Leveraging Inference-Time Compute for Diffusion Models via Global Scheduling of Denoising Trajectories
The analysis from independent random search to a broader family of local search operators, and it is proved that when sensitivities vary across instances, no adaptive policy can avoid worst-case regret that grows linearly in the trajectory length.
Yuan Cao, Yi-Fu Tang, Hang-Qi Li et al.
· 0 citations