SOURCE-LINKED INTELLIGENCE

A Ticket from Marginals to Joints: Coupled-Noise Distillation for One-Step Block Generation in Diffusion Language Models

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Diffusion language models (dLLMs) predict all tokens of a block in parallel, but a single forward pass samples each position from its own marginal distribution, so the tokens need not form a coherent block. We ask whether a discrete masked model can commit an entire block in one pass when its mask embeddings are perturbed by a sampled Gaussian noise field: the same noise should give the same coherent continuation, and different noise should give different ones. We propose CONDOR (Coupled-Noise Distillation for One-Step Readout), which trains such a model from scratch without a target-side enco

Read original source ↗ Open in workspace

recordType

paper

region

Global