Skip to main content

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

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: · Added to this list: November 2, 2026

Cite this paper

ArXiv preprint

arXiv:2610.36466 · Initial submission: 2026-10-27

BibTeX · CSL-JSON

Explore this approach

Alternative generation methods — Change how intermediate steps are generated, revised, or searched—for example, by refining several steps in parallel. Some produce written chains of thought.