About Me

Hi! This is Xiaotian Ye.

I’m a senior undergraduate in Computer Science at Beijing University of Posts and Telecommunications, and a research intern at the Institute of Automation, Chinese Academy of Sciences (CASIA). I work at NLPR, MAIS, where I am fortunate to be advised by Prof. Shu Wu and work with Dr. Mengqi Zhang.

My research focuses on the intersection of knowledge mechanisms and the safety & trustworthiness of foundation models (LLMs/VLMs), and I am generally interested in a wide range of topics such as interpretability, knowledge editing, unlearning, alignment, and agentic safety. I have a broad interest in developing reliable and trustworthy AI systems, enhancing our ability to leverage these technologies in various fields. Beyond my research, I am also passionate about Competitive Programming and have received a silver medal in ICPC - Asia Regional Contest.

Recent Update

• [9/9/2025] 🎉LLM Unlearning Should Be Form-Independent gets accepted to S&P 2026!! See you in San Francisco!
• [9/4/2025] 🎉Thrilled to be awarded the CCF Elite Collegiate Award! Heading to CNCC2025@Harbin for the ceremony!
• [8/21/2025] 🔥Two papers get accepted to EMNLP 2025!
• [2/11/2025] 🎉 Uncovering Overfitting in Large Language Model Editing gets accepted to ICLR 2025 as Spotlight! See you in Singapore!
• [9/20/2024] 🔥 Our paper Knowledge Graph Enhanced Large Language Model Editing gets accepted to EMNLP 2024 Main!
• [12/3/2023] 🍾 Winning a silver medal at the International Collegiate Programming Contest - Asia Regional Contest in Jinan! Huge thanks to my amazing teammates for their invaluable support! 🥈👏

Research Highlights

Contact Information

Feel free to reach out if you want to chat or interested in my work!