Yanshuo Lu

Spatial-semantic prompting outperforms traditional text-only methods in embodied visual tracking, especially in complex environments with similar distractors.

Humanoid robots can now achieve superior stability and accuracy in unpredictable environments by leveraging a physics-based disturbance observer that operates without force sensors.

EM-Fall's embodied sensing approach enables humanoid robots to maintain effective fall detection even in challenging environments, outperforming traditional systems.

Robots can now understand and act on your gaze while following language commands, enabling more intuitive and precise human-robot collaboration.

Forget retargeting: RoboForge's physics-optimized pipeline lets humanoids nail text-guided locomotion with better accuracy and stability.