Zhiyu Huang

A fixed-size latent memory, explicitly optimized for robotic control via question-answering and DINO feature reconstruction, unlocks state-of-the-art long-horizon manipulation performance.

SCAPE reduces scenario-level prediction error by up to 34.7%, enabling safer and more efficient deployment of robot-learning policies in real-world environments.

Autonomous driving policies that ace open-loop tests can still crash and burn in the real world, because they learn to ignore the reactive nature of closed-loop environments.