SANTS adaptively chooses denoising depth in video-based robot action diffusion policies using a state-dependent stopping hazard and noise ratio, trained via downstream action reward to reduce latency.
Spectrally-Guided Diffusion Noise Schedules
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Denoising diffusion models are widely used for high-quality image and video generation. Their performance depends on noise schedules, which define the distribution of noise levels applied during training and the sequence of noise levels traversed during sampling. Noise schedules are typically handcrafted and require manual tuning across different resolutions. In this work, we propose a principled way to design per-instance noise schedules for pixel diffusion, based on the image's spectral properties. By deriving theoretical bounds on the efficacy of minimum and maximum noise levels, we design ``tight'' noise schedules that eliminate redundant steps. During inference, we propose to conditionally sample such noise schedules. Experiments show that our noise schedules improve generative quality of single-stage pixel diffusion models, particularly in the low-step regime.
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SANTS: A State-Adaptive Scheduler for World Action Models
SANTS adaptively chooses denoising depth in video-based robot action diffusion policies using a state-dependent stopping hazard and noise ratio, trained via downstream action reward to reduce latency.