NVIDIA open-sources Structured Data Models library unifying tabular foundation models in PyTorch
lmoroney · x · 2026-10-19
NVIDIA's new open-source Structured Data Models library puts pretrained foundation models for tabular, relational and time-series data — including TabICLv2, TabFM, KumoTabular and TimesFM3 — behind one PyTorch-compatible interface, with GPU preprocessing and an Apache 2.0 license. TabICLv2 works via in-context learning: pass labeled rows as context, get predictions with no training loop. Suggested experiment: benchmark it against your existing gradient-boosted-tree solutions.
Related event: NVIDIA Open-Sources Structured Data Foundation Model Library(2 posts)→
More from Research
- Biomedical researcher hails GPT-5 science acceleration paper with OpenAI as his most consequential work — DeryaTR_ · 2026-10-19
- Frank Nielsen paper introduces scale-of-means framework unifying Fréchet and Karcher means — FrnkNlsn · 2026-10-19
- Dust hyper-optimization delivers ~10x speedup, verified; beyond-backprop algorithms coming — burny_tech · 2026-10-19
- Leading mathematicians warn: rushing to formalize all of math with AI could do lasting damage — AlexKontorovich · 2026-10-19
- Reviewer slams 3 ICLR + 5 AAMAS submissions as too weak even for workshops — Fantastic-Nerve-4056 · 2026-10-19
- Open-source ROS 2 LiDAR localization runs 390 m outdoors on handheld Livox MID-360 — rsasaki0109 · 2026-10-19