
Zhixian Xie
I am PhD student at Intelligent Robotics and Interactive Systems (IRIS) Lab at Arizona State University.
In 2022, I received my B.Eng degree in automation at Shanghai Jiao Tong University, Shanghai, China. I joined IRIS lab for PhD study in 2024.1, working with Dr. Wanxin Jin.




My Research
My research focuses on:
-
Robot Learning from Human I develop algorithms that enable robots to learn efficiently from human data—such as preferences, corrections, and demonstrations. I am interested in imitation learning and interactive learning paradigms to allow robots to generalize from limited supervision and align their behavior with human intent, facilitating natural and adaptive human-robot collaboration.
-
Dexterous Manipulation I design model-based and model-free methods for dynamic, contact-rich manipulation with high-DOF robotic hands. My research integrates control theory and learning to enable robust, generalizable skills such as in-hand reorientation and non-prehensile manipulation, advancing autonomous dexterity in real-world settings.
Publication & Preprints
Safe MPC Alignment with Human Directional Feedback
Zhixian Xie, Wenlong Zhang, Yi Ren, Zhaoran Wang, George. J. Pappas and Wanxin Jin
Preprint, submitted to IEEE Transactions on Robotics (T-RO)
[PDF]/
[Code]/
[Video]/
[Webpage]
Language-Model-Assisted Bi-Level Programming for Reward Learning from Internet Videos
Harsh Mahesheka, Zhixian Xie, Zhaoran Wang, Wanxin Jin
arXiv preprint, 2024
[PDF]/
[Video]/
[Webpage]
Robust Reward Alignment via Hypothesis Space Batch Cutting
Zhixian Xie, Haode Zhang, Yizhe Feng, Wanxin Jin
Accepted by ICML 2025
[PDF]/
[Code]/
[Webpage]
On-Palm Dexterity: Dynamic Reorientation of Objects
via Emergent Flipping and Sliding
Zhixian Xie, Wen Yang, Wanxin Jin
ICRA 2025 Workshop on Learning Meets Model-Based Methods for Contact-Rich Manipulation
[PDF]/
[Webpage]
TwinTrack: Bridging Vision and Contact Physics for Real-Time Tracking of Unknown Dynamic Objects
Wen Yang, Zhixian Xie, Xuechao Zhang, Heni Ben Amor, Shan Lin, Wanxin Jin
arXiv preprint, 2025
[PDF]/
[Webpage]/
[Video]