A single diffusion policy network with per-factor null-token dropout enables additive score composition for robot control under conditional independence, with a trajectory-tube certificate, shown to generalize on drone racing tasks.
International Conference on Learning Representations (ICLR) , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
Non-monotonic sampling schedules never improve upon monotonic baselines in diffusion models, with performance gaps ranging from substantial to negligible depending on the denoiser.
citing papers explorer
-
Factored Diffusion Policies:Compositionally Generalized Robot Control with a Single Score Network
A single diffusion policy network with per-factor null-token dropout enables additive score composition for robot control under conditional independence, with a trajectory-tube certificate, shown to generalize on drone racing tasks.
-
Is Monotonic Sampling Necessary in Diffusion Models?
Non-monotonic sampling schedules never improve upon monotonic baselines in diffusion models, with performance gaps ranging from substantial to negligible depending on the denoiser.