Score: 1

Particle-Guided Diffusion Models for Partial Differential Equations

Published: January 30, 2026 | arXiv ID: 2601.23262v1

By: Andrew Millard, Fredrik Lindsten, Zheng Zhao

Potential Business Impact:

Makes computer models follow science rules better.

Business Areas:
Simulation Software

We introduce a guided stochastic sampling method that augments sampling from diffusion models with physics-based guidance derived from partial differential equation (PDE) residuals and observational constraints, ensuring generated samples remain physically admissible. We embed this sampling procedure within a new Sequential Monte Carlo (SMC) framework, yielding a scalable generative PDE solver. Across multiple benchmark PDE systems as well as multiphysics and interacting PDE systems, our method produces solution fields with lower numerical error than existing state-of-the-art generative methods.

Country of Origin
πŸ‡ΈπŸ‡ͺ Sweden

Page Count
25 pages

Category
Computer Science:
Machine Learning (CS)