Overview

Tabular foundation models aim to make predictions on new tables with little or no task-specific training, often by conditioning on labeled examples in context. Many use transformers or related architectures pretrained on synthetic tasks generated from causal or statistical priors; other approaches learn from real tables, retrieve relevant examples, or adapt frozen models with lightweight heads. Benchmarks such as TabArena and TALENT show strong results on many small- and medium-sized, in-distribution tasks, while gradient-boosted trees and specialized methods remain competitive, especially on large or high-dimensional data. Open challenges include robustness to distribution shift, calibrated uncertainty and fairness, and reducing the memory and inference costs of processing large contexts.

Latest papers

CardsList

209 papers23 papers in the last four weeks, down 45% on the four weeks before. 0.2% of all new papers.

  1. Tabular foundation models for non-tabular tasks

    Aug 23, 2026Goran Nakerst, John Brennan, Wouter Beugeling +1Handwritten Digit RecognitionTabular Foundation Models

  2. Tydra: An Efficient Hybrid Model for Tabular Data

    Aug 21, 2026Mieszko Komisarczyk, Saurabh Mathur, Maurice Kraus +2Hybrid Transformer-State Space Model ArchitecturesTabular Foundation Models

  3. GEAR: Generative Expansion and Real Anchoring for Two-Stage Distillation of Tabular Foundation Models

    Aug 19, 2026Qi Qin, Jiajie Zhu, Dali Chen +6Knowledge DistillationTabular Foundation Models

  4. Understanding the Surprising Generalization Properties of Tabular Foundation Models

    Aug 18, 2026Nour Shaheen, Junwei Ma, Alex Labach +3Tabular Foundation ModelsTabular ICL

  5. ARASH: Adaptive Retrieval And Shot Selection for Tabular Prediction

    Aug 18, 2026Samirasadat Jamalidinan, Yue Xu, Kazem CheshmiTabular PredictionTabular ICL

  6. Do Tabular Foundation Models Still Need Feature Engineering?

    Aug 14, 2026Yifan WU, Pinjun Dong, Jiran Tao +1Tabular Foundation ModelsTabular Prediction

  7. Training Fair Tabular Foundation Models

    Aug 14, 2026Patrik Kenfack, Jesse C. Cresswell, Anthony L. Caterini +2Tabular Foundation ModelsAlgorithmic Fairness

  8. Balanced Adaptive Prototype Selection for Scalable TabPFN Inference on Large-Scale Tabular Data

    Aug 13, 2026Mahboobe Jadid, Melika Rezaye Garkani, Ali MousaviTabular Foundation ModelsTabular ICL

  9. TACTICL: Task-Aware Compression of Tabular ICL Models

    Aug 11, 2026Mykhailo Koshil, Matthias Feurer, Katharina EggenspergerModel CompressionTabular Foundation Models

  10. SkillTFM: Gated Skill Evolution for Training-Free Adaptation of Tabular Foundation Models

    Aug 6, 2026Yi He, Zhengkang Guan, Anpeng Wu +3Tabular Foundation ModelsTest-Time Adaptation

  11. Do Tabular Foundation Models Agree with Themselves?

    Aug 6, 2026Christian Klötergens, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme +1Tabular Foundation ModelsTabular Prediction

  12. Enhancing Tabular Learners with Context-Aware Semantic Embeddings

    Aug 4, 2026Günther Schindler, Maximilian Schambach, Johannes HöhneTabular Foundation ModelsRepresentation Learning

  13. RamanPFN: A physics-guided spectral foundation framework for in-context learning across diverse Raman applications

    Aug 3, 2026Xingyu Pan, Huan Wang, Jinjia Guo +3Tabular Foundation ModelsRepresentation Learning

  14. TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction

    Aug 2, 2026Rasa Hosseinzadeh, Alex Labach, Zexin Xue +3Tabular Foundation ModelsTabular ICL

  15. From field-scale to large-scale spectral libraries: Tabular foundation models in soil spectroscopy

    Aug 1, 2026Viacheslav Barkov, Jonas Schmidinger, Robin Gebbers +1Tabular Foundation ModelsRecursive Least Squares

  16. Revisiting Predictive Process Monitoring in the Age of Foundation Models: A Comparative Study of Sequence, Tabular, and LLM Approaches

    Jul 30, 2026Lennart Fertig, Lukas Kirchdorfer, Tobias SesterhennTabular Foundation ModelsPredictive Process Monitoring

  17. Memory Efficient Tabular Foundation Models

    Jul 30, 2026Shuting Luo, Monika Mikhail Kanaan, Cameron Gordon +2Model CompressionTabular Foundation Models

  18. Understanding Context Sampling in TabPFN on Small Tabular Datasets

    Jul 29, 2026Mohammed AbdullahTabular Foundation ModelsTabular Classification

  19. Empirical Evaluation of Out-Of-Distribution Performance of Tabular Foundation Models

    Jul 28, 2026Malena Loza, David Chushig-Muzo, Eva Milara +3Distribution Shift RobustnessTabular Foundation Models

  20. In-Context Time Series Classification with Random Convolutional Features

    Jul 21, 2026Joscha Cüppers, Jilles VreekenTabular Foundation ModelsTime Series Classification

  21. Topological Signatures of Context-Level Reliability in TabPFN

    Jul 20, 2026James Hu, Mahdi GhelichiTabular Foundation ModelsNeural Representation Geometry

  22. Revisiting data-driven dynamic security assessment with a tabular foundation model

    Jul 17, 2026Olayiwola Arowolo, Maosheng Yang, Jochen CremerTabular Foundation ModelsFew-Shot Learning

  23. Tabular Foundation Models for Discrete Choice Estimation

    Jul 14, 2026Liu Liu, Dan ZhangTabular Foundation ModelsDiscrete Choice Modeling

  24. DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms

    Jul 13, 2026Yikang Chen, Zhengkang Guan, Haoyuan Qian +3Causal Foundation ModelsTabular Foundation Models

  25. Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment

    Jul 13, 2026Chunyu Hu, Tianyin Liao, Ge Lan +4Tabular Foundation ModelsGraph Representation Learning

  26. TabPATE: Differentially Private Tabular In-Context Learning Without Public Data

    Jun 30, 2026Dariush Wahdany, Matthew Jagielski, Jesse C. Cresswell +2Tabular Foundation ModelsDifferential Privacy