Efficient Reinforcement Learning for Diffusion Models

Applying language-model reinforcement-learning recipes directly to diffusion trajectories is costly in both computation and memory. This talk examines objectives, likelihood estimation and rollout design for diffusion post-training. An estimator based on a forward-process variational bound separates training from rollout and permits fast ODE sampling, producing substantial speed improvements. A related first-order stochastic-control approach is also considered.