9. Diffusion Steering via RL

This paper introduces Diffusion Steering via Reinforcement Learning (DSRL), a method for adapting pretrained diffusion policies by learning in their latent-noise space instead of finetuning model weights.https://t.co/qDZKfUIIGv

— DAIR.AI (@dair_ai) 29 juin 2025

9. Diffusion Steering via RL This paper introduces Diffusion Steering via Reinforcement Learning (DSRL), a method for adapting pretrained diffusion policies by learning in their latent-noise space instead of finetuning model weights.

→ View original post on X — @dair_ai