Patrick Egenlauf

Patrick Egenlauf

(he/him)

Doctoral researcher

University of Stuttgart

SimTech Cluster of Excellence

International Max Planck Research School for Intelligent Systems (IMPRS-IS)

Interchange Forum for Reflecting on Intelligent Systems (IRIS)

About

I am a doctoral researcher working on coarse-graining non-equilibrium many-body dynamics with generative machine learning. I am interested in approaches that remain theoretically sound while solving real problems.

My goal is to develop concise, interpretable approaches that help researchers understand complex dynamical systems and build better tools for analysis and approximation.

Research interests

Coarse-graining Non-equilibrium many-body dynamics Generative machine learning Scientific computing
Research focus

My work focuses on coarse-graining non-equilibrium many-body dynamics with generative machine learning.

I care about three things in particular:

  • reducing complexity without losing physical meaning
  • building models that are interpretable and useful
  • combining domain knowledge with data-driven discovery
Publications
Patrick Egenlauf, Hannes A. Kröninger, Arnulf Kung, Mario U. Gaimann, Miriam Klopotek (2026). Entropy production of active matter systems as indicator for computing performance. arXiv preprint.
URL PDF Preprint
Patrick Egenlauf, Iva Březinová, Sabine Andergassen, Miriam Klopotek (2026). Capturing reduced-order quantum many-body dynamics out of equilibrium via neural ordinary differential equations. Machine Learning: Science and Technology.
URL DOI
Patrick Egenlauf, Patric Rommel, Jörg Main (2024). Gaussian-process-regression-based method for the localization of exceptional points in complex resonance spectra. Machine Learning: Science and Technology.
URL DOI
Beyond my research

Topics I am interested in and would like to understand better, and what I do in my spare time.

Physics
Particle physics
Astronomy
Machine learning
Reinforcement learning
Diffusion models
Frontier LLMs
Computing
Cybersecurity
Rust
Python
Free time
Flag football
Sports in general
Supervision and collaboration

I am happy to talk to students, researchers, and companies interested in scientific machine learning, physics-informed modeling, and tools for complex systems.

If you are reaching out about a project, please include a short summary of the problem and the kind of collaboration you have in mind.