GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver

ArXi:2510.17699v2 Announce Type: replace-cross While diffusion models achieve state-of-the-art generation quality, they still suffer from computationally expensive sampling. Recent works address this issue with gradient-based optimization methods that distill a few-step ODE diffusion solver from the full sampling process, reducing the number of function evaluations from dozens to just a few. However, these approaches often rely on intricate