TabPack debuts: a practical tabular baseline trainable on a MacBook
RichmanRonald · x · 2026-10-30
The author announced TabPack, a practical baseline for medium-to-large tabular datasets that is competitive out of the box on benchmarks and can be trained on a modern MacBook. Alongside it, TabPackage, a Python package for training TabPack and building similar models, offers both a PyTorch API (tabpackage.train(...)) and a scikit-learn API (tabpackage.sklearn.TabPackClassifier(...)).
Related event: Yandex Open-Sources TabPack, a Tabular Baseline Trainable on a MacBook(3 posts)→
More from Research
- Stanford study: walking boosts creative thinking scores in 81% of participants — beechinour · 2026-10-31
- New monograph argues 20-watt neuromorphic AI can complement power-hungry transformers — ziv_ravid · 2026-10-31
- Study: none of today's SOTA latent world models faithfully model environment dynamics — udmrzn · 2026-10-31
- kalomaze shares LoRA finetuning loss curves: 3 epochs plus WSD decay beats 1-epoch regime — kalomaze · 2026-10-31
- Fused Zip-NeRF: CUDA rewrite trains 6-7x faster, renders 10x faster on a 5090 — jon_barron · 2026-10-31
- Simulated eval reliably detects direction of model gains, not magnitude — SRSchmidgall · 2026-10-31