# Balance-Aware Pivot Selection for Parallel Diffusion LLM Decoding

Authors: Yejin Lee, Hyundong Jin, Yo-Sub Han.

Selects confident tokens near the centers of masked spans, allowing diffusion language models to fill separate spans in parallel. Studies how this ordering trades generation quality against decoding speed on math, code and instruction-following tasks.

First public: 2026-10-19.
ArXiv initial submission: 2026-10-19.

[Original paper](https://arxiv.org/abs/2610.26040) · [PDF](https://arxiv.org/pdf/2610.26040) · [HTML](https://arxiv.org/html/2610.26040v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.26040/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.26040/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.26040/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.26040/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 0.11.0; literature checked through 2026-10-26.