Vision-Conditioned Variational Bayesian Last Layer Dynamics Models
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Paul Brunzema
PhD Student
Institute for Data Science in Mechanical Engineering (DSME), RWTH Aachen University
I am a PhD student at the Institute for Data Science in Mechanical Engineering (DSME) at RWTH Aachen University, supervised by Sebastian Trimpe, since March 2022. Since September 2023, I am also an associate doctoral researcher in the UnRAVel Research Training Group, funded by the DFG.
Currently, I am a research scientist intern at Meta in New York, NY working on Bayesian optimization and AutoML. In summer 2025, I joined the EPIC group at Toyota Research Institute (TRI) in Los Altos, CA as a research intern, working on autonomous racing in changing conditions.
My research focuses on uncertainty quantification (Gaussian processes, Bayesian neural networks) and sequential decision-making (Bayesian optimization, control, reinforcement learning).
Selected Publications
All publications →
Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch
arXiv preprint arXiv:2608.00316
Event-Triggered Time-Varying Bayesian Optimization
Transactions on Machine Learning Research (TMLR)
Bayesian Optimization via Continual Variational Last Layer Training
International Conference on Learning Representations (ICLR)
BayeSQP: Bayesian Optimization through Sequential Quadratic Programming
Advances in Neural Information Processing Systems (NeurIPS)