Scholar
Shiwei Feng
Google Scholar ID: 3gtm2egAAAAJ
Purdue University
Citations & Impact
Citations
455
H-index
10
i10-index
10
Publications
18
Co-authors
27
list available
Publications
Resume (English only)
Academic Achievements
- Published several papers such as 'TAI3: Testing Agent Integrity in Interpreting User Intent' (NeurIPS 2025), 'Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving' (NeurIPS 2025); Received NeurIPS’25 Scholar Award; Co-authored papers that won ACM SIGSOFT Distinguished Paper Award and Distinguished Artifact Award.
Research Experience
- Served as a Deep Learning Compiler Intern at Apple Neural Engine Compiler Team; Participated in multiple research projects, including LLM agent for protocol auditing, user intent integrity on LLM agents, backdoor attack in RL agents, etc.
Education
- Ph.D. (in progress): Purdue University, Advisor: Xiangyu Zhang; B.Sc.: Nanjing University (graduated in 2020), Initial Advisors: Prof. Fengyuan Xu and Dr. Hao Wu.
Background
- Research Interest: Trustworthy Autonomous Systems, Safe Deployment of Foundation Models; Professional Field: Computer Science; Brief Introduction: A fifth-year Ph.D. student from the Department of Computer Science at Purdue University, advised by Professor Xiangyu Zhang.
Miscellany
- Personal interests not mentioned.
