|

|

My research focuses on building the intelligence for manipulation robots to operate autonomously. As a Staff Research Scientist at NVIDIA, I lead the development of modular Gen AI frameworks for manipulation, such as synthetic data, trajectory and grasp generation. For my work on being the first to deploy deep-learning policies on home robots and scaling robot learning in simulation, I was featured on the MIT TR35 Innovators 2025 List. My work has been frequently reported in the popular media e.g. TechCrunch, The New York Times, WIRED, The Robot Report. Before NVIDIA, I received my PhD from CMU Robotics Institute and my BS in EECS from UC Berkeley.

News

[09/2025] Serving as CoRL 2025 Sponsorships chair. See you in Seoul!
[07/2025] We just opensourced GraspGen, our framework for diffusion-based grasp generation!
[06/2025] Invited talk at CVPR 2025 2nd Point Cloud Tutorial
[03/2025] GraspGen integrated into Intrinsic Flowstate
[03/2025] Invited talks at Wadhwani School of Data Science and AI, IIT-Madras (India) and NUS (Singapore)
[06/2024] RoboPoint and DiffusionSeeder presented at CoRL 2024
[05/2024] Released results on smart pick and place with NVIDIA Isaac Manipulator. 55+ media articles. Invited talk at Automate 2024 hosted by Intrinsic.ai

Selected Projects

cuRoboV2: Dynamics-Aware Motion Generation with Depth-Fused Distance Fields for High-DoF Robots
arXiv
SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL
CVPR 2026 | arXiv / code
Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
arXiv / code
Grasp-MPC: Closed-Loop Visual Grasping via Value-Guided Model Predictive Control
ICRA 2026 | arXiv
scene_synthesizer: A Python Library for Procedural Scene Generation in Robot Manipulation
Journal of Open Source Software 2025 | paper / documentation / code
DiffusionSeeder: Seeding Motion Optimization with Diffusion for Rapid Motion Planning
CoRL 2024 | arXiv
CabiNet: Scaling Neural Collision Detection for Object Rearrangement with Procedural Scene Generation
ICRA 2023 , NeurIPS FM for Decision Making Workshop | project page / arXiv / video / talk / code
6-DOF Grasping for Target-driven Object Manipulation in Clutter
ICRA 2020 | arXiv / video / talk / NVIDIA Blog
Best Robot Manipulation Paper Finalist, Best Student Paper Finalist
Learning by Observation for Surgical Subtasks: Multilateral Cutting of 3D Viscoelastic and 2D Orthotropic Tissue Phantoms
ICRA 2015 | video / New York Times / MedGadget / CBS News
Best Medical Robotics Paper Finalist, Best Conference Paper Finalist
A Single-Use Haptic Palpation Probe for Locating Subcutaneous Blood Vessels in Robot-Assisted Minimally Invasive Surgery
CASE 2015 | paper Best Paper, ICRA Medical Robotics Workshop 2015
A Morphological Study on Direct Polymer Cast Micro-textured Hydrophobic Surfaces
Surface and Coatings Technology 2011 | The Straits Times

Press Coverage

TechCrunch The Robot Report New York Times WIRED The Straits Times CBS News CNET