Saved in:
Bibliographic Details
Main Authors: Na, Kunwoo, Lee, Junghyun, Yun, Se-Young, Lim, Sungbin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.10219
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Recent advances in infinite-dimensional diffusion models have demonstrated their effectiveness and scalability in function generation tasks where the underlying structure is inherently infinite-dimensional. To accelerate inference in such models, we derive, for the first time, an analog of the probability-flow ODE (PF-ODE) in infinite-dimensional function spaces. Leveraging this newly formulated PF-ODE, we reduce the number of function evaluations while maintaining sample quality in function generation tasks, including applications to PDEs.