# Learning When to Commit: Schedule Distillation for Fast Diffusion Language Models

Authors: Aidar Myrzakhan, Zhiqiang Shen.

Constructs diffusion decoding schedules that reveal tokens useful for predicting the remaining positions. Distills these schedules into the model while keeping the target responses fixed, and tests faster parallel decoding on math and code tasks.

First public: 2026-10-26.
ArXiv initial submission: 2026-10-26.

[Original paper](https://arxiv.org/abs/2610.35804) · [PDF](https://arxiv.org/pdf/2610.35804) · [HTML](https://arxiv.org/html/2610.35804v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.35804/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.35804/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.35804/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.35804/record.json)

## Approaches

- [Alternative generation methods](https://latent-implicit-thinking.github.io/topics/alternative-reasoning-schedules/): Change how intermediate steps are generated, revised, or searched—for example, by refining several steps in parallel. Some produce written chains of thought.

Reading-list version 0.12.0; literature checked through 2026-11-02.