Alan Yu

I'm an MEng student at MIT LIDS advised by Luca Carlone. Previously, I did my B.S. in Artificial Intelligence ('24) at MIT, where I was fortunate to work with Ge Yang, Phillip Isola, and John Leonard at CSAIL. I study robot learning and am interested in helping robots understand the real world and its complexities.

Currently, I'm working on hierarchical scene representations and using synthetic data to train robots.

In my free time I enjoy swimming and attempting to play the guitar.

Email  /  Google Scholar  /  Twitter  /  Github

profile photo

Recent Updates

(more)
Nov '24 LucidSim was featured in MIT News, MIT Technology Review, and New Scientist!
Nov '24 Presented our work on Learning Visual Parkour from Generated Images at CoRL 2024.
Sep '24 Started my MEng at MIT LIDS, advised by Luca Carlone.

Research

LucidSim Preview
LucidSim: Learning Visual Parkour from Generated Images
Alan Yu*, Ge Yang*, Ran Choi, Yajvan Ravan, John Leonard, Phillip Isola
Conference on Robot Learning (CoRL) 2024
website / arXiv / code / video / news video / news

We use generative models as a realistic and diverse data source by augmenting classical physics simulators. We demonstrate that robots trained this way can accomplish highly dynamic tasks like parkour without requiring depth.

Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
William Shen*, Ge Yang*, Alan Yu, Jansen Wong, Leslie Pack Kaelbling, Phillip Isola
Conference on Robot Learning (CoRL) 2023 (Best paper award)
website / arXiv / code / video / news

We distill features from 2D foundation models into 3D feature fields, and enable few-shot language-guided manipulation that generalizes across object poses, shapes, appearances and categories.

Teaching

TA for Robotics: Science and Systems (6.4200), Spring 2025.

TA for Robotics: Science and Systems (6.4200), Spring 2024.


Website template provided by Jon Barron; profile picture courtesy of Mike Grimmett.