Scholar
Xiaotian Ye
Google Scholar ID: F0tij1oAAAAJ
Beijing University of Posts and Telecommunications
Citations & Impact
Citations
53
H-index
3
i10-index
2
Publications
6
Co-authors
0
Publications
Resume
Academic Achievements
- Paper 'LLM Unlearning Should Be Form-Independent' accepted to IEEE Symposium on Security and Privacy (S&P) 2026
- Paper 'Uncovering Overfitting in Large Language Model Editing' accepted as Spotlight at ICLR 2025
- Two papers accepted to EMNLP 2025
- Paper 'Knowledge Graph Enhanced Large Language Model Editing' accepted to EMNLP 2024 Main Conference
- Recipient of CCF Elite Collegiate Award (2025)
- Silver medalist at ICPC Asia Regional Contest (2023)
Background
- Senior undergraduate student in Computer Science at Beijing University of Posts and Telecommunications (BUPT)
- Research intern at NLPR/MAIS, Institute of Automation, Chinese Academy of Sciences (CASIA)
- Research focuses on the intersection of knowledge mechanisms and the safety & trustworthiness of foundation models (LLMs/VLMs)
- Broadly interested in interpretability, knowledge editing, unlearning, alignment, and agentic safety
- Passionate about developing reliable and trustworthy AI systems for real-world applications