Uno hybrid diffusion LLM claims 'beats all', but latency-quality is Pareto dominated
joao_gante · x · 2026-09-04
Researcher ssahoo introduced "Uno", targeting diffusion LLMs' two weaknesses vs AR models: lower quality and slower large-batch inference.
- Keeps the AR architecture, with each layer holding two weight sets: AR weights and Diffusion weights
- Diffusion weights enable lossless parallel sampling from the AR distribution
- Claims: faster than all speculative decoding methods (DFlash, EAGLE-3); beats all diffusion LLMs (Mercury 2, Diffusion Gemma, Llada); paper, models, and code released
Contested: bodonoghue85 says the "beats ALL" claim is false — Uno-Qwen is comfortably Pareto dominated on latency-quality by both Mercury 2 and DiffusionGemma, and Uno's LCBv6 number is oddly missing from the writeup.
More from Research
- Sabine Hossenfelder: Science Must Drop the Requirement That Humans Can Understand It — AI Is the Way Forward — coherence · 2026-10-21
- A real larva's connectome — 2,675 cells, 14,066 connections — now swims in a 3D simulation — eptwts · 2026-10-21
- Stanford's T2-z lets robots probe hidden physics with a poke, lifting success from 34% to 73% — stanfordnlp · 2026-10-21
- Fei-Fei Li team unveils FACT, a force-aware foundation model for robot dexterity — stanfordnlp · 2026-10-21
- Upcoming paper claims big models can handle latency-critical real-time robotics — ManlingLi_ · 2026-10-21
- NVIDIA open-sources Flora, a robotics data engine 125x cheaper than GPT-6 Astra — DrJimFan · 2026-10-21