Yuhui Wang

About Me

I am a Ph.D. candidate at Stony Brook University (SBU), supervised by Prof. Ting Wang. My research interests lie in empirical LLM/Agent safety and alignment, with work spanning jailbreak defenses, adaptive red-teaming, and agentic RL.
Before this, I received my Master’s degree from Shanghai Jiao Tong University (SJTU), advised by Prof. Di Wang, and my Bachelor’s degree from Zhejiang University (ZJU).

Selected Publications (Full List)

• MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
  Yuhui Wang, Tanqiu Jiang, Jiacheng Liang, Charles Fleming, Ting Wang

• Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models
  Yuhui Wang, Changjiang Li, Guangke Chen, Jiacheng Liang, Ting Wang
  International Conference on Learning Representations (ICLR), 2026

• Self-Destructive Language Model
  Yuhui Wang, Rongyi Zhu, Ting Wang
  International Conference on Learning Representations (ICLR), 2026

• GraphRAG under Fire
  Jiacheng Liang†, Yuhui Wang†, Changjiang Li, Rongyi Zhu, Tanqiu Jiang, Neil Gong, Ting Wang
  IEEE Symposium on Security and Privacy (IEEE S&P), 2026

• Deep Learning-Based Sensor Selection for Multimodal Recognition and Prognostics Under Time-Varying Operating Conditions
  Yuhui Wang, Andi Wang, Di Wang, Dong Wang
  IEEE Transactions on Automation Science and Engineering (IEEE TASE), 2025

Services

Conference Reviewers

• International Conference on Machine Learning (ICML) 2026 (Gold Reviewer)
• International Conference on Learning Representations (ICLR) 2026
• Conference on Neural Information Processing Systems (NeurIPS) 2025
• IEEE International Conference on Automation Science and Engineering (IEEE CASE) 2024-2025

Journal Reviewers

• IEEE Transactions on Automation Science and Engineering
• Journal of Computer Security

Powered by Jekyll and Minimal Light theme.