I’m a PhD student starting from Fall 2024 at UMass Amherst supervised by Prof. Chuang Gan. My research interests lie in Embodied AI, Language Models and Computer Vision, especially how they can cooperate with each other. A long preserving goal of mine is to build agents that can physically interact with the real world, which requires development of both perception (vision, multi-modal) and decision making (RL, LLM, etc.).