Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates 事件

Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates arXiv:2606.02331v1 Announce Type: new Abstract: Diffusion-based inverse problem solvers can produce realistic reconstructions, but realism alone does not ensure that the recovered details are supported by the measurement. We study this failure as measurement-conditioned hallucination: visually meaningful content that is either implausible or inconsistent with the measured instance. Our analysis separates Bayes-