Jonas is a Machine Learning researcher in Tübingen, where he leads the research group for safety & efficiency-aligned learning (🦭). Before this, he spent time at the Universities of Maryland, Siegen and Münster.
Jonas is constantly fascinated by questions of safety and efficiency in modern machine learning. There are a number of fundamental machine learning questions that come up in these topics that we still do not understand well. On the safety side, he investigates how models can be manipulated through data poisoning, jailbreaks, and adversarial attacks. He’s curious about watermarking for generative models, privacy guarantees in machine learning, and the challenge of defining “safety” in a meaningful technical way. Are there feasible technical solutions that reduce harm?
For efficiency, he studies how we can build systems that do more with less, from weight averaging techniques to recursive computation approaches that extend model capabilities. Jonas is particularly interested in how these systems reason, and whether we can enhance their reasoning abilities while maintaining efficiency. How do we build mechanisms that let these models learn to be intelligent systems? At the core of his research is this intersection: Can we make models that reason well without sacrificing safety? How do computational constraints affect safety guarantees? Can we design systems where intelligence and safety reinforce each other?
