Mauro Castelli

Beyond Teleoperation: Enhancing VLA Robustness via Explicit Kinematic Retargeting of Human Demonstrations

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in generalized robotic control, yet their scalability is fundamentally bottlenecked by the high cost and low diversity of teleoperated data. While abundant, human demonstration videos cannot be directly utilized for policy training due to the...