Dong Zhou

Dong Zhou is a Senior Member of Technical Staff in the AI Group of AMD. He leads a team for AI/ML-related Gaming and Creativity models’ application, including Image/Video processing/enhancement （especially Neural accelerated rendering） and Image/Video/World Generation. Prior to joining AMD, he worked at Visual Computing Group of ByteDance AI Lab. He received his bachelor’s and master’s degree from Tsinghua University.

Posts by Dong Zhou

Nitro-E: A 304M Diffusion Transformer Model for High Quality Image Generation

Nitro-E is an extremely lightweight diffusion transformer model for high-quality image generation with only 304M paramters.

October 24, 2025 by Tong Shen, Jingai Yu, Dong Zhou, Dong Li, Emad Barsoum

Posts by Dong zhou

AMD Hummingbird Image to Video: A Lightweight Feedback-Driven Model for Efficient Image-to-Video Generation

We present AMD Hummingbird, offering a two-stage distillation framework for efficient, high-quality text-to-video generation using compact models.

August 03, 2025 by Takashi Isobe, Dong zhou, He Cui, Mengmeng Ge, Dong Li, Emad Barsoum