Xilun Zhang

I am a second-year PhD student in the Autonomous Systems Lab at Stanford University, advised by Prof. Marco Pavone. I also work with Prof. Chelsea Finn. I previously worked with Mengdi Xu and Prof. Ding Zhao at Carnegie Mellon University, and Prof. Mo Chen at Simon Fraser University.

I am passionate about intelligent decision-making algorithms with applications in Robotics. I am particularly interested in building adaptive robotic systems through approaches such as dynamics learning, test-time verification, and agentic systems. If you're interested in collaboration, feel free to reach out to me via email and I am always happy to chat!

Email Scholar GitHub X / Twitter
Xilun Zhang

News

Publications

Robo-COP
Co-Evolving Robot Orchestrators and Policies through Deployment
Xilun Zhang, Maggie Wang, Erik Bauer, Hong-Xing Yu, Huang Huang†, Jiajun Wu†, Marco Pavone†
arXiv preprint, 2026. † equal advising.
paper webpage
CoVer-VLA
Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment
Jacky Kwok*, Xilun Zhang*, Mengdi Xu, Yuejiang Liu†, Azalia Mirhoseini†, Chelsea Finn†, Marco Pavone†
European Conference on Computer Vision (ECCV), 2026. * equal contribution, † equal advising.
Abridged in CVPR 2026 ScaleBot Workshop. (Best Paper Finalist)
paper webpage
CAPTURE
Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications
Xilun Zhang*, Shiqi Liu*, Peide Huang, William Jongwon Han, Yiqi Lyu, Mengdi Xu, Ding Zhao
IEEE Robotics and Automation Letters (RA-L), 2025. * equal contribution.
Abridged in AAAI 2025 Workshop on Multi-Agent AI in the Real World. (oral presentation)
paper webpage
HJ-ARL
Learning Robust Policies via Interpretable Hamilton-Jacobi Reachability-Guided Disturbances
Hanyang Hu, Xilun Zhang, Xubo Lyu, Mo Chen
IEEE International Conference on Robotics and Automation (ICRA), 2025.
Abridged in AAAI 2025 Workshop on Multi-Agent AI in the Real World. (oral presentation)
paper
RoboTool
Creative Robot Tool Use with Large Language Models
Mengdi Xu*, Peide Huang*, Wenhao Yu*, Shiqi Liu, Xilun Zhang, Yaru Niu, Tingnan Zhang, Fei Xia, Jie Tan, Ding Zhao
CoRL 2023 Workshop on Language and Robot Learning. * equal contribution.
paper webpage
CoVeRS
Continual Vision-based Reinforcement Learning with Group Symmetries
Shiqi Liu*, Mengdi Xu*, Peide Huang, Xilun Zhang, Yongkang Liu, Kentaro Oguchi, Ding Zhao
Conference on Robot Learning (CoRL), 2023. (oral, 6.6%) * equal contribution.
Abridged in RSS 2023 Workshop on Symmetries in Robot Learning.
paper webpage
COMPASS
What Went Wrong? Closing the Sim-to-Real Gap via Differentiable Causal Discovery
Peide Huang, Xilun Zhang*, Zi-ang Cao*, Shiqi Liu*, Mengdi Xu, Wenhao Ding, Jonathan Francis, Bingqing Chen, Ding Zhao
Conference on Robot Learning (CoRL), 2023. * equal contribution.
Abridged in IROS 2023 Workshop on Causality for Robotics: Answering the Question of Why.
paper webpage

Teaching

Service

Projects

BeamWalking
Generalizable BeamWalking for Legged Robots with Reinforcement Learning
Xilun Zhang, Changyi Lin, Zongyuan Wu, Jian Chen
16-831: Intro to Robot Learning (by Deepak Pathak)
paper
HJ Reachability
Enhancing Robustness of Reinforcement Learning using Hamilton-Jacobi Reachability
Xilun Zhang
16-886: Models & Algorithms for Interactive Robotics (by Andrea Bajcsy)
Website Template