Hi, I'm Wanhee Lee, a PhD candidate at Stanford University.

My research centers on scalable autoregressive transformers for visual perception, controllable generation, and multimodal reasoning over spatiotemporal data. I develop unified models that jointly learn from RGB, depth, optical flow, and camera motion, with flexible any-to-any conditioning and generation capabilities. This framework enables a broad range of tasks, including novel view synthesis, rigid and deformable object manipulation, collision reasoning, and geometry extraction.

I would be happy to connect if you are interested in my work.
(Email: wanhee.ai AT gmail.com / Twitter: @lee_wanhee_)

During my PhD, I have been very fortunate to work with Dr. Dan Yamins.