Closing the Context Gap: Activation Alignment for Tabular In-Context Learning
Activation alignment lets tabular models use less context while recovering much of full-context accuracy.
4 stories, newest first · one card per story
Activation alignment lets tabular models use less context while recovering much of full-context accuracy.

NVIDIA released Kumo Tabular, open tabular models that predict new rows in one forward pass.
TabFM-Auto uses an agent to evolve data pipelines and leads TabArena and MLE-Bench tabular results.

Nums AI released Causilo, an Apache-2.0 tabular foundation model achieving the highest single-model Elo (1794) on TabArena for classification and regression.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views