SURE learns sample-adaptive variance in a latent reward model and uses that variance to weight dense post-training feedback, improving image and video diffusion alignment in reported experiments.
Psychological Review , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training
SURE learns sample-adaptive variance in a latent reward model and uses that variance to weight dense post-training feedback, improving image and video diffusion alignment in reported experiments.