AI RESEARCH
DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling
arXiv CS.CV
•
ArXi:2603.11607v1 Announce Type: new Diffusion Models (DMs) have achieved state-of-the-art generative performance across multiple modalities, yet their sampling process remains prohibitively slow due to the need for hundreds of function evaluations. Recent progress in multi-step ODE solvers has greatly improved efficiency by reusing historical gradients, but existing methods rely on handcrafted coefficients that fail to adapt to the non-stationary dynamics of diffusion sampling.