VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling

Understand

Vision-language-action (VLA) models achieve strong in-distribution performance but degrade sharply under novel camera viewpoints and visual perturbations.

• We show that this brittleness primarily arises from misalignment in Spatial Modeling, rather than Physical Modeling.
• To address this, we propose a one-shot adaptation framework that recalibrates visual representations through lightweight, learnable updates.
• Our first method, Feature Token Modulation (FTM), applies a global affine transformation to visual tokens and improves Libero viewpoint accuracy from 48.5% to 87.1% with only 4K parameters.