3 papers
cs.LG2025
Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity
Zichen Liu, Wei Zhang, Tiejun Li
Euclidean diffusion models have achieved remarkable success in generative modeling across diverse domains, and they have been extended to manifold cases in recent advances. Instead…
cs.LG2025
Riemannian Denoising Diffusion Probabilistic Models
Zichen Liu, Wei Zhang, Christof Schütte +1
We propose Riemannian Denoising Diffusion Probabilistic Models (RDDPMs) for learning distributions on submanifolds of Euclidean space that are level sets of functions, including mo…
math.OC2024
On finding optimal collective variables for complex systems by minimizing the deviation between effective and full dynamics
Wei Zhang, Christof Schütte
This paper is concerned with collective variables, or reaction coordinates, that map a discrete-in-time Markov process in to a (much) smaller dimension $k \ll…