2 papers
cs.CV2026
Gauge-Equivariant Attention for Rotation-Stable Scene Understanding
Tianjian Zhou, Yishan Li, Jie Jiang +1
Panoramic scene understanding increasingly relies on icosphere transformers, but a state-of-the-art spherical model loses more than half of its segmentation accuracy wh…
cs.CR2026
SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
Yunhao Feng, Yifan Ding, Yingshui Tan +6
Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We…