{"id":"https://openalex.org/W7131814777","doi":"https://doi.org/10.48550/arxiv.2602.22586","title":"TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion","display_name":"TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion","publication_year":2026,"publication_date":"2026-02-26","ids":{"openalex":"https://openalex.org/W7131814777","doi":"https://doi.org/10.48550/arxiv.2602.22586"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.22586","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008996322","display_name":"Donghong Cai","orcid":"https://orcid.org/0000-0001-5350-135X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cai, Donghong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069049743","display_name":"Jiarui Feng","orcid":"https://orcid.org/0000-0002-3409-6819"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Jiarui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127414237","display_name":"Yanbo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yanbo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127149647","display_name":"Da Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Da","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127122542","display_name":"Yixin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yixin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127240039","display_name":"Muhan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Muhan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5008996322"],"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/T10028","display_name":"Topic Modeling","score":0.2134000062942505,"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/T10028","display_name":"Topic Modeling","score":0.2134000062942505,"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":0.15000000596046448,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.08100000023841858,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7799999713897705},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5396000146865845},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5038999915122986},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.42289999127388},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3986999988555908},{"id":"https://openalex.org/keywords/diffusion-process","display_name":"Diffusion process","score":0.36079999804496765},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.3361000120639801}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7799999713897705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218000292778015},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5396000146865845},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4708000123500824},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41609999537467957},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3750999867916107},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.36079999804496765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3481999933719635},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C500300565","wikidata":"https://www.wikidata.org/wiki/Q925667","display_name":"Computer simulation","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C2780411076","wikidata":"https://www.wikidata.org/wiki/Q5462653","display_name":"Fluent","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C48753275","wikidata":"https://www.wikidata.org/wiki/Q11216","display_name":"Numerical analysis","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.22586","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.22586","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.22586","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":"pmh:doi:10.48550/arxiv.2602.22586","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.8261206746101379,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Synthetic":[0],"tabular":[1,21,132],"data":[2,13,133],"generation":[3,134],"has":[4],"attracted":[5],"growing":[6],"attention":[7,173],"due":[8],"to":[9,82,90,193],"its":[10],"importance":[11],"for":[12,130],"augmentation,":[14],"foundation":[15],"models,":[16],"and":[17,36,60,71,87,119,151,196],"privacy.":[18],"However,":[19],"real-world":[20],"datasets":[22],"increasingly":[23],"contain":[24],"free-form":[25,131],"text":[26,84,92],"fields":[27],"(e.g.,":[28],"reviews":[29],"or":[30,76,109],"clinical":[31],"notes)":[32],"alongside":[33],"structured":[34],"numerical":[35,70,111,159],"categorical":[37,72,152],"attributes.":[38],"Generating":[39],"such":[40],"heterogeneous":[41],"tables":[42],"with":[43,161],"joint":[44,137],"modeling":[45,115,158],"of":[46,116,190],"different":[47],"modalities":[48],"remains":[49],"challenging.":[50],"Existing":[51],"approaches":[52],"broadly":[53],"fall":[54],"into":[55],"two":[56],"categories:":[57],"diffusion-based":[58],"methods":[59],"LLM-based":[61,96,197],"methods.":[62],"Diffusion":[63],"models":[64,146,149],"can":[65,106],"capture":[66],"complex":[67],"dependencies":[68],"over":[69],"features":[73,153,160],"in":[74],"continuous":[75,163],"discrete":[77,104],"spaces,":[78],"but":[79],"extending":[80],"them":[81],"open-ended":[83],"is":[85],"nontrivial":[86],"often":[88],"leads":[89],"degraded":[91],"quality.":[93],"In":[94,121],"contrast,":[95],"generators":[97],"naturally":[98],"produce":[99],"fluent":[100],"text,":[101],"yet":[102],"their":[103],"tokenization":[105],"distort":[107],"precise":[108],"wide-range":[110],"values,":[112],"hindering":[113],"accurate":[114],"both":[117],"numbers":[118],"language.":[120],"this":[122],"work,":[123],"we":[124],"propose":[125],"TabDLM,":[126],"a":[127,136,162,179],"unified":[128],"framework":[129],"via":[135],"numerical--language":[138],"diffusion":[139,144,164],"model":[140],"built":[141],"on":[142,184],"masked":[143,155],"language":[145],"(MDLMs).":[147],"TabDLM":[148,191],"textual":[150],"through":[154,166],"diffusion,":[156],"while":[157],"process":[165],"learned":[167],"specialized":[168],"numeric":[169],"tokens":[170],"embedding;":[171],"bidirectional":[172],"then":[174],"captures":[175],"cross-modality":[176],"interactions":[177],"within":[178],"single":[180],"model.":[181],"Extensive":[182],"experiments":[183],"diverse":[185],"benchmarks":[186],"demonstrate":[187],"the":[188],"effectiveness":[189],"compared":[192],"strong":[194],"diffusion-":[195],"baselines.":[198]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-28T00:00:00"}