An information-theoretic method optimizes CFG schedules in diffusion models by targeting a reference consistency-coverage trade-off via trajectory-level estimates from samples.
Conditional diffusion models with classifier-free gibbs-like guidance,
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
-
Information-Theoretic Classifier-Free Guidance with Adaptive Schedule Optimization
An information-theoretic method optimizes CFG schedules in diffusion models by targeting a reference consistency-coverage trade-off via trajectory-level estimates from samples.