Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees

ArXi:2605.05387v1 Announce Type: new We study zero-shot conditional sampling with pretrained diffusion models for linear inverse problems, including inpainting and super-resolution. In these problems, the observation determines only part of the unknown signal. The remaining degrees of freedom must be sampled according to the correct conditional data distribution. Existing projection-based samplers enforce measurement consistency by correcting the observed component during reverse diffusion.