A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.
arXiv preprint arXiv:2410.08134 , year =
2 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
2
Pith papers citing it
2
external citations · external index
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Coupling Models enable single-step discrete sequence generation via learned couplings to Gaussian latents and outperform prior one-step baselines on text perplexity, biological FBD, and image FID metrics.
citing papers explorer
-
Adaptive Order Policies for Masked Diffusion
A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.
-
Coupling Models for One-Step Discrete Generation
Coupling Models enable single-step discrete sequence generation via learned couplings to Gaussian latents and outperform prior one-step baselines on text perplexity, biological FBD, and image FID metrics.