Flow Group Reward Policy Optimization

Concept

An algorithm adapted from the LLM field for image generation, aiming to increase diversity of generated images for a given prompt and using relative rewards to update the model policy.

Mentioned in 1 video

Videos Mentioning Flow Group Reward Policy Optimization

Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 6 - Model Training

Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 6 - Model Training

Stanford Online

An algorithm adapted from the LLM field for image generation, aiming to increase diversity of generated images for a given prompt and using relative rewards to update the model policy.