DIDR aligns one-step diffusion generators by propagating reward-tilted distributions across noise levels, achieving better preference alignment than multi-step teachers in a single step.
𝑠ref istrainedfor10,000stepsviaDSMonsamplesfrom 𝑞0 (Adam,lr=3 ×10−4, batch 2,048)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL
DIDR aligns one-step diffusion generators by propagating reward-tilted distributions across noise levels, achieving better preference alignment than multi-step teachers in a single step.