One-shot Conditional Sampling: MMD meets Nearest Neighbors

ArXi:2509.25507v2 Announce Type: replace-cross How can we generate samples from a conditional distribution that we never fully observe? This question arises across a broad range of applications in both modern machine learning and classical statistics, including image post-processing in computer vision, approximate posterior sampling in simulation-based inference, and conditional distribution modeling in complex data settings. In such settings, compared with unconditional sampling, additional feature information can be leveraged to enable adaptive and efficient sampling. Building on this, we.