Dongrui Liu Ph.D

Biography

Currently, I am working at the Shanghai AI Lab as a Research Scientist. I got a Ph.D. degree from Shanghai Jiao Tong University and was supervised by Prof. Quanshi Zhang. Before that, I received my B.Sc. degree from Northeastern University.

My research interests include topics in the trustworthiness of multi-modal foundation models/agents and AI for Science, e.g., jailbreak, defense, alignment, interpretability, efficient reasoning, computer use/mobile agent, and embodied agent safety.

We are hiring full-time researchers, interns, and joint PhDs (with SJTU/FDU, etc) to work together on Trustworthy AI! I am open to collaboration and discussions. Feel free to drop me an email at drliu96@sjtu.edu.cn if you are interested.

Honors & Awards

• ACL 2025 Outstanding Paper Award (Top 0.3%)
• CVPR 2024 Best Paper Award Candidate (Top 0.2%)
• Shanghai Jiao Tong University Outstanding Graduate (Top 4%)
• National Scholarship (Top 2%)

News

Projects

• AgentDoG
  A Diagnostic Guardrail Framework for AI Agent Safety and Security
  
• SafeWork-F1
  Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.0 & 1.5
  
• SafeWork-R1
  SafeWork-R1: Coevolving Safety and Intelligence under the AI-45◦ Law
  

Selected Publications [Google Scholar]

Academic Services

• Area Chair:
  NeurIPs Position Paper Track, ICLR LLA Workshop,

• Conference Reviews:
  ICML, CVPR, ICCV, ECCV, NeurIPs, ICLR, AAAI, ACL, AISTATS, ICRA, IROS, PAMI, IJCV, TKDE, TVCG, TCSVT, T-ITS, TMLR