Denis Blessing

Learning Boltzmann Generators via Constrained Mass Transport

Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference

DIME: Diffusion-Based Maximum Entropy Reinforcement Learning

MaNGO — Adaptable Graph Network Simulators via Meta-Learning

Underdamped Diffusion Bridges with Applications to Sampling

End-to-end Learning of Gaussian Mixture Priors for Diffusion Sampler

Sequential Controlled Langevin Diffusions

Scaffolding Dexterous Manipulation with Vision-Language Models