Publications
Zirui Wang, Shuda Li, Henry Howard-Jenkins, Victor Adrian Prisacariu, Min Chen
arXiv
I am a research scientist at Goertek USA, working on advancing robotic Vision-Language-Action (VLA) models with egocentric data.
I received my PhD from the University of Oxford and later continued as a postdoctoral researcher in the same group, the Active Vision Lab, advised by Victor Adrian Prisacariu and Min Chen. My work focuses on deep learning for 3D systems.
My MSc was completed at the University of Bristol, where I worked on high frame-rate videos advised by David Bull.
More broadly, I am interested in how 3D geometry-constrained deep learning may improve biomolecular modeling.
Zirui Wang, Shuda Li, Henry Howard-Jenkins, Victor Adrian Prisacariu, Min Chen
arXiv