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. Can Tabular Foundation Models Amortize Statistical Inference?

    Sep 27, 2026Kai Ye, Shijin Gong, Hongyi Zhou +2Amortized InferenceConfidence Region Estimation

  2. Benchmarking Attention for Tabular Foundation Models

    Sep 25, 2026Maximilian Schambach, Clemens Biehl, Sam ThelinTabular Foundation ModelsEfficient Attention

  3. SwitchPFN: Shared Switching Dynamics for Frozen In-Context Time Series Classification

    Sep 24, 2026Zhenyi Zhu, Jacqueline Pang, Peilin Shen +7Tabular Foundation ModelsTime Series Classification

  4. Learning to Fluctuate: Statistical Foundations for Causal Tabular Pretraining

    Sep 22, 2026Zhiheng ZhangCausal Foundation ModelsSynthetic Data Pretraining

  5. A JEPA Recipe for Tabular Foundation Models

    Sep 22, 2026Mingyu Jeon, Suwan Cho, Jae Young SuhTabular Foundation ModelsSelf-Supervised Pre-Training

  6. Causilo Technical Report

    Sep 19, 2026Minyong Cho, Minho Jeong, Dooho Lee +2Tabular Foundation ModelsTabular Prediction

  7. Benchmarking Tabular Foundation Models as Surrogates in Expensive Evolutionary Optimization

    Sep 16, 2026Lu Han, Jin Wang, Yuchen Li +5Tabular Foundation ModelsSurrogate-Assisted Optimization

  8. TabPFN-3.5: Technical Report

    Sep 15, 2026Benjamin Jäger, Nick Erickson, Léo Grinsztajn +44Tabular Foundation ModelsInference-Time Optimization

  9. Attention Quantization for Tabular Foundation Models

    Sep 11, 2026Jonas M. Kübler, Benjamin Jäger, Klemens Flöge +2Efficient Transformer InferenceTabular Foundation Models

  10. The Anatomy and Boundary of Adaptation under Temporal Tabular Shift

    Sep 10, 2026Tianyu Wang, Xi Vincent Wang, Lihui Wang +2Tabular Foundation ModelsDistribution Shift

  11. Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models

    Sep 10, 2026Raad Bin Tareaf, Murad Al-Rajab, Samia Loucif +2Data LeakageTabular Foundation Models

  12. Streaming Hierarchical Inference with Tabular Foundation Models

    Sep 7, 2026Vitor Crista, Afonso Lourenço, Diogo Martinho +1Tabular Foundation ModelsEfficient Inference

  13. TabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical Tables

    Sep 7, 2026Jules Kreuer, Sofiane Ouaari, Julia Hellmig +2Tabular Foundation ModelsTabular ML

  14. LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models

    Sep 5, 2026Mingqi Yang, Zidong Guo, Jihui Yang +1In-Context LearningRetrieval-Augmented ICL

  15. Adaptation Interfaces for In-Context Tabular Foundation Models in Time-to-Event Prediction

    Sep 4, 2026Minh-Khoi Pham, Luca Cotugno, Dan Cernei +8Event Time PredictionTabular Foundation Models

  16. Mitra-v2 Technical Report

    Sep 3, 2026Yefan Tao, Xiyuan Zhang, Xinyi Liu +13Tabular Foundation ModelsTabular Prediction

  17. Do Tabular Foundation Models Know Physics? Contamination, Units, and the Deterministic Limit

    Sep 2, 2026Wassim Tenachi, Yashar Hezaveh, Laurence Perreault Levasseur +1Tabular Foundation ModelsPhysical Reasoning

  18. TSPFN: A Temporal Tabular Foundation Model for Physiological Time Series Classification

    Aug 31, 2026Jérémie Stym-Popper, Clément Rambour, Federica Granese +2Tabular Foundation ModelsTime Series Classification

  19. Foundation models for electricity price forecasting and battery arbitrage: Can they replace market-specific forecasting models?

    Aug 31, 2026Arkadiusz Lipiecki, Rafał WeronTabular Foundation ModelsElectricity Price Forecasting

  20. SOMTab: Set-Order Mamba for Efficient Tabular In-Context Learning

    Aug 28, 2026Hao Wang, Siyu Zhang, Wei MaTabular ICLTabular Foundation Models

  21. EXAONE Tabular 1.0 : Technical Report

    Aug 26, 2026Moonjung Eo, Min-Kook Suh, Hye-Seung Cho +4Tabular Foundation ModelsTabular ICL