TabPFN-3 delivers state-of-the-art tabular prediction performance on benchmarks up to 1M rows, is up to 20x faster than prior versions, and introduces test-time scaling that beats non-TabPFN models by hundreds of Elo points.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
unclear 2representative citing papers
TabPFN-2.5 scales tabular foundation models to 20x larger datasets, outperforms tuned tree models on TabArena, achieves near-perfect win rates against default XGBoost, and adds a distillation engine for fast production deployment.
Hycean models with a 1-bar H2 envelope, percent-level CH4 and CO, and CO2 at 10^-3 to 10^-2 reproduce the 0.8-5.2 μm JWST spectra of K2-18b.
citing papers explorer
-
TabPFN-3: Technical Report
TabPFN-3 delivers state-of-the-art tabular prediction performance on benchmarks up to 1M rows, is up to 20x faster than prior versions, and introduces test-time scaling that beats non-TabPFN models by hundreds of Elo points.
-
TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models
TabPFN-2.5 scales tabular foundation models to 20x larger datasets, outperforms tuned tree models on TabArena, achieves near-perfect win rates against default XGBoost, and adds a distillation engine for fast production deployment.
-
A Hycean Interpretation of K2-18b Supported by Photochemical Atmospheric Compositional
Hycean models with a 1-bar H2 envelope, percent-level CH4 and CO, and CO2 at 10^-3 to 10^-2 reproduce the 0.8-5.2 μm JWST spectra of K2-18b.