AI RESEARCH
Principled Design of Diffusion-based Optimizers for Inverse Problems
arXiv CS.CV
•
ArXi:2605.11506v1 Announce Type: new Score-based diffusion models achieve state-of-the-art performance for inverse problems, but their practical deployment is hindered by long inference times and cumbersome hyperparameter tuning. While pretrained diffusion models can be reused across tasks without re