Third-year CS PhD at USC, working with Yue Wang.
One model should be enough — to see, to imagine, to understand, to create. I work on making that model simple, scalable, and real, with a focus on vision-centric unified multimodal systems.
“Make things as simple as possible, but not simpler.”
My earlier work spans 3D/4D scene reconstruction, self-supervised learning, and visual representation. Long live representation learning!