Internal Guidance as a Sampling Method for Tilted Diffusion Models
Reward guidance methods sample an exponential tilt of a base density using a diffusion model trained with only samples from the base distribution. Existing methods use what we call external guidance: additive terms in the drift or multiplicative terms on the transition probabilities.
By Curtis McDonald, Peter BartlettarXiv - stat.ML
Read the full story
Originally published by arXiv - stat.ML on Oct 22, 2026.
Comments
Sign in to join the discussion.