PhD Researcher · CISPA Helmholtz Center · Technical University of Munich
Better known as “Oscar” 😊
I am a Ph.D. student at Technical University of Munich working at the CISPA Helmholtz Center for Information Security. I am also a member of the TUM Graduate School.
My primary research interest is Machine Learning. More broadly, I am interested in exploring underutilized mathematical frameworks and adapting them to machine learning settings, bridging the gap between abstract theory and practical algorithms. In this direction, my current work engages with Neural ODEs as continuous-depth models for dynamical systems, and Rough Path Theory as a general mathematical tool for sequence modeling.
ICLR 20262026
Proposes FlowReg, a neural ODE-based regularization method for reinforcement learning that aligns an agent's latent representation with the underlying environment dynamics by modeling MDP trajectories as ODE flows. Integrated into Actor-Critic algorithms, it improves performance across Atari environments.
ACM CCS 20262026
Presents a reinforcement learning framework for proof search in the Tamarin security protocol verifier, inspired by AlphaZero and AlphaProof. A stateless Tamarin API exposes proof search as a classical RL environment, in which Monte Carlo Tree Search is guided by a neural heuristic that learns from completed subproofs. Across 16 case studies, it finds more proofs automatically than Tamarin's standard search and produces shorter proofs than both the standard and human-engineered heuristics.
NeurIPS 20262026