Author

M. Kozyra

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Feb 2026

TASTE: Task-Aware Out-of-Distribution Detection via Stein Operators

A task-aware framework based on so-called Stein operators, which links distribution shift to the input sensitivity of the model, with theoretical guarantees, and which aligns closely with task degradation while showing competitive performance compared to established baselines.

M. Kozyra, G. Reinert · arXiv.org · 1 citation

#machine learning Preprint Oct 2026

Interfaces and Modules: A Scalable Representation for Weight-Space Learning across Architectures

Weight-space learning across architectures requires representations that respect parameter symmetries and scale to large networks. Existing equivariant tensor encoders require architecture-specific symmetry specifications, while neuron graphs make global attention costly. We introduce a typed graph organized around sha...

M. Kozyra, Michael M. Bronstein · 0 citations