Jianglan Wei

I am a senior undergrad in Artificial Intelligence at Huazhong University of Science and Technology and a research intern at UC Berkeley, advised by Prof. Masayoshi Tomizuka. My research focuses on robot learning, where I develop reinforcement learning algorithms to generate control policies and world models to anticipate the consequences of robot actions.

Email  /  CV  /  Scholar  /  Github

profile photo

News

May 2025 Selected as student speaker at the Berkeley Global Access closing ceremony.
Dec 2024 Awarded the UC Berkeley BGA Scholarship 2024 (Top 10 students).
Nov 2024 Joined the MSC lab as a research intern, advised by Prof. Masayoshi Tomizuka.
Nov 2024 Won the National First Prize in CUMCM 2024 (Top 0.5% among 59,278 teams).
Sept 2024 Began studies at UC Berkeley as a visiting student.

Research

clean-usnob

Reimagination with Test-time Observation Interventions: Distractor-Robust World Model Predictions for Visual Model Predictive Control
Yuxin Chen*, Jianglan Wei*, Chenfeng Xu, Boyi Li, Masayoshi Tomizuka, Andrea Bajcsy, Ran Tian

RSS Workshop on OOD, 2025 (Oral, Best Paper Finalist)
Under Review as a Conference Paper
arXiv

clean-usnob

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), 2025
arXiv / Project Page

clean-usnob

Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image
Cunxin Fan*, Xiaosong Jia*, Yihang Sun, Yixiao Wang, Jianglan Wei, Ziyang Gong, Xiangyu Zhao, Masayoshi Tomizuka, Xue Yang, Junchi Yan, Mingyu Ding,

ICRA Workshop on VLMs in Robotics, 2025 (Oral, Spotlight)
Under Review as a Conference Paper
arXiv

clean-usnob

HDC-X: Efficient Medical Data Classification for Embedded Devices
Jianglan Wei*, Zhenyu Zhang*, Pengcheng Wang*, Mingjie Zeng, Zhigang Zeng

Under Review as a Conference Paper
arXiv / Code

clean-usnob

CodeAvatar: Learning Animatable Occlusion-Aware 3D Avatars in the Wield via Codebook Lookup Transformers
Qinzheng Zhou*, Hao Wang*, Jianglan Wei, Lijing Lu, Zhihang Li

Under Review as a Conference Paper
PDF

Course Project

clean-usnob clean-usnob

UC Berkeley CS180/280A: Intro to Computer Vision and Computational Photography
Course taught by Alexei Efros

Main Page / Code
Page by Project: Project 1 / Project 2 / Project 3 / Project 4 / Project 5 / Project 6


Template stolen from Jon Barron.