Pu Yang

Allocating additional computation during decision-making boosts long-horizon robot manipulation success by significantly enhancing subtask prediction accuracy.

$\tau_0$-WM outperforms traditional models by seamlessly integrating action prediction and evaluation, leading to superior performance in complex robotic tasks.

Generalist robot policies can achieve 95% success rates on real-world manipulation tasks by continually learning from a fleet of robots, even in the face of distribution shifts and long-tail failures.