# Nemotron-Labs-Diffusion-Uni: Elastic Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation

Authors: Shufan Li, Hanrong Ye, Greg Heinrich, Yonggan Fu, Haotian Zhang, Sifei Liu, Aditya Grover, Pavlo Molchanov.

Trains a unified multimodal diffusion model using an autoregressive view for teacher supervision and a consistency loss for blockwise decoding. Evaluates visual math and logic alongside image generation and editing.

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

[Original paper](https://arxiv.org/abs/2610.36466) · [PDF](https://arxiv.org/pdf/2610.36466) · [HTML](https://arxiv.org/html/2610.36466v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.36466/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.36466/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.36466/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.36466/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 0.12.0; literature checked through 2026-11-02.