Hi, I am a graduate student specializing in Artificial Intelligence at Peking University. Before that, I completed my undergraduate studies in Intelligent Science and Technology with a double major in Economics at Peking University. I am passionate about advancing AGI and solving real-world problems using AI technologies.
About Me
Research Interests
Post-Training of Large Language Models
Focus on LLMs and Multi-modal Large Models preference optimization
AI Agents
Building LLM agents with reasoning, tool use, long-term memory, and self-correction
Featured Projects
Selective Alignment for Post-Training
Designed a selective alignment strategy to optimize user preferences during post-training
Preference Optimization Pipeline
Developed reward model evaluation frameworks and efficient online DPO pipelines
STEM Reasoning Optimization with Rule-based RL
Constructed and cleaned a high-quality 85k-scale STEM multiple-choice dataset for scientific reasoning, incorporating rule-based filtering, reflection-based evaluation, and repetition penalty to enhance LLM scientific reasoning performance under Zero-RL training
Anomaly Detection Framework
Proposed frameworks for anomaly detection with limited labeled data
Publications
2025
2024
2024
Wenxuan Zhang, Hongzhi Liu*, Zhijin Dong, Yingpeng Du, Chen Zhu, Yang Song, Hengshu Zhu, Zhonghai Wu. "Bridging the Information Gap Between Domain-Specific Model and General LLM for Personalized Recommendation."
Web and Big Data, Springer Nature Singapore, 2024, pp. 280--294.
Awards & Honors
2024.12
Peking University Merit Student
2023.12
Third Prize, 20th Huawei Cup China Graduate Mathematical Contest in Modeling
2021.10
Peking University Excellent Study Award
2021.5
Third Prize, 19th AcWing Cup Programming Contest
2020.10
National Encouragement Scholarship