04:38
2026-05-23
dev.to
large-language-models
Diffusion Language Models: How NVIDIA Nemotron-Labs Diffusion Shatters the Autoregressive Speed Ceiling
NVIDIA released Nemotron-Labs Diffusion on May 23, 2026, a family of diffusion language models (DLMs) that generate entire blocks of tokens in parallel and iteratively refine them, rather than produci…