Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors
–Neural Information Processing Systems
Recent advancements in solving Bayesian inverse problems have spotlighted de-noising diffusion models (DDMs) as effective priors. Although these have great potential, DDM priors yield complex posterior distributions that are challenging to sample.
Neural Information Processing Systems
Oct-10-2025, 13:29:52 GMT