I'm a Machine Learning Engineer at Kuaishou, focusing on LLM post-training, reinforcement learning, and Agentic AI, with an emphasis on improving reasoning, planning, tool use, and multi-turn interaction capabilities.
I received my Master's degree from the University of Science and Technology of China (USTC) and my Bachelor's degree from Tongji University. Previously, I worked as an LLM Research Intern at Tencent.
My research interests include LLM Post-training, Reinforcement Learning, Agentic AI, and Retrieval-Augmented Generation (RAG). I have also published three papers on GraphRAG.
You can find more about my research on Google Scholar and DBLP.
I'm always interested in exploring new ideas in LLMs and contributing to the open-source community. Feel free to connect!