Yujun Zhou
Scholar

Yujun Zhou

Google Scholar ID: t0c7rQQAAAAJ
University of Notre Dame
Trustworthy LLMLLM ReasoninngAdversarial Machine Learning
Citations & Impact
All-time
Citations
198
 
H-index
7
 
i10-index
7
 
Publications
20
 
Co-authors
8
list available
Resume (English only)
Academic Achievements
  • Multiple papers accepted by top conferences including Nature Machine Intelligence, EMNLP Findings, ACL Findings, IJCAI, NeurIPS, etc.; awarded OpenAI's Researcher Access Program.
Research Experience
  • Currently conducting research in Mine Lab; previously joined Tencent AI Lab as a summer research intern.
Education
  • Ph.D. student in Computer Science at the University of Notre Dame since Spring 2023, advised by Prof. Xiangliang Zhang; also a graduate student in the Foundation Models and Applications Lab (FMAL) at Lucy Family Institute for Data & Society. Previously, received B.E. in Computer Science and Engineering from the University of Electronic Science and Technology of China (UESTC) and M.S. in Computer Science from King Abdullah University of Science and Technology (KAUST).
Background
  • Research interests: Large Language Model (LLM) reasoning and trustworthy LLMs. Aims to understand how LLMs reason, where their reasoning fails, and how to enhance their ability to generalize beyond seen problems. Also studies how to make LLMs more reliable, safe, and aligned in safety-critical contexts. Engaged in the ND-IBM Tech Ethics Lab Collaborative Project, exploring ways to extend the trustworthiness of LLMs to practical domains such as laboratory safety and investigating misalignment behaviors.
Miscellany
  • Seeking potential research collaborations and the position of industry research intern.