👤 Biography

Xiaowei Chi is a Ph.D. candidate in the Individualized Interdisciplinary Program, Division of Emerging Interdisciplinary Areas, at The Hong Kong University of Science and Technology (HKUST), under the supervision of Prof. Yike Guo. His research focuses on multimodal generative models in robotics, with a particular interest in building world models to advance general intelligence in real-world environments. He also works in close collaboration with Prof. Shanghang Zhang at Peking University (PKU). Xiaowei has published multiple papers in top-tier conferences and journals, including CVPR, ICML, AAAI, and ICRA.

🔍 Vision

I'm currently dedicated to creating a new generation of family robots. My goal is to infuse them with vitality through cutting-edge robotics technologies — bringing us closer to making the dream of >Doraemon-like companions a reality.

If you are working on exciting problems in these areas or know of opportunities that align with these interests, feel free to reach out — I’d love to connect!

Always happy to chat!

If you would like to chat about life, career planning, or research ideas related to World Model and Embodied AI, feel free to email me to schedule a meeting. I dedicate 1 hour every week for such conversations.

🎓 Education

• The Hong Kong University of Science and Technology (HKUST), Dual Ph.D. Candidate in AI
• Beijing University of Posts and Telecommunications (BUPT), B.Eng. in Electronic Engineering

📢 News

• [2025.11] Three papers accepted by AAAI 2026
• 🔥 [2025.10] Our work was featured by CCTV: [Beijing: Open-source Embodied World Model — Robots can now unify perception and action]
• [2025.10] One paper accepted by NeurIPS 2026

📝 Publications

📒 Selected publications

Preprint'2025

WoW: Towards a World-omniscient World-model Through Embodied Interaction

• Xiaowei Chi, Peidong Jia, Chun-Kai Fan, Xiaozhu Ju, Weishi Mi, et.al,
• Preprint 2025
• [Paper] [Page]

Preprint'2025

Can World Models Benefit VLMs for World Dynamics?

• Kevin Zhang, Kuangzhi Ge, Xiaowei Chi, Renrui Zhang3, Shaojun Shi, Zhen Dong, Sirui Han, Shanghang Zhang
• Preprint 2025
• [Paper] [Page]

ICML'2025

EVA: An Embodied World Model for Future Video Prediction

• Xiaowei Chi, Hengyuan Zhang, Chun-Kai Fan, Xingqun Qi, Rongyu Zhang, Anthony Chen, Chi-min Chan, Wei Xue, Wenhan Luo, Shanghang Zhang, Yike Guo
• ICML 2025
• [Paper]- [page]

Preprint'2025

MinD: Unified Visual Imagination and Control via Hierarchical World Models

• Xiaowei Chi, Kuangzhi Ge, Jiaming Liu, Siyuan Zhou, Peidong Jia, Zichen He, Yuzhen Liu, Tingguang Li, Lei Han, Sirui Han, Shanghang Zhang, Yike Guo
• Preprint 2025
• [Paper] [Code]

CVPR'2023

BEVSAN: Accurate BEV 3D Object Detection via Slice Attention Networks

• Xiaowei Chi, Jiaming Liu, Ming Lu, Rongyu Zhang, Zhaoqing Wang, Yandong Guo, Shanghang Zhang
• CVPR 2023
• [Paper] [Code]

📚 Full publications

Please visit Google Scholar or DBLP for the full list.

💻 Working(Internship&Full-tmie)

• Tencent RoboticsX Lab (2024.11-2025.08) Research Intern
• AutoX (2021.7-2022.08) Full-time Autonomous Driving Algorithm Engineer

😄 Miscellaneous