Nemotron-Labs-Diffusion Collection A Tri-Mode Language Model Family Unifying Autoregressive, Diffusion, and Self-Speculation Decoding • 7 items • Updated about 13 hours ago • 48
view article Article Towards Speed-of-Light Text Generation with Nemotron-Labs Diffusion Language Models nvidia • 13 days ago • 29
view article Article Ulysses Sequence Parallelism: Training with Million-Token Contexts kashif, stas • Mar 9 • 30