A Reversible Solver for Diffusion SDEs
Abstract
Diffusion models have quickly become the state-of-the-art for generation tasks across many different data modalities. An important ability of diffusion models is the ability to encode samples from the data distribution back into the sampling prior distribution. This is useful for performing alterations to real data samples along with guided generation via the continuous adjoint equations. We propose an *algebraically reversible* solver for diffusion SDEs that can exactly invert real data samples into the prior distribution.
Cite
Text
Blasingame and Liu. "A Reversible Solver for Diffusion SDEs." ICLR 2025 Workshops: DeLTa, 2025.Markdown
[Blasingame and Liu. "A Reversible Solver for Diffusion SDEs." ICLR 2025 Workshops: DeLTa, 2025.](https://mlanthology.org/iclrw/2025/blasingame2025iclrw-reversible/)BibTeX
@inproceedings{blasingame2025iclrw-reversible,
title = {{A Reversible Solver for Diffusion SDEs}},
author = {Blasingame, Zander W. and Liu, Chen},
booktitle = {ICLR 2025 Workshops: DeLTa},
year = {2025},
url = {https://mlanthology.org/iclrw/2025/blasingame2025iclrw-reversible/}
}