Xiao Chen (陈 骁)
Ph.D. Student@MMLab, CUHK
Biography
Hi there👋! I'm a third-year Ph.D. student at MMLab, The Chinese University of Hong Kong, advised by Prof. Tianfan Xue. I received my B.Eng. Degree and Honors Degree (Chu Kochen Honors College) from Zhejiang University.
I'm currently a research intern at NVIDIA, working on robotic foundation models for loco-manipulation. Prior to that, I've spent wonderful time as an on-site research intern at Shanghai AI Laboratory, working closely with Dr. Jingbo Wang, Dr. Tai Wang, and Dr. Jiangmiao Pang.
My interest lies at the intersection of Robotics and Computer Vision. My recent research focuses on two aspects:
- Active perception, reconstruction, and generation of the 3D/4D world, with an emphasis on interactive assets and physically plausible motions
- General-purpose loco-manipulation, robotic foundation models, robot learning data flywheels
News
- [2026-02] 🎉 Two paper (Mimic2DM) and (DynamicTree) accepted at CVPR 2026!
- [2026-01] 🎉 One paper (AdaMimic) accepted at ICRA 2026!
- [2026-01] 🎉 One paper (FullPart) accepted at ICLR 2026!
- [2025-09] Invited talk at CV Life (计算机视觉life)!
- [2025-09] Invited talk at 3DCVer (3D视觉工坊)!
- [2025-06] 🎉 Two papers (GLEAM and CoPart) accepted at ICCV 2025!
- [2025-06] 🎉 HoST is selected as a Best Systems Paper Finalist at RSS 2025!
- [2025-04] 🎉 One paper (HoST) accepted at RSS 2025!
- [2024-07] Invited talk at AI Spot, hosted by OpenMMLab!
- [2024-02] 🎉 Two papers (GenNBV and EmbodiedScan) accepted at CVPR 2024!
Publications
▼ Active Perception, Reconstruction, and Generation of 3D/4D world
GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes
GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction
FullPart: Generating Each 3D Part at Full Resolution
ICLR 2026
Lihe Ding*, Shaocong Dong*, Yaokun Li, Chenjian Gao, Xiao Chen, Rui Han, Yihao Kuang, Hong Zhang, Bo Huang, Zhanpeng Huang, Zibin Wang, Dan Xu†, Tianfan Xue†
Lihe Ding*, Shaocong Dong*, Yaokun Li, Chenjian Gao, Xiao Chen, Rui Han, Yihao Kuang, Hong Zhang, Bo Huang, Zhanpeng Huang, Zibin Wang, Dan Xu†, Tianfan Xue†
CoPart: Contextual Part Latents for 3D Generation
ICCV 2025
Shaocong Dong*, Lihe Ding*, Xiao Chen, Yaokun Li, Yuxin Wang, Yucheng Wang, Qi Wang,
Jaehyeok Kim, Chenjian Gao, Zhanpeng Huang, Zibin Wang, Tianfan Xue†, Dan Xu†
Shaocong Dong*, Lihe Ding*, Xiao Chen, Yaokun Li, Yuxin Wang, Yucheng Wang, Qi Wang,
Jaehyeok Kim, Chenjian Gao, Zhanpeng Huang, Zibin Wang, Tianfan Xue†, Dan Xu†
DynamicTree: Interactive Real Tree Animation via Sparse Voxel Spectrum
EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI
CVPR 2024
Tai Wang*, Xiaohan Mao*, Chenming Zhu*, Runsen Xu, Ruiyuan Lyu, Peisen Li, Xiao Chen,
Wenwei Zhang, Kai Chen, Tianfan Xue, Xihui Liu, Cewu Lu, Dahua Lin, Jiangmiao Pang†
Tai Wang*, Xiaohan Mao*, Chenming Zhu*, Runsen Xu, Ruiyuan Lyu, Peisen Li, Xiao Chen,
Wenwei Zhang, Kai Chen, Tianfan Xue, Xihui Liu, Cewu Lu, Dahua Lin, Jiangmiao Pang†
▼ Humanoid-Scene Interaction & Universal Humanoid Control
Mimic2DM: Learning to Control Physically-simulated 3D Characters via Generating and Mimicking 2D Motions
AdaMimic: Towards Adaptable Humanoid Control via Adaptive Motion Tracking
ICRA 2026
Tao Huang, Huayi Wang, Junli Ren, Kangning Yin, Zirui Wang, Xiao Chen, Feiyu Jia, Wentao Zhang, Junfeng Long, Jingbo Wang†, Jiangmiao Pang†
Tao Huang, Huayi Wang, Junli Ren, Kangning Yin, Zirui Wang, Xiao Chen, Feiyu Jia, Wentao Zhang, Junfeng Long, Jingbo Wang†, Jiangmiao Pang†
HoST: Learning Humanoid Standing-up Control across Diverse Postures
RSS 2025 (Best Systems Paper Finalist)
Tao Huang, Junli Ren, Huayi Wang, Zirui Wang, Qingwei Ben, Muning Wen, Xiao Chen,
Jianan Li, Jiangmiao Pang†
Tao Huang, Junli Ren, Huayi Wang, Zirui Wang, Qingwei Ben, Muning Wen, Xiao Chen,
Jianan Li, Jiangmiao Pang†
PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System
arXiv 2025 (under review)
Huayi Wang*, Wentao Zhang*, Runyi Yu*, Tao Huang, Junli Ren, Feiyu Jia, Zirui Wang, Xiaojie Niu,
Xiao Chen, Jiahe Chen, Qifeng Chen†, Jingbo Wang†, Jiangmiao Pang†
Huayi Wang*, Wentao Zhang*, Runyi Yu*, Tao Huang, Junli Ren, Feiyu Jia, Zirui Wang, Xiaojie Niu,
Xiao Chen, Jiahe Chen, Qifeng Chen†, Jingbo Wang†, Jiangmiao Pang†
Open-Source Projects
Awesome Spatial Exploration Policies
(2025) A curated list of papers about spatial exploration. The exploration task, also known as next-best-view planning, aims to determine the next best viewpoints to model and understand target scenes.
Batch Export Generated 3D Scenes for Robot Learning
A LiDAR SLAM System for Mobile Robots
(2020) Python, ROS (gazebo, rviz). A lightweight, self-developed LiDAR SLAM system for mobile robots, featuring LiDAR odometry (ICP), state estimation (EKF), and path planning (DWA and A*).
Services
Academic Reviewer
Conference
- Computer Vision and Pattern Recognition (CVPR)
- International Conference on Computer Vision (ICCV)
- European Conference on Computer Vision (ECCV)
- International Conference on Learning Representations (ICLR)
- International Conference on Intelligent Robots and Systems (IROS)
- ACM SIGGRAPH
- ACM Multimedia (ACM-MM)
- The Association for the Advancement of Artificial Intelligence (AAAI)
- The British Machine Vision Conference (BMVC)
- IEEE Robotics and Automation Letters (RA-L)
- IEEE Transactions on Automation Science and Engineering (T-ASE)
- IEEE Transactions on Cognitive and Developmental Systems (TCDS)
- Neurocomputing
Teaching Assistant
- 2024-2025 Term2, Introduction to Systems Programming, IERG2080, CUHK
- 2024-2025 Term1, Problem Solving by Programming, ENGG1110B, CUHK
- 2023-2024 Term2, Introduction to Systems Programming, IERG2080, CUHK
- 2023-2024 Term1, Multimedia Coding and Processing, IERG4190/IEMS5707, CUHK