Hi, I'm Xu Li (李旭), a computer science undergrad at Northeastern University Boston, MA.
I'm particularly interested in agents safety and their long horizon robustness.
Currently conducting research at Chats Lab under the supervision of Prof. Weiyan Shi.
Updates
🎉 2026.02
Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
🎉 2025.09
ICCV 2025 6th CLVISION Workshop Challenge
[link]
🎉 2025.05
MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering
arXiv, 2025 [pdf]
Email: li.xu2@northeastern.edu