Jun Wang

Hi, I’m currently pursuing a Master’s degree in Computer Science at UC San Diego, where I am fortunate to have the guidance of Professor Xiaolong Wang, researching on robotics, imitation learning, computer vision. Additionally, I am also collaborating closely with Professor Taylor Berg-Kirkpatrick to explore the exciting possibilities of zero-shot singing voice synthesis in the realm of computer music.

Prior to my Master’s degree, I completed my bachelor’s degree in Computer Science at Zhejiang University, under the guidance of Professor Amy Yuexuan Wang.

Before pursuing my master program, I had the privilege of interning in the speech research team at 4paradigm for 3 months in 2022.

With diverse research interests spanning various fields, I am driven to explore the potential of utilizing audio, vision, and language in the realm of embodied AI and beyond.

Apart from my academic pursuits, I am an avid fan of Arsenal FC. In my spare time, I enjoy playing soccer and badminton. I am also passionate about musicals and was actively involved in a club during my undergraduate studies, where I helped prepare several musical performances.

selected publications

CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation

Jun Wang*, Yuzhe Qin*, Kaiming Kuang, Yigit Korkmaz, Akhilan Gurumoorthy, Hao Su, and Xiaolong Wang

CVPR 2024, Nov 2023

Abs HTML PDF

We introduce CyberDemo, a novel approach to robotic imitation learning that leverages simulated human demonstrations for real-world tasks. By incorporating extensive data augmentation in a simulated environment, CyberDemo outperforms traditional in-domain real-world demonstrations when transferred to the real world, handling diverse physical and visual conditions. Regardless of its affordability and convenience in data collection, CyberDemo outperforms baseline methods in terms of success rates across various tasks and exhibits generalizability with previously unseen objects. For example, it can rotate novel tetra-valve and penta-valve, despite human demonstrations only involving tri-valves. Our research demonstrates the significant potential of simulated human demonstrations for real world dexterous manipulation tasks.