DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling
Published in arXiv preprint, 2026
This paper proposes Dynamic Gradient Weighting (DyWeight), a lightweight, learning-based multi-step solver for efficient diffusion sampling that achieves superior visual fidelity with significantly fewer function evaluations.
Recommended citation: T Zhao, M Lei, L Yuan, Y Yang, C Song, Y Wang, B Zhu, C Zhang. (2026). "DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling." arXiv preprint arXiv:2603.11607.
Download Paper