My name is Jan, I am a master’s student in computer science at EPFL and a research assistant at the Autonomous Systems Group at the University of Texas at Austin, where I work on Large Language Models (LLMs) in strategy games.

At a high level, I am interested in understanding how our mind works and in building machines that can perceive, think, and learn. Practically speaking, my research focuses on reverse-engineering deep learning models to understand the internal mechanisms that give rise to intelligent behavior, how these mechanisms emerge during training, and why they break down in long-horizon or unfamiliar settings. I study neural networks both post-hoc and throughout training, linking training signals and optimization dynamics to the internal algorithms models form and the behaviors that follow. My goal is a scientific understanding that (i) enables principled training and architecture design, and (ii) yields insights into human learning and cognition.

I am always happy to discuss these topics, so if you have related thoughts or questions, please do not hesitate to contact me.