About me

I am a Ph.D. student working on robotics and machine learning. My research interests include leveraging robot manipulation by imitation learning, reinforcement learning, and streamlining robotic systems to fulfill real-world applications. Currently, I am working on applying geometric deep learning to SE(3) robotic policy learning.

(2025 Summer) I am currently seeking a full-time research position in robotics to contribute to impactful work in the industry.

Besides being passionate about robotics, I also enjoy mountain and road biking, photography, and watching inspiring videos on YouTube.

Internship

• (2024 Summer) Amazon Robotics, supervised by Jane Shi and Fan Wang.
• (2023 Summer) Robotics and AI Institute, supervised by Prof. Aaron Dollar.

Education

• (2020-Present) Ph.D., Khoury College of Computer Sciences , Northeastern University. I am working in The Helping Hands Lab, advised by Professor Robert Platt.

• (2017-2020) M.S, Robotics, Northeastern University, Boston, MA, USA

• (2013-2017) B.S, Automation, South China University of Technology, Guangzhou, Guangdong, China

Publication

EquAct: An SE(3)-Equivariant Multi-Task Transformer for Open-Loop Robotic Manipulation
Xupeng Zhu, Yu Qi, Yizhe Zhu, Robin Walter*, Robert Platt*
In submission
` `
` `

SE(3)-Equivariant Diffusion Policy in Spherical Fourier Space
Xupeng Zhu, Fan Wang, Robin Walters, Jane Shi
ICML 2025
(Axiv is coming soon) (Code is coming soon)

` `
` `

Forces for Free: Vision-Based Contact Force Estimation with a Compliant Hand
Yifan Zhu*, Mei Hao*, Xupeng Zhu*, Quentin Bateux, Alex Wong, Aaron M. Dollar
Science Robotics 2025
` `
` `

Hierarchical Equivariant Policy via Frame Transfer
Haibo Zhao*, Dian Wang*, Yizhe Zhu, Xupeng Zhu, Owen Howell, Linfeng Zhao, Yaoyao Qian, Robin Walters, Robert Platt
ICML 2025
` `
` `

Push-Grasp Policy Learning Using Equivariant Models and Grasp Score Optimization
Boce Hu*, Heng Tian*, Dian Wang, Haojie Huang, Xupeng Zhu, Robin Walters, Robert Platt
Preprint
(Arxiv) ` `
` `

Coarse-to-Fine 3D Keyframe Transporter
Xupeng Zhu, David Klee*, Dian Wang*, Boce Hu, Haojie Huang, Arsh Tangri, Robin Walters, Robert Platt
Preprint
(Arxiv) ` `
` `

Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D
Haojie Huang, Owen Lewis Howell*, Dian Wang*, Xupeng Zhu*, Robert Platt^†, Robin Walters^†
ICLR 2024, Vienna, Austria
(Website) (Openreview) (Video) ` `
` `

A General Theory of Correct, Incorrect, and Extrinsic Equivariance
Dian Wang, Xupeng Zhu, Jung Yeon Park, Robert Platt, Robin Walters
NeurIPS 2023
(PDF) (Code) (Video) ` `
` `

On Robot Grasp Learning Using Equivariant Models
Xupeng Zhu, Dian Wang, Guanang Su, Ondrej Biza, Robin Walters, Robert Platt
Autonomous Robots. 2023
(PDF) (Code) (Website) (Arxiv) ` `
` `

SEIL: Simulation-augmented Equivariant Imitation Learning
Mingxi Jia*, Dian Wang*, Guanang Su, David Klee, Xupeng Zhu, Robin Walters, Robert Platt
* Equal Contribution
ICRA 2023, London, UK
(PDF) (Page) (Video) ` `
` `

Edge Grasp Network: Graph-Based SE(3)-invariant Approach to Grasp Detection
Haojie Huang, Dian Wang, Xupeng Zhu, Robin Walters, Robert Platt
ICRA 2023, London, UK
(PDF) (Page) (Code) ` `
` `

Integrating Symmetry into Differentiable Planning with Steerable Convolutions
Linfeng Zhao, Xupeng Zhu*, Lingzhi Kong*, Robin Walters, Lawson L.S. Wong
ICLR 2023, RLDM 2022
(PDF) (Code) (Page) ` `
` `

On-Robot Learning With Equivariant Models
Dian Wang, Mingxi Jia, Xupeng Zhu, Robin Walters, Robert Platt
CoRL 2022, Auckland, New Zealand
(Webpage) (PDF) (OpenReview) (Video) ` `
` `

BulletArm: An Open-Source Robotic Manipulation Benchmark and Learning Framework
Dian Wang, Colin Kohler, Xupeng Zhu, Mingxi Jia, Robert Platt
ISRR 2022, Geneva, Switzerland
(PDF) (Code) ` `
` `

Sample Efficient Grasp Learning Using Equivariant Models
Xupeng Zhu, Dian Wang, Ondrej Biza, Guanang Su, Robin Walters, Robert Platt
RSS 2022, New York, USA
(PDF) (Code) (Website) (Video) ` `
` `

Equivariant Q Learning in Spatial Action Spaces
Dian Wang, Robin Walters, Xupeng Zhu, Robert Platt
CoRL 2021, London, UK
(PDF) (OpenReview) (Poster) (Page) (Video) (Code) ` `
` `

Two Hybrid End-Effector Posture-Maintaining and Obstacle-Limits Avoidance Schemes for Redundant Robot Manipulators
Zhijun Zhang, Siyuan Chen, Xupeng Zhu, Ziyi Yan
IEEE Transactions on Industrial Informatics, vol. 16, no. 2, pp. 754-763, Feb. 2020
(PDF) ` `
` `

* indicates equal contribution; ^† indicates equal advising.

Service

Reviewer: ICML2025, CoRL2024-2022, ICRA2024-2023, T-RO2022

Teaching Assistant: CS5180 Reinforcement Learning, CS5100 Introduction to AI