Finite-particle approximation of the Doob h-function causes reward hacking via two failure modes in reward-guided diffusion; a damping schedule corrects within-mode bias in Gaussian settings.
Classifier-free guidance: From high-dimensional analysis to generalized guidance forms.arXiv preprint arXiv:2502.07849, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Are we really tilting? The mechanics of reward guidance in flow and diffusion models
Finite-particle approximation of the Doob h-function causes reward hacking via two failure modes in reward-guided diffusion; a damping schedule corrects within-mode bias in Gaussian settings.