Xuanbin Peng 彭宣滨

Email: xup004[at]ucsd.edu

Office: Jacobs 4511

I am currently a research assistant at University of California, San Diego (UCSD) advised by Prof. Xiaolong Wang.

My research interest lies in the intersection of robotics, perception, planning, reasoning, and decision-making, with their application in complex, real-world environments.

While immersed in the academic field, I also appreciate letting loose by playing basketball and table tennis during my spare time. Furthermore, philosophy and poetry also interest me a lot.

I remain open and eager to collaborate with like-minded individuals to discover the potential and possibilities of robotics across various fields.

profile photo

Research

My current research interest lies in data-centric learning, compositionality, mobile manipulation and whole-body control. My long-term goal is to develop general-purpose intelligent robots that can infer and interact with the dynamic and open world environment over long-horizon with adaptability, generalizability, dexterity, and safety.

* denotes equal contribution

Publication Image

Exbody2: Advanced Expressive Humanoid Whole-Body Control

Mazeyu Ji*, Xuanbin Peng*, Fangchen Liu, Ge Yang, Jialong Li, Xuxin Cheng, Xiaolong Wang

A generalized whole-body tracking framework that can take any reference motion inputs and control the humanoid to mimic the motion.

Arxiv

project page/paper/video

New Scientist / explorersweb / LifeScience / TechEblog

Publication Image

WildLMa: Long Horizon Loco-Manipulation in the Wild

Ri-Zhao Qiu*, Yuchen Song*, Xuanbin Peng*, Sai Aneesh Suryadevara, Ge Yang, Minghuan Liu, Mazeyu Ji, Chengzhe Jia, Ruihan Yang, Xueyan Zou, Xiaolong Wang

Integrate an LLM-based high-level planner, an imitation learning skill library, and a learned whole-body controller for in-the-wild loco-manipulation over long-horizon.

IEEE International Conference on Robotics and Automation (ICRA) 2025.

Accepted

project page/paper/video

Yahoo News / Interesting Engineering / Gadgets360 / TechXplore

Publication Image

3D-Spatial Multimodal Memory

Xueyan Zou, Yuchen Song, Ri-zhao Qiu, Xuanbin Peng, Jianglong Ye, Sifei Liu, Xiaolong Wang

Integrate embeddings from foundation models and 3D Gaussian Splatting to restore rich semantic knowledge and 3D-sptial information.

The International Conference on Learning Representations (ICLR) 2025.

Accepted

project page/paper/video/code


Academic Services

Journal Reviewer:

  • IEEE Robotics and Automation Letters (RAL), 2024

Conference Reviewer:

  • IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025
  • Conference on Robot Learning (CoRL), 2025
  • Robotics: Science and Systems (RSS), 2025