Scholar
Bohang Zhang
Google Scholar ID: hJgT4tYAAAAJ
Peking University
Citations & Impact
Citations
1,121
H-index
11
i10-index
11
Publications
14
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- First-authored papers have won the ICLR 2023 Outstanding Paper Award and ICLR 2024 Outstanding Paper Honorable Mention; Ph.D. thesis selected as CAAI Outstanding Doctoral Dissertation Honorable Mention and Outstanding Doctoral Dissertation in Peking University.
Research Experience
- Research areas include understanding the power and limitations of large language models (LLMs) in complex reasoning; analyzing the expressive power of graph neural networks (GNNs), providing guidance on GNNs design principles that enable them to effectively represent necessary graph structural information; designing powerful Lipschitz neural networks with certified robustness guarantees; designing and analyzing optimization algorithms for efficient neural network training.
Education
- Ph.D. student at Peking University, advised by Prof. Liwei Wang; Undergraduate studies at School of the Gifted Young in Xi’an Jiaotong University, majoring in Computer Science.
Background
- Main research area includes studying the foundations of machine learning, such as the expressive power, robustness, and optimization of neural networks. Provides theoretical and algorithmic insights into the strengths and weaknesses of fundamental deep learning models and algorithms (often through a computer science perspective), based on which designs new (provably better) models/algorithms.
Miscellany
- Contact via email or Wechat; open to collaboration and chat.
