Weijie Zhou
About Me
I am a third-year Ph.D. student jointly trained by Beijing Jiaotong University (BJTU) and the Institute of Automation, Chinese Academy of Sciences (CASIA). I am fortunate to be advised by Prof. Jinqiao Wang, Prof. Honghui Dong and Dr. Chaoyang Zhao. I am currently a Research Intern under the Tencent “Project UP” (腾讯青云计划) at Tencent Robotics X Lab, supervised by Dr. Zhengyou Zhang.
My research interests lie in Embodied AI and Foundation Models for Robotics. Currently, my work focuses on endowing robots with physical common sense through Physically-grounded VLMs and exploring World Models for predictive control and long-horizon reasoning.
News
- [2026.03] 🚀 Selected for the elite Tencent “Project UP” (腾讯青云计划).
- [2026.01] 🏆 Awarded the Annual Outstanding Intern at Tencent Robotics X Lab (Sole recipient of the year).
- [2025.09] 🎉 One paper (PhysVLM-AVR) accepted to NeurIPS 2025.
- [2025.08] 🏆 Awarded the Outstanding Intern (2025 H1) at Tencent Robotics X Lab.
- [2025.08] 📄 Released technical report TAIROS with Tencent Robotics X Lab.
- [2025.06] 🎉 One paper (LightPlanner) accepted to IROS 2025.
- [2025.02] 🎉 One paper (PhysVLM) accepted to CVPR 2025.
Recent Publications
-
NeurIPS 2025
39th Conference on Neural Information Processing Systems (NeurIPS), 2025 -
Tencent Robotics X Lab
Tencent Robotics X Lab Tech Report, 2025PDF Project Page Released -
IROS 2025
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025 -
CVPR 2025
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Other Publications
- Weijie Zhou, Zijun Wang, Minshu Zhang, Liwen Wang. Wind turbine actual defects detection based on visible and infrared image fusion. IEEE TIM, 2023.
Internships
Tencent Robotics X Lab (Project UP), Shenzhen | March 2026 – Present
- Advanced Research: Continuing research on embodied AI and large-scale multimodal models as part of the elite “Project UP” talent program.
Tencent Robotics X Lab, Shenzhen | March 2025 – October 2025
- TAIROS AI Platform: Co-developed an embodied AI platform for robotics applications, deployed at 4+ offline events including the 2025 World AI Conference.
- Multi-Agent Shared Memory Reasoning: Designed a streaming perception and on-demand reconstruction memory system enabling multi-agent long-horizon reasoning without pre-built maps.