AID amortizes guidance for diffusion inpainting by training a reusable module via an auxiliary Gaussian formulation and continuous-time actor-critic algorithm, improving quality-speed trade-off with under 1% overhead.
Haoran Wang, Thaleia Zariphopoulou, and Xun Yu Zhou
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
ART learns adaptive timestep grids for score-based diffusion sampling via continuous-time control and actor-critic RL, yielding higher sample quality than fixed schedules at matched compute while generalizing across budgets and pipelines.
ART reparameterizes diffusion sampling time and uses RL to learn optimal timestep schedules that reduce discretization error and improve generation quality across budgets and datasets.
citing papers explorer
-
Amortized Guidance for Image Inpainting with Pretrained Diffusion Models
AID amortizes guidance for diffusion inpainting by training a reusable module via an auxiliary Gaussian formulation and continuous-time actor-critic algorithm, improving quality-speed trade-off with under 1% overhead.
-
ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning
ART learns adaptive timestep grids for score-based diffusion sampling via continuous-time control and actor-critic RL, yielding higher sample quality than fixed schedules at matched compute while generalizing across budgets and pipelines.
-
ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule
ART reparameterizes diffusion sampling time and uses RL to learn optimal timestep schedules that reduce discretization error and improve generation quality across budgets and datasets.