Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Interpretable by Design Tabular Prediction via In-Context Local Linear Learning
Ran Eisenberg, Steven Berger, Ofir Lindenbaum
In-context learning (ICL) lets tabular foundation models make predictions without dataset-specific training or fine-tuning. These models achieve strong predictive accuracy, but int…
cs.LG2026
Learning Permutation from Structure Without Supervision
Ran Eisenberg, Ofir Lindenbaum
Many learning problems require uncovering a hidden ordering that reveals structure in unordered data, such as monotonicity in sorting or spatial continuity in jigsaw reconstruction…