Diffusion language models can generate text in parallel, but repeated denoising makes them slow. New cache-aware work makes the trade-off worth watching.
Diffusion language models can generate text in parallel, but repeated denoising makes them slow. New cache-aware work makes the trade-off worth watching.
NVIDIA's Nemotron-Labs-Diffusion unifies AR, diffusion, and self-speculation in one architecture. It can switch modes mid-generation. The paper claims 6× more tokens per forward than AR — but the real story is how tri-mode changes what hardware you need.