The discrete diffusion NELBO equals data entropy plus an exact path KL to the oracle reverse process, and the denoiser, cavity, and score parameterizations are three interconvertible coordinates of the unique optimal reverse jump rate.
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
years
2026 2roles
method 1polarities
use method 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
-
What Does a Discrete Diffusion Model Learn?
The discrete diffusion NELBO equals data entropy plus an exact path KL to the oracle reverse process, and the denoiser, cavity, and score parameterizations are three interconvertible coordinates of the unique optimal reverse jump rate.
-
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.