David Held

Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling

Differentiable Trajectory Optimization as a Policy Class for Reinforcement and Imitation Learning

DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning

Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks

GenBot: Generative Simulation Empowers Automated Robotic Skill Learning at Scale