How Deep Learning Finally Cracked Messy Tables - Frank Hutter

Frank Hutter, co-founder of Prior Labs, talks about TabPFN, a tabular foundation model that makes predictions in a single forward pass, and the research behind it. TabPFN is pre-trained on synthetic datasets drawn from a prior over structural causal models, rather than on real data. At prediction time it takes the whole training table as context and outputs an approximation of the Bayesian posterior predictive distribution, without per-dataset training or hyperparameter search. Frank explains how this grew out of his earlier work on AutoML and neural architecture search, how the priors are built and revised, and why tabular data was hard for deep learning for so long. The conversation also covers the TabArena benchmark, how the architecture changed from TabPFN v1 to v3, scaling to larger tables, using the model with coding agents, test-time compute, Google's TabFM, causal inference and interventions, and relational data. At the end, a short update Frank recorded after the interview covers the TabPFN-3.5 release. TOC: 00:00 Introduction 00:44 Welcome and Frank's background 02:05 Why tabular data was hard for deep learning 07:50 Why there is little public tabular data 10:17 Pre-training on synthetic data 12:52 The TabArena benchmark 19:28 From AutoML to neural architecture search 26:34 TabPFN as a learned algorithm 30:50 Bayesian prediction in one forward pass 39:37 Scaling to larger tables 43:47 Why LLMs struggle with large tables 47:48 Using TabPFN with coding agents 55:15 Beyond classification and regression 57:47 Output heads and architecture from v1 to v3 1:05:29 Test-time compute and adaptation 1:12:26 Interpolation and extrapolation 1:13:32 Google's TabFM 1:16:53 How the priors are designed 1:18:40 Correlation, causation and interventions 1:29:06 Causal foundation models 1:33:21 Language models and numerical data 1:35:22 Relational and multimodal data 1:38:31 Use in organisations 1:46:38 The open research arm 1:50:21 Update: TabPFN-3.5 1:52:38 Closing REFS: AdamW (Loshchilov & Hutter) https://arxiv.org/abs/1711.05101 SGDR (Loshchilov & Hutter) https://arxiv.org/abs/1608.03983 TabNet (Arik & Pfister) https://arxiv.org/abs/1908.07442 Deep Sets (Zaheer et al.) https://arxiv.org/abs/1703.06114 TabPFN v2, Nature (Hollmann et al., 2025) https://www.nature.com/articles/s41586-024-08328-6 Transformers Can Do Bayesian Inference (Müller et al.) https://arxiv.org/abs/2112.10510 TabArena (Erickson et al.) https://arxiv.org/abs/2506.16791 AutoGluon-Tabular (Erickson et al.) https://arxiv.org/abs/2003.06505 Beyond IID: How General Are Tabular Foundation Models, Really? https://arxiv.org/abs/2606.30410 Neural Architecture Search: A Survey (Elsken, Metzen & Hutter) https://arxiv.org/abs/1808.05377 Auto-WEKA (Thornton et al.) https://www.cs.ubc.ca/~hutter/papers/AutoWEKA-KDD2013.pdf TabPFN v1 (Hollmann et al., 2022) https://arxiv.org/abs/2207.01848 TabPFN-3 technical report https://arxiv.org/abs/2605.13986 TabPFN-2.5 report https://arxiv.org/abs/2511.08667 CAAFE (Hollmann et al.) https://arxiv.org/abs/2305.03403 TabICL (Qu et al.) https://arxiv.org/abs/2502.05564 TabICLv2 (Qu et al.) https://arxiv.org/abs/2602.11139 TuneTables (Feuer et al.) https://arxiv.org/abs/2402.11137 A Spline Theory of Deep Networks (Balestriero & Baraniuk) https://proceedings.mlr.press/v80/balestriero18b.html Google TabFM https://research.google/blog/introducing-tabfm-a-zero-shot-foundation-model-for-tabular-data/ TALENT benchmark (Ye et al.) https://arxiv.org/abs/2407.00956 Do-PFN (Robertson et al.) https://arxiv.org/abs/2506.06039 CausalPFN (Balazadeh et al.) https://arxiv.org/abs/2506.07918 Causal Foundation Models with Partial Graphs (Reuter et al.) https://arxiv.org/abs/2602.14972 RelBench (Robinson et al.) https://arxiv.org/abs/2407.20060 RelArena-α, TabPFN-Rel and RPI https://arxiv.org/abs/2608.16319 TabPFN on GitHub https://github.com/PriorLabs/TabPFN Prior Labs technical reports https://priorlabs.ai/technical-reports TabPFN-3.5 technical report https://arxiv.org/abs/2609.17895 TabPFN-3.5 model page (Prior Labs) https://priorlabs.ai/tabpfn-3-5 Otto Group Product Classification Challenge (Kaggle, 2015) https://www.kaggle.com/competitions/otto-group-product-classification-challenge --- RESCRIPT: https://app.rescript.info/share/e99676c25ee6189fbf54c9be07eb623e