Yingjin JIANG（江英进）

I am a first-year MPhil student at The Hong Kong University of Science and Technology (Guangzhou). My research focuses on mechanistic interpretability and LLM interpretability, aiming to uncover the internal mechanisms that enable complex reasoning in large language models. I am particularly interested in understanding how LLMs store knowledge and perform multi-step reasoning, with the goal of building more trustworthy and reliable AI systems.