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.
Not currently ranked — collecting fresh signals.
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.
Frequently asked
- What is 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.
- Is awesome-alignment-of-diffusion-models open source?
- Yes — xie-lab-ml/awesome-alignment-of-diffusion-models is open source, released under the MIT license.
- How popular is awesome-alignment-of-diffusion-models?
- xie-lab-ml/awesome-alignment-of-diffusion-models has 430 stars on GitHub.
- Where can I find awesome-alignment-of-diffusion-models?
- xie-lab-ml/awesome-alignment-of-diffusion-models is on GitHub at https://github.com/xie-lab-ml/awesome-alignment-of-diffusion-models.