I am currently a master’s student at the School of Computer Science and Technology, East China Normal University, under the supervision of Professor Linlin Wang. My primary collaborator, Ph.D. Xin Yi, has provided me with invaluable guidance and support throughout my studies. Prior to this, I earned my BEng degree from Xiangtan University, where I was mentored by Associate Professor Xuan Lin.

My research focuses on the safety of large language models (including multi-modal large language models), and I am very interested in the internals of safety alignment of large language models.

If you like the template of this homepage, welcome to star and fork my open-sourced template version AcadHomepage .

🔥 News

  • 2025.05: 🎉 My first paper as the first author has been accepted by ACL 2025!

📝 Publications

🗡️🛡️ Jailbreak Attacks and Defenses

ACL 2025
sym

Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models \ Yue Li*, Xin Yi*, Dongsheng Shi, Gerard de Melo, Xiaoling Wang and Linlin Wang.

Arxiv | Project | ACL Anthology

  • The current pruning methods will lead to a significant degradation of the model’s safety at a higher sparsity.
  • The HSR (Hierarchical Safety Realignment) method we proposed can achieve safety realignment for the pruned model by restoring only a very small number of neurons. HSR is effective for both LLM and LVLM.

📄🔍 Watermarks and Fingerprints

🎖 Honors and Awards

  • 2023.05, The 2023 China College Student Programming Competition (CCPC) National Invitational (Hunan), Silver Medalist
  • 2022.04, The 46th International Collegiate Programming Contest (ICPC) Asian Regional Competition (Kunming), Bronze Medalist

📖 Educations

  • 2024.09 - Present, Master, East China Normal University, Shanghai.
  • 2020.09 - 2024.06, Undergraduate, Xiangtan Univeristy, Xiangtan.
  • 2017.09 - 2020.06, Zhejiang Yueqing Middle School, Wenzhou.