Han Cai
Scholar

Han Cai

Google Scholar ID: x-AvvrYAAAAJ
NVIDIA
Artificial intelligenceMachine LearningEfficient Deep LearningAutoML
Citations & Impact
All-time
Citations
9,888
 
H-index
27
 
i10-index
32
 
Publications
20
 
Co-authors
23
list available
Resume (English only)
Academic Achievements
  • 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