# Hierarchical Masked Diffusion Language Models

Authors: Parul Gupta, Satwik, Avni Aggarwal, Bhavesh Gurnani, Arnab Kumar Mondal, Dinesh Khandelwal, Dinesh Garg, Parag Singla.

Predicts which masked positions should be filled first, then predicts their tokens with a hierarchy-aware diffusion model. Tests this ordering on text generation and Sudoku, where earlier solved cells can help determine later ones.

First public: 2026-10-21.
ArXiv initial submission: 2026-10-21.

[Original paper](https://arxiv.org/abs/2610.29255) · [PDF](https://arxiv.org/pdf/2610.29255) · [HTML](https://arxiv.org/html/2610.29255v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.29255/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.29255/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.29255/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.29255/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.