Frank Hutter on TabPFN: How Tabular Foundation Models Predict in a Single Forward Pass
Machine Learning Street Talk · rss · 2026-09-24
Machine Learning Street Talk interviews Prior Labs co-founder Frank Hutter on TabPFN, a tabular foundation model pre-trained on synthetic data drawn from a prior over structural causal models. At inference it takes the full training table as context and approximates the Bayesian posterior predictive distribution in a single forward pass — no per-dataset training or hyperparameter search.
Key topics
- Why tabular data resisted deep learning for so long, and the path from AutoML/neural architecture search to TabPFN.
- The TabArena benchmark, architecture evolution from v1 to v3, scaling to larger tables, test-time compute and adaptation.
- Using TabPFN with coding agents, Google's TabFM, causal inference and interventions, and relational data.
- Ends with an update on the TabPFN-3.5 release.
More from Research
- Tadpole: TUM uses autoencoders as foundation models for 3D PDEs with online learning — jiqizhixin · 2026-10-23
- Arc Institute's COMPASS Uses Genomic Language Models to Map Noncoding DNA Functions — anshulkundaje · 2026-10-23
- FDA crosses a regulatory watershed with personalized neoantigen cancer vaccine, per Gottlieb — alex_peys · 2026-10-23
- VIPerturb-seq Update: 10x Genomics to Commercialize Single-Cell CRISPR Screening Tech — anshulkundaje · 2026-10-23
- New Paper Replicates Transformer Loss Spikes with Simple Quadratic Models — CSProfKGD · 2026-10-23
- Diffusion Models book team to host NeurIPS 2026 tutorial on diffusion LLMs in Sydney — mittu1204 · 2026-10-23