RPU stabilizes the prior update in diffusion inverse solvers to reduce measurement-conditioned hallucinations, with reported gains on FFHQ and ImageNet.
Rods: Robust optimization inspired diffusion sampling for detecting and reducing hallucination in generative models.arXiv preprint arXiv:2507.12201, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates
RPU stabilizes the prior update in diffusion inverse solvers to reduce measurement-conditioned hallucinations, with reported gains on FFHQ and ImageNet.