From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion

The paper introduces committed reveal sampling (CRS), a training‑free sampler for uniform discrete diffusion models that stores selected argmax tokens as persistent context for subsequent predictions. CRS keeps these tokens visible in later model inputs, which theoretically prevents Bayes error from increasing as noise decreases and encourages consistent sequence‑level choices. Empirical tests on Duo‑distilled data show that CRS without top‑p truncation achieves lower generative perplexity than fixed‑p baselines across various numbers of function evaluations, offering a more favorable perplexity–entropy trade‑off.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• diffusion