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.
NeurIPS Workshop on Deep Generative Models and Downstream Applications , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Primal-dual guided decoding casts constrained discrete diffusion as a KL-regularized optimization solved online with adaptive Lagrangian multipliers to satisfy constraints while staying close to the unconstrained model distribution.
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.
-
Primal-Dual Guided Decoding for Constrained Discrete Diffusion
Primal-dual guided decoding casts constrained discrete diffusion as a KL-regularized optimization solved online with adaptive Lagrangian multipliers to satisfy constraints while staying close to the unconstrained model distribution.