EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

The Current Generation of Tabular Foundation Models: A Critical Review

Sergei O. Kurashkin, Vadim S. Tynchenko, Aleksei S. Borodulin, Vladimir A. Nelyub, Nikolay O. Kalutsky, Tee Connie

Machine Learning and Knowledge Extraction · 2026-08-13 · 8 (8) · 244

DOI: 10.3390/make8080244 ↗

At a glance

Journal article in Machine Learning and Knowledge Extraction, published online on 2026-08-13. Written by Sergei O. Kurashkin and 5 co-authors. Cited 1 times so far (Crossref); 152 references. The full text is freely available (open access, CC BY 4.0).

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Tabular foundation models (TFMs) have moved tabular machine learning from per-dataset training towards amortised in-context inference, fitting a small-to-medium table in a single forward pass without a training run. The 2024–2026 release train, the TabPFN and TabICL lines and challengers such as Mitra, LimiX and Orion, has produced a generation whose architectures, capabilities and limits are documented mainly in preprints, while existing surveys treat these models as a subsection of tabular deep learning or of language-model table understanding. This review is, to our knowledge, the first organised around the current generation. From a corpus of 961 screened records and 98 retained studies, it taxonomises the architectures by pretraining regime, maps the capability space across five axes, isolates the language-model-on-tabular strand for prediction, feature engineering and generation, and summarises openness and deployment. A dedicated critical synthesis then reads the reported capabilities against independent evidence: on the studies reviewed here, tree-based and deep models retain the lead across 142 curated datasets that go beyond the standard independent and identically distributed setting; on 112 datasets, the models attain the highest accuracy but weaker conditional coverage than gradient-boosted trees; and robustness under feature shift, fairness and generation quality remain open. Amortised in-context prediction is thus a working paradigm whose independent evidence has yet to match its benchmark claims.

Cite

APA

Kurashkin, S. O., Tynchenko, V. S., Borodulin, A. S., Nelyub, V. A., Kalutsky, N. O., & Connie, T. (2026). The Current Generation of Tabular Foundation Models: A Critical Review. Machine Learning and Knowledge Extraction, 8(8), 244. https://doi.org/10.3390/make8080244

Vancouver

Kurashkin SO, Tynchenko VS, Borodulin AS, Nelyub VA, Kalutsky NO, Connie T. The Current Generation of Tabular Foundation Models: A Critical Review. Machine Learning and Knowledge Extraction. 2026;8(8):244. doi:10.3390/make8080244

BibTeX
@article{Kurashkin2026,
  author = {Kurashkin, Sergei O. and Tynchenko, Vadim S. and Borodulin, Aleksei S. and Nelyub, Vladimir A. and Kalutsky, Nikolay O. and Connie, Tee},
  title = {The Current Generation of Tabular Foundation Models: A Critical Review},
  journal = {Machine Learning and Knowledge Extraction},
  year = {2026},
  volume = {8},
  number = {8},
  pages = {244},
  doi = {10.3390/make8080244}
}
Start for free →