Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design

arXiv:2602.04663v3 Announce Type: replace-cross Abstract: Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion…

Read the full story at arXiv cs.AI ↗