I'm a researcher at Google Zurich. My research focuses on multimodal reasoning, representation learning, and planning under uncertainty. I'm particularly interested in how learned representations support reasoning, and how we can understand and control model behavior.
Previously, I led a research group at FZI Research Center for Information Technology and Karlsruhe Institute of Technology (KIT). I received my Ph.D. from KIT, advised by Christoph Stiller and Mykel Kochenderfer.
I engineer and align representations in deep learning models. Key aspects of my work include leveraging representation quality metrics and invariance properties of features for learning. I apply these techniques to create more interpretable and controllable models.
My research covers model-based reinforcement learning, focusing on partially observable Markov decision processes and multi-armed bandits. My work includes novelty detection, information gathering, and curriculum learning to enhance learning efficacy.
Autonomous driving serves as a major application area of my research. I develop and evaluate algorithms that operate in real-time on autonomous car prototypes to study sequential decision-making, interpretability, and generalization.