Picture taken in Sagrada Familia

Le Chen
陳樂

I am a Computer Science PhD student at the Empirical Inference department of Max Planck Institute for Intelligent Systems and ETH Zurich, advised by Prof. Bernhard Schölkopf and Prof. Dieter Büchler.

Previously, I obtained my M.S. in Electrical Engineering and Information Technology at ETH Zurich. I also spent time at Microsoft Mixed Reality & AI Lab in Zurich, Tencent AI Lab and Tencent Robotics X Lab.

I am interested in building general agents and robots that can perform a wide range of tasks. My research falls at the intersection of robotics and reinforcement learning. I am now working on dexterous manipulation.

E-Mail / LinkedIn / Github

Research

Generalist World Model Pre-Training for Efficient Reinforcement Learning

Preprint, 2025.

RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands

Conference on Robot Learning (CoRL), 2024
(*: equal contribution)

Safe & Accurate at Speed with Tendons: A Robot Arm for Exploring Dynamic Motion

Robotics: Science and Systems (RSS), 2024

GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation

Preprint, 2024.

Identifying Policy Gradient Subspaces

International Conference on Learning Representations (ICLR), 2024

LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry

IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024

Leveraging Neural Radiance Fields for Uncertainty Aware Visual Localization

IEEE International Conference on Robotics and Automation (ICRA), 2024

Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fields

IEEE Robotics and Automation Letters (RA-L), 2022
IEEE International Conference on Robotics and Automation (ICRA), 2023
(*: equal contribution)

Unified Data Collection for Visual-Inertial Calibration via Deep Reinforcement Learning

IEEE International Conference on Robotics and Automation (ICRA), 2022
(*: equal contribution)

Learning Trajectories for Visual-Inertial System Calibration via Model-based Heuristic Deep Reinforcement Learning

Conference on Robot Learning (CoRL), 2020
(*: equal contribution)

Jiles-Atherton Based Hysteresis Identification of Shape Memory Alloy-Actuating Compliant Mechanism via Modified Particle Swarm Optimization Algorithm

Complexity, vol. 2019.

Projects

Transition From Model-Based to Model-Free Actor-Critic Reinforcement Learning

Course Project in Deep Learning, 2020

Leveraging Pixel Correspondences for Sparse-to-Dense Feature-Metric Localization

Course Project in 3D Vision, 2020


Adapted from this awesome template