About

I am a Ph.D. student in Computer Science at Southern University of Science and Technology (SUSTech), starting in Fall 2026. My research lies at the intersection of Embodied AI, Robotics, and Multimodal Learning, with the goal of developing intelligent systems that can perceive, reason, communicate, and act in the physical world.

My research explores how AI agents can move beyond passive perception toward interactive intelligence — learning from multimodal experiences, collaborating with humans, and adapting to complex real-world environments.

Research Interests

Embodied AI & Robotics

I study vision-language-action (VLA) models, robot learning, and intelligent agents that connect perception, reasoning, and action. My interests include scalable learning frameworks for robots and their deployment in real-world scenarios.

Multimodal Learning

I investigate the integration of vision, language, audio, and sensor modalities to enable richer representations, long-horizon reasoning, and context-aware decision-making.

Human-Robot Interaction

I am interested in building real-time, adaptive, and interruptible HRI systems where robots can communicate naturally, reflect on their behavior, and continuously improve through interaction.

Computational Aesthetics

I explore how human perception, visual illusions, and aesthetic principles can provide computational insights for designing more intelligent and perceptually aligned AI systems.

Education

Ph.D. in Computer Science
Southern University of Science and Technology (SUSTech) — Shenzhen, China
2026 – 2029
Research focus: Embodied AI, Intelligent Agents, Robotics

M.Sc. in Robotics
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) — Abu Dhabi, UAE
2024 – 2026
Research focus: Multimodal embodied intelligence and robot interaction.
Thesis: An Embodied Robot Interaction Framework Based on Multimodal Large Language Model Agents (ChatPiano)

B.Sc. in Artificial Intelligence
University of Edinburgh — Edinburgh, United Kingdom
2019 – 2024
Thesis: Uncertainty-Aware Cloud-Edge Collaborative LiDAR Point Cloud Segmentation for Autonomous Driving

Previous Experience

Before starting my Ph.D., I worked as a Research Assistant at Tsinghua University’s State Key Laboratory of Automotive Safety and Energy, where I led a 10-person research team working on autonomous driving perception systems.

Beyond academia, I have contributed to and co-founded multiple AI technology initiatives, working across robotics, multimodal AI, and human-centered intelligent systems. I also founded CWAI, an international AI research community connecting researchers and practitioners interested in the future of human–AI collaboration and symbiosis.