scikit-learn Co-creator Gael Varoquaux to Present TabICL Tabular Foundation Model at Paper Club
GaelVaroquaux · x · 2026-10-19
Unaite's 7th Paper Club hosts scikit-learn co-creator, Inria research director and Probabl co-founder Gael Varoquaux to present tabular foundation models.
The featured paper, TabICL: A Tabular Foundation Model for In-Context Learning on Large Data, matches TabPFN on the TALENT benchmark while being up to 10x faster at inference, and outperforms TabPFNv2 and CatBoost across 53 datasets with over 10K samples. Inference code and pretrained weights are open-sourced at github.com/soda-inria/tabicl. Event: October 21, 18:00, PariSanté Campus.
More from Research
- Agent reproduces black hole images from EHT raw data in 2 hours for ~$7 — fofrAI · 2026-10-19
- Researchers crack Google's 64-bit docid: it's a Jenkins hash fingerprint of the URL — gaganghotra_ · 2026-10-19
- The mysterious 'Chinese spirit neuron' may trace back to a Dream of the Red Chamber translation — Sauers_ · 2026-10-19
- Why native multimodal models won't win it all: they can't compress visual context — gabriberton · 2026-10-19
- 4-year bitter-lesson evolution of MLLM vision: from LLaVA crops to native-resolution images — gabriberton · 2026-10-19
- Data World paper: RL on synthetic data environments adds 20.9 points on DABstep-Hard — omarsar0 · 2026-10-19