EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video (Best Paper Award at RSS2025 EgoAct Workshop)
EMOTION: Expressive Motion Sequence Generation for Humanoid Robots with In-Context Learning (2025 IEEE Robotics and Automation Letters, RA-L)
CaDRE: Controllable and Diverse Generation of Safety-Critical Driving Scenarios using Real-World Trajectories (2025 IEEE International Conference on Robotics and Automation, ICRA 2025)
Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications (2024 IEEE Robotics and Automation Letters, RA-L)
Gradient Shaping for Multi-Constraint Safe Reinforcement Learning (6th Annual Learning for Dynamics & Control Conference, L4DC 2024)
Creative Robot Tool Use with Large Language Models (Preprint)
What Went Wrong? Closing the Sim-to-Real Gap via Differentiable Causal Discovery (7th Annual Conference on Robot Learning, CoRL 2023)
Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables (The 26th International Conference on Artificial Intelligence and Statistics, AISTATS 2023)
Continual Vision-based Reinforcement Learning with Group Symmetries (7th Annual Conference on Robot Learning, CoRL 2023, Oral, 6.6%)
Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation (The 36th Conference on Neural Information Processing Systems, NeurIPS 2022)
Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training (The 31st International Joint Conference on Artificial Intelligence, IJCAI 2022)
Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling (2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022)
Research Experience
09/2025: Joined Google DeepMind!
09/2024: Joined Apple AIML!
09/2024: Defended thesis titled 'Co-evolving Environments and Agents for Physical-World Deployments'!
11/2023: RoboTool covered by TechXplore as a featured story!
08/2023: Two papers (one Oral) accepted by CoRL 2023!
Background
A researcher at Google DeepMind, working on robot foundation models. Previously worked at Apple. Obtained B.E. from Nanyang Technological University, M.S. from Stanford, and Ph.D. from Carnegie Mellon University.