Phd Student
CurrentWorking on 3D scene and language to action models, designed for Robotic Manipulation (specifically: Multi-Task Keysteps Action Prediction from 3D and Language inputs). I focus my work on making these models better generalize to novel scenarios.My long term goal is to enable AI to perceive and act in the physical world.Supervised by Cordelia Schmid (Google/Inria) and Shizhe Chen (Inria).