3 papers
cs.LG2026
Interfaces and Modules: A Scalable Representation for Weight-Space Learning across Architectures
Michał Kozyra, Michael Bronstein
Weight-space learning across architectures requires representations that respect parameter symmetries and scale to large networks. Existing equivariant tensor encoders require arch…
cs.LG2026
TASER: Task-Aware Stein Regularisation for Geometry-Driven Smoothness
Michał Kozyra, Gesine Reinert
Deep neural networks remain sensitive to distribution shifts, motivating regularisation informed by data geometry. We introduce TASER (Task-Aware Stein Regularisation), a compact t…
cs.LG2026
TASTE: Task-Aware Out-of-Distribution Detection via Stein Operators
Michał Kozyra, Gesine Reinert
Out-of-distribution detection methods are often either data-centric, detecting deviations from the training input distribution irrespective of their effect on a trained model, or m…