Work with us

We always welcome motivated Master’s students to collaborate on projects at the intersection of optimization, robotics, and machine learning. If you are interested in these areas, feel free to get in touch.

About

Sebastian Sanokowski conducts research at the intersection of generative modeling and optimization. His work focuses on developing diffusion-based methods that address complex problems without relying on labeled data, with applications in optimization, robotics, and reinforcement learning. His goal is to build scalable, theoretically grounded approaches that remain robust across diverse tasks and domains. His research has been published at top machine learning conferences, including ICML, NeurIPS, and ICLR.

Selected Publications: 

1. Sanokowski, Sebastian, Sepp Hochreiter, and Sebastian Lehner. "A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization." ICML 2024.
2. Sanokowski, Sebastian, et al. "Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics." ICLR 2025.
3. Sanokowski, Sebastian, et al. "Variational Annealing on Graphs for Combinatorial Optimization." NeurIPS 2023.
4. Sanokowski, S., Gruber, L., Bartmann, C., Hochreiter, S., and Lehner, S. "Rethinking Losses for Diffusion Bridge Samplers." NeurIPS 2025.
5. Berzins, A., Radler, A., Volkmann, E., Sanokowski, S., Hochreiter, S., and Brandstetter, J. "Geometry-Informed Neural Networks." ICML 2025.
6. Sanokowski, Sebastian, and Kaustubh Patil. "A Diffusion Model Framework for Maximum Entropy Reinforcement Learning." arXiv preprint arXiv:2512.02019 (2025).

Education: 

Sebastian earned his PhD in Artificial Intelligence from Johannes Kepler University Linz, where he completed his thesis on "Data-Free Combinatorial Optimization Using Generative Neural Networks" under the supervision of Prof. Sepp Hochreiter. He holds a Master of Science and Bachelor of Science in Physics from Friedrich-Alexander-Universität Erlangen-Nürnberg.