xie-lab-ml/awesome-alignment-of-diffusion-models
A curated collection of research papers on aligning diffusion models with human preferences using reinforcement learning and feedback techniques.
Velocity · 7d
+0.5
★ / day
Trend
→steady
star history
This repository aggregates academic papers on techniques for aligning text-to-image diffusion models with human feedback. It covers methods like RLHF, RLAIF, reward-based fine-tuning, and direct optimization for improving model outputs. The collection includes landmark papers from top venues such as NeurIPS and ICLR.