Mingcong Lei

I'm a Y4 Undergraduate student from The Chinese University of Hong Kong, Shenzhen, majoring in Computer Science and Engineering. My research focuses on embodied AI and robotics. My research interests lie at the intersection of large language models, robotics, and embodied intelligence. I'm particularly interested in developing robust frameworks that enable AI agents to perform complex tasks in dynamic real-world environments. My recent work includes developing CLEA (Closed-Loop Embodied Agent), a novel architecture that enhances task execution capabilities in dynamic environments through interactive task planning and multimodal execution criticism. I've also worked on STMA (Spatio-Temporal Memory Agent), which focuses on improving long-horizon task planning by integrating spatio-temporal memory and dynamic knowledge graphs.

I aim to bridge the gap between high-level language understanding and practical robotic execution, developing systems that can reliably handle real-world uncertainties and environmental changes. My research emphasizes creating robust, adaptable AI agents that can effectively decompose complex tasks while maintaining reliable execution in dynamic settings.

I am currently looking for PhD opportunities for Fall 2026.

My resume