# Measured Coupling for Parallel Decoding in Diffusion Language Models

Authors: Tal Oved, Lior Wolf.

Measures how committing one token changes confidence in other tokens, then uses those interactions to choose which positions to fill together. Shares cached states and model calls between the probes and the main decoder.

First public: 2026-11-05.
ArXiv initial submission: 2026-11-05.

[Original paper](https://arxiv.org/abs/2611.08307) · [PDF](https://arxiv.org/pdf/2611.08307) · [HTML](https://arxiv.org/html/2611.08307v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2611.08307/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2611.08307/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2611.08307/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2611.08307/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 0.15.2; literature checked through 2026-11-03.