# From Denoising Dynamics to Endpoint Uncertainty in Diffusion Language Models

Authors: Julio C. Amador Díaz López.

Measures how quickly tokens settle during diffusion decoding and relates this to variation across repeated answers. Tests whether features from one denoising run predict agreement among independent runs, separating output stability from correctness.

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

[Original paper](https://arxiv.org/abs/2610.35425) · [PDF](https://arxiv.org/pdf/2610.35425) · [HTML](https://arxiv.org/html/2610.35425v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.35425/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.35425/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.35425/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.35425/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.
- [Analysis and evaluation](https://latent-implicit-thinking.github.io/topics/implicit-reasoning-evaluation/): Measure how well these methods work, investigate what their internal computation does, and identify where they fail. This includes experiments, studies of model internals, and mathematical results.

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