Published papers in top-tier conferences such as NeurIPS, ICCV, ICML, CVPR, and ICLR. Projects have been highlighted by MIT homepage and news. Specific projects include but not limited to: Jet-Nemotron, Sparse Video-Gen, Win Fast or Lose Slow, DC-AE series, SANA series, COAT, HART, EfficientViT-SAM, CAN, DistriFusion, EfficientViT, Lite Pose, Network Augmentation for Tiny Deep Learning, TinyTL, APQ, Once-For-All Network (OFA), and ProxylessNAS.
Research Experience
Currently a research scientist at NVIDIA Research. Joined NVIDIA after completing the doctoral degree.
Education
Received a doctoral degree from MIT EECS; Master's and bachelor's degrees from Shanghai Jiao Tong University (SJTU).
Background
Research interests lie in artificial intelligence and machine learning, particularly efficient foundation models (diffusion models, LLMs, etc), EdgeAI, and AutoML.
Miscellany
Contact information: Email, Google Scholar, GitHub, Twitter, LinkedIn