Published multiple papers, including 'Latent Weight Diffusion: Generating reactive policies instead of trajectories' (2025) and 'Open X-Embodiment: Robotic Learning Datasets and RT-X Models' (2024, Best Conference Paper at ICRA 2024). Additionally, a paper on cross-morphology demonstration learning was accepted to CoRL 2023.
Research Experience
Currently a robotics researcher at Intrinsic, working with Stefan Schaal. Previously, he completed his PhD at the University of Southern California, focusing on learning visuomotor manipulation skills for robotic arms. He has also been involved in several research projects, such as founding the RASC Robotics Blog at USC and giving invited research talks on dexterous manipulation at various institutions.
Education
PhD in Computer Science (Robotics), 2024, University of Southern California, Advisor: Gaurav Sukhatme
Background
Research interests include dexterous robot manipulation, deformable objects, learning from demonstrations, and reinforcement learning. During his PhD, his thesis focused on learning visuomotor manipulation skills for robotic arms using LfD and RL methods, primarily applied to cloth manipulation and precision assembly tasks. He has also worked on combining planning algorithms with learning to achieve greater autonomy for robots.
Miscellany
Started the USC Robotics Seminar (URoS) along with Prof. Somil Bansal, providing a platform for robotics researchers at USC to present and discuss their work.