Xudong Xu     徐旭东

I am a researcher at Galbot, working on Embodied AI.

I recieved my Ph.D. degree from Multimedia Laboratory in the Chinese University of Hong Kong, advised by Prof. Dahua Lin. I recieved my B.E in Automation from Nanjing University in June 2018.

My research interests lie in creating interactive scenes for humanoid robotics, with a focus on humanoid navigation and loco-manipulation.
I am looking for highly motivated interns at Galbot. Please feel free to email me (xuxudong@galbot.com) if you are interested.

LinkedIn / Google Scholar / Github

Aug. 2018 - Mar. 2023, Department of Information Engineering, the Chinese University of Hong Kong

Ph.D. in Information Engineering

Sept. 2014 - Jun. 2018 , School of Management and Engineering, Nanjing University

Bachelor in Automation

GPA: 92.4/100, Rank: 1 / 37

RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation
Shujie Zhang^*, Jingkun Yi^*, ..., Xudong Xu⁺, Weinan Zhang, Chunhua Shen
Arxiv, 2026
[paper] [code] [project]

EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies
Ning Gao, Jinliang Zheng, Xing Gao, ..., Xudong Xu, ..., Chunhua Shen
Arxiv, 2026
[paper] [code] [project]

Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis
Yixuan Yang^*, Zhen Luo^*, Wanshui Gan^*, ..., Zhaoyang Lyu, Xudong Xu⁺
Arxiv, 2026
[paper] [code] [project]

EgoSim: Egocentric World Simulator for Embodied Interaction Generation
Jinkun Hao^*, Mingda Jia^*, ..., Jiangmiao Pang, Xudong Xu⁺
ECCV, 2026
[paper] [code] [project]

RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation
Boyang Wang^*, Haoran Zhang^*, Shujie Zhang^*, ..., Xudong Xu⁺, Jiangmiao Pang
Arxiv, 2026
[paper] [code] [project]

STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System
Zhen Luo^*, Yixuan Yang^*, Xudong Xu⁺, Jinkun Hao, Zhaoyang Lyu, Feng Zheng⁺, Jiangmiao Pang, Yanwei Fu
ICML, 2026
[paper] [code] [project]

MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning
Jinkun Hao^*, Naifu Liang^*, Zhen Luo^*, Xudong Xu⁺, ..., Jiangmiao Pang
NeurIPS, 2025 (Spotlight)
[paper] [code] [project]

InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts
Weipeng Zhong^*, Peizhou Cao^*, ..., Bo Dai, Xudong Xu⁺, Jiangmiao Pang⁺
NeurIPS, 2025
[paper] [code] [project]

AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
Lihan Jiang^*, Yucheng Mao^*, ..., Xudong Xu, ..., Dahua Lin, Bo Dai⁺
ACM Transactions on Graphics (Proc. SIGGRAPH Asia 2025)
[paper] [code] [project]

Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation
Xinyu Lian, Zichao Yu, ..., Xudong Xu⁺, Zhaoyang Lyu⁺, Bo Dai, Jiangmiao Pang
ArXiv, 2025
[paper] [code] [project]

Boosting 3D Object Generation through PBR Materials
Yitong Wang, Xudong Xu⁺, Li Ma, Haoran Wang, Bo Dai
SIGGRAPH Asia, 2024
[paper] [code] [project]

RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpainting
Qi Wang^*, Ruijie Lu^*, Xudong Xu⁺, ..., Bo Dai, Gang Zeng, Dan Xu
ECCV, 2024
[paper] [code] [project]

MATLABER: Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR
Xudong Xu, Yitong Wang, Zhaoyang Lyu, Xingang Pan, Bo Dai
ArXiv, 2023
[paper] [code] [project]

Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio
Xudong Xu, Dejan Markovic, Jacob Sandakly, Todd Keebler, Steven Krenn, Alexander Richard
NeurIPS, 2023 (Spotlight)
[paper] [code] [dataset]

InternVerse: A Simulation Data Platform for Embodied AI
[Try it!]
Intern Robotics Team, Shanghai AI Lab
[press1] [press2] [press3]