VLA-Scope: Shift-Aware Failure Prediction for Vision-Language-Action Models
VLA-Scope is introduced, a two-stage framework that combines input-shift characterization with execution history to predict failure during OOD rollouts and achieves a higher ROC-AUC than the evaluated ActProbe and SAFE-MLP baselines.
Kai-Wen Zhu, Dongfang Liu, Liang-Kai Liu
· 0 citations