
CoRL 2026 Workshop
Description
A community-wide effort to unify simulation benchmarking and real-world robot deployment. Simulation has become the engine of modern embodied AI. Physics-grounded environments like BEHAVIOR provide the scale, safety, and reproducibility that physical data collection cannot, enabling agents to develop high-level reasoning, long-horizon planning, and dexterous bimanual manipulation across thousands of everyday scenarios.
Event location
Let your network know you`re going
Share this event to start conversations, invite colleagues, and connect before it begins.
Meet the speakers
Yilun Du
Theme:Harvard University - Compositional world models and diffusion policies for generalizable robot planning: from video-based planning to 4D embodied world models
Yashraj Narang
Theme:NVIDIA - GPU-accelerated simulation for scalable robot learning: Isaac Lab, MimicGen, and sim-to-real dexterous manipulation
Guannan Qu
Theme:Carnegie Mellon University - Foundations for scalable and reliable robot policy learning, interpretability for decision-making, physical understanding of learned models, and scalable multi-agent planning
Chen Tang
Theme:UC Los Angeles - Deep reinforcement learning for real-world robotics: lessons from simulation to deployment, hierarchical RL, and safe offline-to-online policy transfer










