Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action Models
Abstract
Vision-Language-Action (VLA) policies often fail under distribution shift, suggesting that decisions may depend on spurious visual correlations rather than task-relevant causes. We formulate visual-action attribution as an interventional estimation problem. Accordingly, we introduce the Interventional Significance Score (ISS), an interventional masking procedure for estimating the causal influence of visual regions on action predictions, and the Nuisance Mass Ratio (NMR), a scalar measure of attribution to task-irrelevant features. We analyze the statistical properties of ISS and show that it admits unbiased estimation, and we characterize conditions under which action prediction error provides a valid proxy for causal influence. Experiments across diverse manipulation tasks indicate that NMR predicts generalization behavior and that ISS yields more faithful explanations than existing interpretability methods. These results suggest that interventional attribution provides a simple diagnostic approach for identifying causal misalignment in embodied policies.
Cite
@article{arxiv.2605.00321,
title = {Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action Models},
author = {Hanxin Zhang and Mingshuo Xu and Abdulqader Dhafer and Shigang Yue and Hongbiao Dong and Zhou Daniel Hao},
journal= {arXiv preprint arXiv:2605.00321},
year = {2026}
}
Comments
Accepted at the 43rd International Conference on Machine Learning (ICML 2026)