4 papers
Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking
Jinquan Zhang, Dongfu Yin, Run Yang +3
Vision-Language-Action (VLA) policies promise general robotic manipulation, but their robustness against physical-world attacks remains fragile. In particular, we show that physica…
Beyond Pixels: Vector-to-Graph Transformation for Reliable Schematic Auditing
Chengwei Ma, Zhen Tian, Zhou Zhou +5
Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual understanding, yet they suffer from a critical limitation: structural blindness. Even state-of-the…
AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models
Zhifeng Rao, Wenlong Chen, Lei Xie +4
Vision-Language-Action (VLA) models have recently achieved remarkable progress in robotic perception and control, yet most existing approaches primarily rely on VLM trained using 2…
Intelligent Power Grid Design Review via Active Perception-Enabled Multimodal Large Language Models
Taoliang Tan, Chengwei Ma, Zhen Tian +3
The intelligent review of power grid engineering design drawings is crucial for power system safety. However, current automated systems struggle with ultra-high-resolution drawings…