Martin Wertich

Martin Wertich

MSc student at ETH Zurich working on machine learning theory, statistical learning, and high-dimensional systems

Publications

You can also find my articles on my Google Scholar profile.

Conference Papers

ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning

Published in International Conference on Machine Learning (ICML), 2026

Authors: Davit Melikidze*, Marian Schneider*, Jessica Lam*, Martin Wertich*, Ido Hakimi, Barna Pásztor, and Andreas Krause

* Equal contribution

ACTIVEULTRAFEEDBACK introduces a modular active learning pipeline that uses uncertainty-aware reward estimates to select informative response pairs, reducing the amount of preference data needed for strong downstream performance.

Paper BibTeX Blog Code Dataset Poster