Homepage
About Me
I am a first-year PhD student at the University of Science and Technology of China (USTC) Lab for Data Science, where I have the privilege of working under the guidance of Prof. Xiangnan He. My research lies at the intersection of LLM agent and Data Mining, with a focus on assisting user experiences on academic research and recommendations with LLMs.
Currently, I am also working as a research intern at Kuaishou Technology, where I contribute to the development and optimization of recommendation algorithms that directly impact millions of users.
Research Interests
My research aims to bridge the gap between user preferences and content delivery by:
- LLM-Powered Recommendations: Leveraging large language models to generate more contextually aware and diverse recommendations
- Treatment Effect Estimation: Applying causal inference techniques to understand and optimize user interest exploration
- Controllable Recommendation Systems: Developing frameworks that allow fine-grained control over recommendation diversity and personalization
- User Behavior Modeling: Understanding implicit user interests and improving engagement through data-driven insights
Recent Highlights
🎉 [Jan 2025] Our paper “DLCRec: A Novel Approach for Managing Diversity in LLM-Based Recommender Systems” has been accepted by WSDM 2025!
🎉 [Jul 2024] Presented our work “Treatment Effect Estimation for User Interest Exploration” at SIGIR 2024 in Washington, D.C.
| 🏆 [Impact] At Kuaishou, our recommendation algorithms achieved significant improvements: Average app time: +0.120% | Follow rate: +1.002% | Forward rate: +0.984% | Download rate: +1.018% | Collection rate: +1.102% | Negative feedback: -2.627% |
Featured Publications
My work has been published at top-tier conferences in information retrieval and data mining, including SIGIR and WSDM. I focus on developing practical solutions that balance recommendation accuracy with diversity, ensuring users discover content that truly matches their evolving interests.
Check out my Publications, Research & Practice, and CV for more details!