Featured

Activation injection study dissects vision-language-action models

Researchers propose an interpretability pipeline to analyze what a fine-tuned vision-language-action (VLA) policy is computing internally. On pi0.5, injecting task A's activations into the action expert while the policy views task B's scene caused 99.6% of episodes (n=1968) to execute task A's motor trajectory, indicating the injected program is bound to absolute workspace coordinates and ignores the visible scene.

Part of the event: Study: pi0.5 actions bind to absolute coordinates

This page provides a summary and source link only.