2 papers
cs.LG2026
Task Vectors Can Be Linearly Decomposed into Interpretable and Controllable Components
Yukiya Horiba, Hakaze Cho, Takahiro Yakoh
Task Vectors (TVs) provide a compact way to steer large language models, but they are typically treated as atomized directions merely extracted from hidden states, leaving their in…
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…