Preprint
Aug 2026
Uncovering and Mitigating Positional Blind Spots in Vision-Language-Action Models
This paper proposes a two-stage black-box framework to uncover and mitigate Positional Blind Spots, and evaluates its framework on five state-of-the-art VLA policies across two benchmarks, and finds that PBS are pervasive and spatially concentrated in all of them.
Dongdong An, Pengjie Zhao, Yihao Huang et al.
· 0 citations