# HiLo-RD: Cross-Budget Self-Distillation for Masked Diffusion Language Models

Authors: Xiang Li, Chengting Yu, Jungang Li, Yilun Zheng, Junzhuo Li, Xingyao Zhang, Wenbo Su, Xuming Hu.

Aligns a diffusion model’s low-budget hidden states with its own longer-budget trajectories. Distilling states at committed positions reduces early fixation on wrong answer tokens in math and code tasks.

First public: 2026-10-27.
ArXiv initial submission: 2026-10-27.

[Original paper](https://arxiv.org/abs/2610.36901) · [PDF](https://arxiv.org/pdf/2610.36901) · [HTML](https://arxiv.org/html/2610.36901v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.36901/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.36901/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.36901/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.36901/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.