Pinned Loading

1. InPO InPO Public

   [CVPR 2025 Highlight] InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment

   Python 43 3

2. SmPO SmPO Public

   [ICML 2025] Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences

   Python 29 4

3. Reward-Forcing Reward-Forcing Public

   Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation

   Python 237 12

4. xie-lab-ml/awesome-alignment-of-diffusion-models xie-lab-ml/awesome-alignment-of-diffusion-models Public

   The collection of awesome papers on alignment of diffusion models.

   386 17