Adaptive correction scheduling for hard constraints in generative sampling recovers 71% of stepwise projection benefits using 75% fewer corrections by focusing on trajectory-perturbing steps.
Adadiff: Adaptive step selection for fast diffusion
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Reward Forcing combines EMA-Sink tokens and Rewarded Distribution Matching Distillation to deliver state-of-the-art streaming video generation at 23.1 FPS without copying initial frames.
citing papers explorer
-
Enforcing Constraints in Generative Sampling via Adaptive Correction Scheduling
Adaptive correction scheduling for hard constraints in generative sampling recovers 71% of stepwise projection benefits using 75% fewer corrections by focusing on trajectory-perturbing steps.
-
Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
Reward Forcing combines EMA-Sink tokens and Rewarded Distribution Matching Distillation to deliver state-of-the-art streaming video generation at 23.1 FPS without copying initial frames.