SOURCE-LINKED INTELLIGENCE

Limits of Confidence in Diffusion

arXiv · Artificial Intelligence · article · Sep 17, 2026 · UTC

Discrete diffusion, including remasking and uniform-state samplers, generate a sequence by writing multiple token positions per step, drawing each from a per-position distribution and choosing which positions to write from those same distributions. For domains of general interest (pixels, phonemes, or words) there are inherent dependencies between tokens. We show that a step matches the training distribution only when the positions it writes are conditionally independent given the tokens already fixed, that no product of per-position distributions can match a dependent group, and that per-posi

Read original source ↗ Open in workspace

recordType

paper

region

Global