Hallucinations in diffusion models are driven by local intrinsic dimension instabilities on the manifold, which Intrinsic Quenching corrects by deflating it.
Gradcheck: Analyzing classifier guid- ance gradients for conditional diffusion sampling
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
C²FG provides a time-dependent guidance controller for diffusion models derived from score discrepancy upper bounds, implemented as an exponential decay function without retraining.
citing papers explorer
-
Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models
Hallucinations in diffusion models are driven by local intrinsic dimension instabilities on the manifold, which Intrinsic Quenching corrects by deflating it.
-
C$^2$FG: Control Classifier-Free Guidance via Score Discrepancy Analysis
C²FG provides a time-dependent guidance controller for diffusion models derived from score discrepancy upper bounds, implemented as an exponential decay function without retraining.