RigidFormer: Learning Rigid Dynamics and Beyond with Transformers
NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception
A High-Fidelity Simulation Benchmark for Underwater Robot Co-Design
Scaling Cross-Embodiment World Models for Dexterous Manipulation
Towards Embodiment Scaling Laws in Robot Locomotion
SHEC3R: Robot-Grounded Visual Geometry for Stationary Hand-Eye Calibration
Tactile-Driven Dexterous Grasp Refinement under Uncertain One-Shot Perception
Toward High-Fidelity Simulation for Contact-Rich Robotic Manipulation
TOPORETARGET: Interaction-Preserving Retargeting for Sim-to-Real Dexterous Manipulation
Learning on the Fly: Rapid Policy Adaptation via Differentiable Simulation
MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation
Contact-UAN: Unsupervised Actuator Networks as a Residual World Model for Humanoid Control
FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control
Catch It All!: Generalizable Dynamic Catching with a Dexterous Hand
OmniXtreme: Actuation-Aware Sim-to-Real Transfer for High-Dynamic Humanoid Skills