Scholar
Jiawei Zhang
Google Scholar ID: vCY9ZRcAAAAJ
University of Chicago
Citations & Impact
Citations
632
H-index
14
i10-index
16
Publications
20
Co-authors
11
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Publications: 'Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth' and several other papers; Projects: UDora (a unified red teaming framework), SafeAuto (knowledge-enhanced safe autonomous driving) among others.
Research Experience
- Interned at NVIDIA Research, Bytedance Seed, Nuro AI, and Sea AI, and works closely with Meta GenAI. Participated in internal red-teaming evaluations for OpenAI o1, Google DeepMind, and ElevenLabs TTS with Virtue AI.
Education
- Ph.D. in Computer Science at the University of Chicago, under the guidance of Prof. Bo Li; M.S. in Computer Science from Siebel School of Computing and Data Science at the University of Illinois Urbana-Champaign; B.S. from Zhejiang University.
Background
- Research Interests: Making LLMs and LLM agents reliable at scale. Professional Field: Computer Science, particularly in secure learning.
Miscellany
- Personal Quote: 'Man is but a reed, the most feeble thing in nature; but he is a thinking reed.'
