I am currently a full-time researcher at Tencent, focusing on video generation and world model research, working closely with Jingwei Huang. We are actively recruiting research interns. If you are interested, feel free to reach out to either Jingwei Huang or me. We look forward to collaborating with like-minded students to work on exciting research problems.
Prior to this role, I was a PhD student in the 3DVLab at the Hong Kong University of Science and Technology (HKUST) supervised by Prof. Ping Tan, until I withdrew from the PhD program in March 2026. I also completed a research internship at Horizon Robotics Technology R&D Co., Ltd., collaborating closely with Wei Yin during my PhD period. I earned my M.S. degree from the College of Computer Science at Nankai University in 2024, under the supervision of Prof. Ming-Ming Cheng and Prof. Jun Xu. I received my B.E. degree from Dalian University of Technology (DLUT) in 2021. My research interests include computer vision, computer graphics, video generation and world models.
🔥 News
- 2025.06: 🎉🎉 Two papers are accepted by ICCV 2025.
- 2024.11: 🎉🎉 One paper is accepted by 3DV 2025.
- 2023.02: 🎉🎉 One paper is accepted by CVPR 2023 (Highlight).
- 2023.01: 🎉🎉 One paper is accepted by TIP.
- 2022.07: 🎉🎉 One paper is accepted by ECCV 2022 (Oral).
📝 Publications
DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT
arxiv, 2024
Xiaotao Hu, Wei Yin, Mingkai Jia, Junyuan Deng, Xiaoyang Guo, Qian Zhang, Xiaoxiao Long, Ping Tan
Paper | Code | Project page
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization
arxiv, 2025
Mingkai Jia, Wei Yin, Xiaotao Hu, Jiaxin Guo, Xiaoyang Guo, Qian Zhang, Xiao-Xiao Long, Ping Tan
Epona: Autoregressive DiffusionWorld Model for Autonomous Driving
International Conference on Computer Vision (ICCV), 2025
Kaiwen Zhang, Zhenyu Tang, Xiaotao Hu, Xingang Pan, Xiaoyang Guo, Yuan Liu, Jingwei Huang, Li Yuan, Qian Zhang, Xiao-Xiao Long, Xun Cao, Wei Yin
Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration
International Conference on Computer Vision (ICCV), 2025
Junyuan Deng, Wei Yin, Xiaoyang Guo, Qian Zhang, Xiaotao Hu, Weiqiang Ren, Xiaoxiao Long, Ping Tan
Ctrl-Room: controllable text-to-3D room meshes generation with layout constraints
International Conference on 3D Vision (3DV), 2025
Chuan Fang, Yuan Dong, Kunming Luo, Xiaotao Hu, Rakesh Shrestha, Ping Tan
🎖 Honors and Awards
- 2022.09: The Third Prize Scholarship, Nankai University.
- 2019.11: Silver Medal, The 44th ACM International Collegiate Programming Contest (ICPC), Nanchang.
- 2019.09: The First Prize Scholarship, Dalian University of Technology.
📖 Educations
- 2024.09 - now, PhD student in Electronic & Computer Engineering, Hong Kong University of Science and Technology (HKUST), Hong Kong.
- 2021.09 - 2024.06, M.S. in Computer Science, Nankai University (NKU), Tianjin, China.
- 2017.09 - 2021.06, B.S. in Software Engineering (ranking 4%), Dalian University of Technology (DLUT), Dalian, China.
💬 Invited Talks
not yet
💻 Internships
- 2024.03 - now, Horizon Robotics Technology R&D Co., Ltd., Beijing & Shanghai.
- 2023.08 - 2024.03, Light Illusions, Beijing.
- 2022.08 - 2023.08, Megvii, Beijing.