frontier models
Diffusion Drew Several Tokens From an Autoregressive Model
Uno adds lightweight diffusion weights without replacing the base next-token distribution.
Published Updated Story ID: mp-2026-09-04-018
Summary
Uno adds lightweight diffusion weights without replacing the base next-token distribution.
The authors report up to threefold throughput gains over the base model and advantages over tested speculative decoders at every batch size, while releasing code and checkpoints. Quality claims remain benchmark-specific.
Why it matters
Uno adds lightweight diffusion weights without replacing the base next-token distribution.
Limits and context
- Quality claims remain benchmark-specific.
Key claims
Uno adds lightweight diffusion weights without replacing the base next-token distribution.
Qualification: Quality claims remain benchmark-specific.
Evidence: source-2026-09-04-020
Sources
- arXiv preprint 2609.04010arXiv · primary research
Corrections
No corrections have been recorded for this story.