913},{"id":"https://openalex.org/keywords/statistical-relational-learning","display_name":"Statistical relational learning","score":0.4546000063419342},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.423799991607666},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41119998693466187},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.41110000014305115},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.39879998564720154},{"id":"https://openalex.org/keywords/relational-model","display_name":"Relational model","score":0.3813000023365021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718500018119812},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5709999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5690000057220459},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5485000014305115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49799999594688416},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.4546000063419342},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.3813000023365021},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3628000020980835},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.30880001187324524},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2624000012874603}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.12596","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12596","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.12596","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12596","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":"article"},"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":{"We":[0],"introduce":[1],"KumoRFM-2,":[2],"the":[3,79,85,90,97,169],"next":[4],"iteration":[5],"of":[6,29,69,116,158],"a":[7,26,66,172],"pre-trained":[8],"foundation":[9,36,174],"model":[10,175],"for":[11],"relational":[12,42,206],"data.":[13,124,163],"KumoRFM-2":[14,38,64,105,141,202],"supports":[15],"in-context":[16],"learning":[17],"as":[18,20,109,111],"well":[19],"fine-tuning":[21],"and":[22,71,81,89,93,119,132,136,144,161],"is":[23,168],"applicable":[24],"to":[25,34,74,102,122,149,179,198,204],"wide":[27],"range":[28],"predictive":[30],"tasks.":[31],"In":[32,100],"contrast":[33,101],"tabular":[35],"models,":[37],"natively":[39],"operates":[40],"on":[41,128,183],"data,":[43],"processing":[44],"one":[45],"or":[46,55],"more":[47],"connected":[48],"tables":[49],"simultaneously":[50],"without":[51],"manual":[52],"table":[53,87],"flattening":[54],"target":[56],"variable":[57],"generation,":[58],"all":[59],"while":[60,151,194],"preserving":[61],"temporal":[62],"consistency.":[63],"leverages":[65],"large":[67],"corpus":[68],"synthetic":[70],"real-world":[72],"data":[73],"pre-train":[75],"across":[76],"four":[77],"axes:":[78],"row":[80],"column":[82],"dimensions":[83,95],"at":[84,96],"individual":[86],"level,":[88],"foreign":[91],"key":[92],"cross-sample":[94],"database":[98],"level.":[99],"its":[103],"predecessor,":[104],"injects":[106],"task":[107],"information":[108],"early":[110],"possible,":[112],"enabling":[113],"sharper":[114],"selection":[115],"task-relevant":[117],"columns":[118],"improved":[120],"robustness":[121],"noisy":[123,162],"Through":[125],"extensive":[126],"experiments":[127],"41":[129],"challenging":[130],"benchmarks":[131],"analysis":[133],"around":[134],"expressivity":[135],"sensitivity,":[137],"we":[138],"demonstrate":[139],"that":[140],"outperforms":[142],"supervised":[143,181],"foundational":[145],"approaches":[146,182],"by":[147],"up":[148],"8%,":[150],"maintaining":[152],"strong":[153],"performance":[154,188],"under":[155],"extreme":[156],"settings":[157],"cold":[159],"start":[160],"To":[164],"our":[165],"knowledge,":[166],"this":[167],"first":[170],"time":[171],"few-shot":[173],"has":[176],"been":[177],"shown":[178],"surpass":[180],"common":[184],"benchmark":[185],"tasks,":[186],"with":[187],"further":[189],"improving":[190],"upon":[191],"fine-tuning.":[192],"Finally,":[193],"KumoRFM-1":[195],"was":[196],"limited":[197],"small-scale":[199],"in-memory":[200],"datasets,":[201],"scales":[203],"billion-scale":[205],"datasets.":[207]},"counts_by_year":[],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2026-04-16T00:00:00"}