I’m Weihan Fei (费维瀲), a sophomore undergraduate student at the University of Science and Technology of China (USTC), School of the Gifted Young, majoring in Artificial Intelligence (GPA: 3.87/4.3, Rank: 14/103).

My research is finding-driven: I like to start from concrete empirical phenomena and design mechanisms that explain or improve them, especially when the resulting ideas are concise, mathematically intuitive, and structurally elegant. My current research focuses on adaptive-thinking in generative recommendation and hierarchical query-to-query retrieval for long-context agent memory, and I am also interested in AI interpretability and safety because I care about whether humans can still understand, supervise, and control AI systems in a principled way. I have also pursued self-directed study in machine learning and systems, including Stanford CS229 (Machine Learning), CS230 (Deep Learning), CS224n (Natural Language Processing), MIT 6.S184 (Generative AI Foundations), and Berkeley CS61B (Data Structures).

News

• [Mar 2026] I started research on QQMem: Hierarchical Query-to-Query Retrieval for Long-Context Agent Memory, supervised by Prof. Xiang Wang
• [Nov 2025] I joined Alpha-Lab at USTC, working on Adaptive-Thinking for Generative Recommendation under the supervision of Prof. An Zhang
• [Oct 2025] I won the First Prize (Provincial Level) at the 17th Chinese Mathematics Competitions (Non-Math Major, top 20)
• [Sept 2025] I was awarded the Silver Prize of the Outstanding Undergraduates Scholarship