نسخة أولية وصول مفتوح
GeomVLA: Unifying Scene, Motion, and Action in 3D
We present GeomVLA, a Vision-Language-Action (VLA) model that unifies perception, latent scene motion prediction, and action generation within a shared robot-centric 3D coordinate frame. Our approach lifts pretrained VLM features into spatially grounded 3D scene tokens using depth and camera calibration, while retainin …