Yu Li
M.S. Student in Artificial Intelligence @ Fudan University
Research interests: trustworthy multimodal foundation models/agents, agent safety, data-centric visual learning, and cross-domain few-shot learning.
About
I am currently pursuing my M.S. degree in Artificial Intelligence at the School of Data Science, Fudan University, advised by Prof. Yanwei Fu. I am also a research intern at Shanghai Artificial Intelligence Laboratory, working with Dr. Dongrui Liu. Before joining Fudan, I received my B.S. degree in Software Engineering from Dalian University of Technology.
My research interests include trustworthy multimodal foundation models and agents, agent safety, data-centric visual learning, cross-domain few-shot learning, retrieval-guided generation, jailbreak and defense, alignment, interpretability, efficient reasoning, computer-use/mobile agents, and embodied agent safety. I am open to collaboration and discussions. Feel free to drop me an email if you are interested.
News
- Apr 2026ATBench was released on arXiv for trajectory-level agent safety evaluation and diagnosis.
- Jan 2026AgentDoG was released as a diagnostic guardrail framework for AI agent safety and security.
- 2025Domain-RAG was accepted to NeurIPS 2025.
Education
Fudan University
Dalian University of Technology
Experience
Shanghai Artificial Intelligence Laboratory
Worked on data pipelines and benchmark construction for trajectory-level agent safety diagnosis, including scalable synthesis, filtering, and evaluation data design.