trends.barnas.net

method · first seen 15 Oct 2026

reinforcement learning for diffusion models

Also: diffusion RL, flow matching RL, policy optimization for diffusion language models, reinforcement learning from reward optimization for diffusion and flow models

Applying reinforcement learning to align diffusion-based generators with reward signals after pretraining.

Mentions per week

0219 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

attention routingdiffusion language modelfew-step diffusion sampling