Lexington Whalen | Efficient AIhttps://research.nvidia.com/labs/eai/author/lexington-whalen/Lexington WhalenHugo Blox Builder (https://hugoblox.com)en-usTue, 07 Jul 2026 00:00:00 +0000https://research.nvidia.com/labs/eai/media/icon_hu_f6c58f2ed9051eb5.pngLexington Whalenhttps://research.nvidia.com/labs/eai/author/lexington-whalen/Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decodinghttps://research.nvidia.com/labs/eai/publication/nemotron-labs-diffusion/Tue, 07 Jul 2026 00:00:00 +0000https://research.nvidia.com/labs/eai/publication/nemotron-labs-diffusion/<!-- Original preprint metadata: https://arxiv.org/abs/2607.05722v1 Featured image: https://arxiv.org/html/2607.05722v1/tri_mode_illustration.png Verified against the EAI publication list on 2026-11-10. Conference metadata and BibTeX: https://aclanthology.org/2026.emnlp-main.2416/ (checked 2026-11-10). -->Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speedhttps://research.nvidia.com/labs/eai/publication/efficient-dlm/Tue, 16 Dec 2025 00:00:00 +0000https://research.nvidia.com/labs/eai/publication/efficient-dlm/<!-- Original preprint metadata: https://arxiv.org/abs/2512.14067v2 Featured image: https://arxiv.org/html/2512.14067v2/acc_block_size.png Verified against the EAI publication list on 2026-11-10. Conference metadata and BibTeX: https://proceedings.mlr.press/v306/fu26q.html (checked 2026-11-10). -->