Yuhao Wang (王宇豪)
Yuhao Wang is an AI researcher broadly interested in large language models, agent systems, trustworthy AI, and reinforcement learning. Currently, he focuses on building reliable and efficient agent systems and their alignment with humans.
Email / Google Scholar / Homepage / Github
News
- [2025.12]Joined GenAI Lab at SUSTech as a research assistant.
Research
My research mainly focuses on LLMs, RAG systems, agent systems, and memory systems. I am especially interested in trustworthy AI and AI security, including the robustness, alignment, and secure deployment of LLM-based agents and retrieval-augmented pipelines.
* denotes equal contributions. A few selected papers are listed below:
-
Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries PreprintarXiv, 2025
Experience
-
RA @ GenAI Lab at SUSTech
-
M.Sc. in Electrical & Computer Engineering @ National University of Singapore (NUS)
-
Algorithm Engineer @ 星海图(galaxeAI)人工智能有限公司
-
B.Eng. in Electronic and Information Engineering @ Nanjing University of Science and Technology
Awards
- Best Student Award, NJUST (×3).