Julius Berner

Researcher, NVIDIA

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Guided Diffusion Sampling on Function Spaces with Applications to PDEs

#2204 · Jiachen Yao, Abbas Mammadov, Julius Berner, Gavin Kerrigan, Jong Chul Ye, Kamyar Azizzadenesheli, Anima Anandkumar

We present a general framework to solve inverse PDE problems through function space diffusion models in a plug-and-play way.

Poster Session 6

1 paper

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

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

#502 Spotlight · Denis Blessing, Julius Berner, Lorenz Richter, Carles Domingo-Enrich, Yuanqi Du, Arash Vahdat, Gerhard Neumann

We develop trust region methods for stochastic optimal control to improve sampling from unnormalized densities, transition path sampling, and diffusion model finetuning.