I’m a third-year Ph.D. student at McGill University and Mila, Quebec AI Institute, advised by Prof. Yichuan Ding.
Prior to McGill, I graduated from Tsinghua University, advised by Prof. Xianyuan Zhan, where I worked on offline RL to build real-world decision-making systems that are scalable and reliable.
My research currently focuses on two directions:
Alignment of LLMs. RLHF, preference modeling, and on-policy distillation (OPD) for post-training through a reinforcement learning lens.
Marketing research with LLMs. LLM-powered methods for consumer research, behavioral simulation, personalization, and decision support.
