SOURCE-LINKED INTELLIGENCE

GeomVLA: Unifying Scene, Motion, and Action in 3D

arXiv · AI, language, vision and robotics · article · Sep 12, 2026 · UTC

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 retaining the semantic representations learned during VLM pretraining. We further introduce a 3D Scene Trajectory Denoiser, a task-conditioned module that learns a latent representation of how scene points are expected to move in 3D. Rather than executing the predicted trajectory as an o

Read original source ↗ Open in workspace

recordType

paper

region

Global