Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning
This work adds a persistent hidden state to a diffusion denoiser and removes its timestep conditioning, leaving a single shared update that can be run to arbitrary depth, and develops an anytime solver that keeps improving with inference depth far beyond the rollout lengths and backpropagation window used in training.
M. Drozdova, Aidan Sirbu, Pietro Miotti et al.
· 0 citations