3 papers
cs.LG2026
Noise, Denoise, Correct: MCMC Posterior Sampling with Diffusion Priors in Three Steps
So Takao, Gregory David Bellchambers, Luke Ye +2
Pretrained diffusion models are powerful priors for inverse problems, but posterior sampling under nonlinear, non-differentiable forward models remain hard. We introduce diffusion…
stat.ML2026
Direct Intermediate Initialization for Tilted Diffusion Samplers
Gregory D. Bellchambers
Some diffusion posterior samplers construct Gaussian-tilted intermediate distributions along the reverse process. We observe that these targets can be pulled back to clean-space po…
stat.ML2025
Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
Gregory Bellchambers
The success of diffusion models has driven interest in performing conditional sampling via training-free guidance of the denoising process to solve image restoration and other inve…