This was a delightful collaboration with Sitan Chen, @jerryzli.bsky.social, @pangwei.bsky.social, and my wonderful advisors Lillian J. Ratliff and
@sewoong79.bsky.social. There’s lots of remaining work to be done on learning to sample that we’re excited to explore!
arxiv.org/abs/2502.17423
7/
@sewoong79.bsky.social. There’s lots of remaining work to be done on learning to sample that we’re excited to explore!
arxiv.org/abs/2502.17423
7/
S4S: Solving for a Diffusion Model Solver
Diffusion models (DMs) create samples from a data distribution by starting from random noise and iteratively solving a reverse-time ordinary differential equation (ODE). Because each step in the itera...
arxiv.org
February 27, 2025 at 6:24 PM
This was a delightful collaboration with Sitan Chen, @jerryzli.bsky.social, @pangwei.bsky.social, and my wonderful advisors Lillian J. Ratliff and
@sewoong79.bsky.social. There’s lots of remaining work to be done on learning to sample that we’re excited to explore!
arxiv.org/abs/2502.17423
7/
@sewoong79.bsky.social. There’s lots of remaining work to be done on learning to sample that we’re excited to explore!
arxiv.org/abs/2502.17423
7/
S4S-Alt achieves a 1.5-2x improvement over a “vanilla” diffusion ODE solver, particularly with few NFEs, and achieves SOTA performance for techniques that do not modify the underlying DM, while being competitive with training-based methods for a fraction of a compute cost!
6/
6/
February 27, 2025 at 6:24 PM
S4S-Alt achieves a 1.5-2x improvement over a “vanilla” diffusion ODE solver, particularly with few NFEs, and achieves SOTA performance for techniques that do not modify the underlying DM, while being competitive with training-based methods for a fraction of a compute cost!
6/
6/
Furthermore, to fully explore the DM solver design space, we learn both the discretization steps and the solver coefficients with S4S-Alt, which proceeds through alternating minimization, giving even further quality improvements.
5/
5/
February 27, 2025 at 6:24 PM
Furthermore, to fully explore the DM solver design space, we learn both the discretization steps and the solver coefficients with S4S-Alt, which proceeds through alternating minimization, giving even further quality improvements.
5/
5/
In S4S, we directly learn the coefficients for any diffusion solver by minimizing the global error in the final generated sample. S4S consistently outperforms traditional ODE solvers across model architectures and time discretizations, especially in the few-step regime.
4/
4/
February 27, 2025 at 6:24 PM
In S4S, we directly learn the coefficients for any diffusion solver by minimizing the global error in the final generated sample. S4S consistently outperforms traditional ODE solvers across model architectures and time discretizations, especially in the few-step regime.
4/
4/
Other prior work fixes the ODE solver and focuses on selecting optimal discretization steps for the reverse process. While this leads to impressive gains, it overlooks the full design space of the diffusion model solver.
3/
3/
February 27, 2025 at 6:24 PM
Other prior work fixes the ODE solver and focuses on selecting optimal discretization steps for the reverse process. While this leads to impressive gains, it overlooks the full design space of the diffusion model solver.
3/
3/
Previous work on solving diffusion ODEs focuses on minimizing numerical errors at each step of sequentially solving the ODE. This approach works well with many steps, but breaks down when the number of steps is small.
2/
2/
February 27, 2025 at 6:24 PM
Previous work on solving diffusion ODEs focuses on minimizing numerical errors at each step of sequentially solving the ODE. This approach works well with many steps, but breaks down when the number of steps is small.
2/
2/