NVIDIA AI Introduce SpatialClaw: A Training-Free Agent That Treats Code as the Action Interface for Spatial Reasoning
NVIDIA Research has launched SpatialClaw, a training-free framework for spatial reasoning. It targets a persistent weak point in vision-language fashions (VLMs). These fashions nonetheless battle to evaluate the place objects are, how they relate, and the way they transfer in 3D. SpatialClaw doesn’t retrain the mannequin. Instead, it adjustments the motion interface the agent makes…
