Zhong-Yi Luo

Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models

Latent Interface Training (LIT), a framework-agnostic two-stage strategy that first establishes a spatial-goal-conditioned action prior without images, then constrains visual conditioning through a pose-supervised latent interface, improves overall LIBERO-Plus success while preserving or improving average LIBERO succes...