sdpo
PublicCode for the paper "Aligning Few-Step Diffusion Models with Dense Reward Difference Learning"
Creat:2024-11-18T22:14:41
Update:2025-03-13T14:22:35
https://arxiv.org/abs/2411.11727
18
Stars
0
Stars Increase
Code for the paper "Aligning Few-Step Diffusion Models with Dense Reward Difference Learning"