activity
20202026
most citedUnderstanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields

7 citations · 25 across the 29 of their papers we have counts for

collaborators
Showing cs.ROShow all

1 paper · 1 filter

cs.RO2026

Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models

Yukiya Horiba, Koshiro Aoki, Shunsuke Yasuki +2

Adversarial patches can disrupt Vision-Language-Action (VLA) models by manipulating visual observations, leading to failures in robot control. However, it remains poorly understood…