2026-09-23T14:12:08.350Z
- url:
https://arxiv.org/abs/2609.20581v1→ https://arxiv.org/abs/2609.20581
SOURCE-LINKED INTELLIGENCE
Limits of Confidence in Diffusion
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
Evidence & attribution
- arXiv · Artificial Intelligence · 2026-09-17T15:36:53.000Z
- arXiv · AI, language, vision and robotics · 2026-09-17T15:36:53.000Z
First collected: 2026-09-19T20:26:32.566Z. This is not the publication date.
Observed changes
AIIC observation times, not verified publisher revision times. Up to eight recent revisions.