Jianglan Wei

Robotics Institute, Carnegie Mellon University

I am an MS Robotics student at Carnegie Mellon University, advised by Prof. David Held. Before joining CMU, I was an undergraduate researcher at UC Berkeley with Prof. Masayoshi Tomizuka.

My current research focuses on generalist policies for dexterous manipulation. I am working towards a future where robots can do anything humans can do, and more!

Jianglan Wei Profile Picture

News

Joined the Robot Perceiving and Doing (RPAD) Lab at CMU, advised by Prof. David Held.

Attended ICRA 2026 in Vienna to present the ReOI World Model (photo).

Awarded the Chiang Chen Overseas Fellowship ($50,000) to support my graduate studies.

Older news (before 2026)

Attended CoRL 2025 in Seoul to present MEReQ (photo).

Invited to deliver the student address at the Berkeley Global Access closing ceremony.

Awarded the UC Berkeley BGA Scholarship 2024 (Top 10 students per term).

Won the National First Prize in the Contemporary Undergraduate Mathematical Contest in Modeling (CUMCM) 2024 (Top 0.5% among 59,278 teams).

Joined the Mechanical Systems Control (MSC) Lab at UC Berkeley, advised by Prof. Masayoshi Tomizuka (our photo).

Research

Reimagination with Test-time Observation Interventions

Yuxin Chen*, Jianglan Wei*, Chenfeng Xu, Boyi Li, Masayoshi Tomizuka, Andrea Bajcsy, Ran Tian

IEEE International Conference on Robotics and Automation (ICRA),
Best Paper Finalist at RSS Out-of-Distribution Workshop,

arXiv website

MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention

Yuxin Chen*, Chen Tang*, Jianglan Wei, Chenran Li, Ran Tian, Xiang Zhang, Wei Zhan, Peter Stone, Masayoshi Tomizuka

Conference on Robot Learning (CoRL),

arXiv website

Interleave-VLA: Enhancing Robot Manipulation with Interleaved Instructions

Cunxin Fan*, Xiaosong Jia*, Yihang Sun, Yixiao Wang, Jianglan Wei, Ziyang Gong, Xiangyu Zhao, Masayoshi Tomizuka, Xue Yang, Junchi Yan, Mingyu Ding

International Conference on Learning Representations (ICLR),

arXiv website

HD3C: Efficient Medical Data Classification for Edge Devices

Jianglan Wei*, Zhenyu Zhang*, Pengcheng Wang*, Mingjie Zeng, Zhigang Zeng

CAAI International Conference on Artificial Intelligence (CICAI),

arXiv code patent

DSN: Energy-Efficient EMG Signal Classification Method Enabling Real-Time Monitoring for Edge Healthcare

Zhenyu Zhang*, Xiaozhe Meng*, Jianglan Wei, Mingjie Zeng, Xianzhe Meng, Zhigang Zeng

Neural Networks, Vol. 205

paper

Projects

Computer Vision and Computational Photography

UC Berkeley CS180 taught by Prof. Alexei Efros (Fall 2024).

website code

By chapter: coloring, blending, morphing, stitching, diffusion, NeRF

Autonomous Vehicle Mapping and Navigation

Final project for Autonomous Systems at HUST (Fall 2025).

code study notes

Study Notes

I believe the best way to learn is by building projects and taking notes along the way. Most of my notes are adapted from existing tutorials with a different emphasis on the details. Here is a selection of my notes that are ready for sharing.

ROS 2 Notes

Notion

Web Design Notes

Notion

Terminal Command Notes (Linux)

Notion