Ali Hatamizadeh
@ahatamiz1
LLM Tech Lead & Staff Research Scientist @NVIDIA
Co-creator of Gated DeltaNet & Gated DeltaNet-2
๊ฐ์
June 2015
180 ํ๋ก์ ์ค 4.1K ํฌ
GDN for diffusion LLMs ๐๐
dQwen3.5: Hybrid-Attention Diffusion Language Models
Adapting hybrid attention-RNN language models into diffusion models achieves a given training loss in about half the tokens of a full-attention control, while supporting strong parallel decoding.
๋ ๋ณด๊ธฐ
