Jul 2026
What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle Learning
A counterfactual ablation framework called Counterfactual Vision Action Analysis (CVAA) is proposed that systematically removes individual detected objects from front-camera images using photorealistic generative inpainting to prepare counterfactual sets to evaluate the difference in the model's response.
Kalpana Panda, W. Maia, Vinti Agarwal et al.
· arXiv.org · 1 citation