Introduces adjoint-equation framework establishing dimension-free convergence bounds in any IPM for discrete diffusion models under masked and uniform priors.
Advances in Neural Information Processing Systems , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Discrete diffusion models learn data support before frequencies because the exact reverse process decomposes edits into a dominant validity scale and a finer probability coefficient.
NI Sampling accelerates discrete diffusion language models up to 14.3 times by training a neural indicator to select which tokens to sample at each step using a trajectory-preserving objective.
citing papers explorer
-
Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space
Introduces adjoint-equation framework establishing dimension-free convergence bounds in any IPM for discrete diffusion models under masked and uniform priors.
-
Support Before Frequency in Discrete Diffusion
Discrete diffusion models learn data support before frequencies because the exact reverse process decomposes edits into a dominant validity scale and a finer probability coefficient.
-
NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization
NI Sampling accelerates discrete diffusion language models up to 14.3 times by training a neural indicator to select which tokens to sample at each step using a trajectory-preserving objective.