Author name: Frederic Wang, Katherine L. Bouman

arXiv:2604.21066v2 Announce Type: replace-cross
Abstract: While diffusion priors generate high-quality posterior samples across many inverse problems, they are often trained on limited training sets or purely simulated data, thus inheriting the errors…

arXiv:2604.21066v1 Announce Type: new
Abstract: While diffusion priors generate high-quality posterior samples across many inverse problems, they are often trained on limited training sets or purely simulated data, thus inheriting the errors and biase…