Profile

Mateusz Pach is an ELLIS PhD researcher in the Explainable Machine Learning group at the Technical University of Munich and Helmholtz AI, supervised by Zeynep Akata and Serge Belongie. He received his Bachelor's and Master's degrees from Jagiellonian University in Krakow, where he was a member of the GMUM research group. During his studies, Mateusz worked at Amazon and G-Research. His primary research interest is understanding and adapting multimodal generative models.

Publications

"Stitch: Training-Free Position Control in Multimodal Diffusion Transformers"
Jessica Bader *, Mateusz Pach *, Maria Bravo, Serge Belongie, Zeynep Akata
In Review

"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models"
Mateusz Pach, Shyamgopal Karthik, Quentin Bouniot, Serge Belongie, Zeynep Akata
NeurIPS 2025

"LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision"
Mateusz Pach, Dawid Rymarczyk, Koryna Lewandowska, Jacek Tabor, Bartosz Zieliński
ICLR 2025

"TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration"
Jan Olszewski, Dawid Rymarczyk, Piotr Wójcik, Mateusz Pach, Bartosz Zieliński
WACV 2025