Brian Wei

I'm an undergraduate student at Washington University in St. Louis studying Data Science and Economics. I am also an undergraduate researcher in the Multimodal Vision Research Laboratory led by Dr. Nathan Jacobs.

I also served as an undergraduate research fellow in the Statistics and Data Science Summer Research Program, advised by Dr. Nan Lin.

Email  /  CV  /  Scholar  /  Github

profile photo

Research

I am interested in multimodal models, representation learning, controllable image and video generation, and developing efficient approaches for large-scale models. My work focuses on applications in remote sensing and natural image domains, and I am also eager to explore a broader range of topics.

     Publications

VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics
Dan Cher*, Brian Wei*, Srikumar Sastry, Nathan Jacobs
WACV, 2026
project page / github / arXiv

We introduce VectorSynth, a diffusion-based model that generates pixel-accurate satellite imagery from polygonal geographic annotations with semantic attributes, enabling spatially grounded, geometry- and language-guided image synthesis and editing.

     Projects

WashU Robotics Club
Jan 2023 - Dec 2024
website / github

I served as Co-President of the WashU Robotics Club, following my role as software lead on the rover project. Check out the club website for a look at the projects I was fortunate to work on during my time there!


Thank you to Jon Barron for the site template.