M. Maghoumi

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Architecture Design (Transformers, SSMs, MoE) (1)Inference & Quantization (1)Natural Language Processing (1)

Frequent co-authors

Yonggan Fu (1)Lexington Whalen (1)L. Whalen (1)Abhinav Garg (1)

Papers (1)

Jul 7, 2026

NVIDIA6d ago

Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding

Switching between autoregressive and diffusion modes allows Nemotron-Labs-Diffusion to achieve unprecedented throughput and efficiency in language modeling.

Yonggan Fu, Lexington Whalen, L. Whalen +26

Architecture Design (Transformers, SSMs, MoE)Inference & Quantization Natural Language Processing

Search

M. Maghoumi

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)