EUVIMEDEUVIMED entdecken
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 · 13.08.2026 · 8 (8) · 244

DOI: 10.3390/make8080244 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 13.08.2026. Verfasst von Sergei O. Kurashkin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 152 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

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}
}
Kostenlos starten →