3 papers
cs.LG2026
DGPO: RL-Steered Graph Diffusion for Neural Architecture Generation
Aleksei Liuliakov, Luca Hermes, Barbara Hammer
Reinforcement learning fine-tuning has proven effective for steering generative diffusion models toward desired properties in image and molecular domains. Graph diffusion models ha…
cs.LG2026
Drift Localization using Conformal Predictions
Fabian Hinder, Valerie Vaquet, Johannes Brinkrolf +1
Concept drift -- the change of the distribution over time -- poses significant challenges for learning systems and is of central interest for monitoring. Understanding drift is thu…
cs.LG2024
Koopman-Based Surrogate Modelling of Turbulent Rayleigh-Bénard Convection
Thorben Markmann, Michiel Straat, Barbara Hammer
Several related works have introduced Koopman-based Machine Learning architectures as a surrogate model for dynamical systems. These architectures aim to learn non-linear measureme…