TabPFN outperforms published models on three energetic-material properties
Untuned TabPFN on Chemprop embeddings beats Chemprop itself and is more than ten times faster than XGBoost.
34
Untuned TabPFN on Chemprop embeddings beats Chemprop itself and is more than ten times faster than XGBoost.
Researchers adapt TabPFN features for tabular anomaly detection, with ZEN and FOCUS beating ADBench baselines.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views