Hongyu Wang
Scholar

Hongyu Wang

Google Scholar ID: u0tc8ioAAAAJ
Institute of Computing Technology, Chinese Academy of Sciences
Deep LearningNatural Language ProcessingComputer Vision
Citations & Impact
All-time
Citations
1,009
 
H-index
9
 
i10-index
9
 
Publications
16
 
Co-authors
6
list available
Resume (English only)
Academic Achievements
  • Publications: BitNet accepted as a regular paper by JMLR 2025; BitVLA, the first 1-bit VLA model for robotics manipulation and multimodal tasks; BitNet v2, native 4-bit activations for 1-bit LLMs; BitNet b1.58 2B4T, the first native 1-bit LLM trained at scale; BitNet a4.8, enabling 4-bit activations for 1-bit LLMs; bitnet.cpp, the official inference framework; Q-Sparse, the fully Sparsely-Activated LLM; DeepNet accepted as a regular paper by TPAMI 2024.
Research Experience
  • Research intern at General Artificial Intelligence group (GenAI), MSR-Asia, under the supervision of Dr. Furu Wei and Shuming Ma from Aug. 2021 to June 2025.
Education
  • Received B.Eng. degree from the Department of Computer Science and Technology, University of Science and Technology of China (USTC), advised by Professor Chao Qian; now a Ph.D. student at CAS, supervised by Professor Xilin Chen.
Background
  • Research Interests: Efficient architecture for large-scale foundation models, multimodal reasoning, robotics. Currently a Ph.D. candidate at the Institute of Computing Technology, Chinese Academy of Sciences (CAS).
Miscellany
  • Email: why0711@mail.ustc.edu.cn