5 papers
FailureSpot: Label-Efficient Timestamp-Level Failure Detection for Vision-Language-Action Models
Jie Ma, Zongxi Liu, Yi Zhu
Vision-language-action (VLA) policies have shown strong potential for general-purpose robotic manipulation, but they can still fail unpredictably during long-horizon execution, mak…
FailSAE: Towards Interpretable Failure Prediction for Vision-Language Models via Sparse Autoencoders
Jie Ma, Zongxi Liu, Yi Zhu
Vision-language models (VLMs), such as CLIP, have achieved strong performance across multimodal tasks by aligning visual and textual representations in a shared embedding space. As…
Send Less, Perceive More: Masked Quantized Point Cloud Communication for Loss-Tolerant Collaborative Perception
Sheng Xu, Enshu Wang, Hongfei Xue +6
Collaborative perception allows connected vehicles to overcome occlusions and limited viewpoints by sharing sensory information. However, existing approaches struggle to achieve hi…
Asymmetry Vulnerability and Physical Attacks on Online Map Construction for Autonomous Driving
Yang Lou, Haibo Hu, Qun Song +5
High-definition maps provide precise environmental information essential for prediction and planning in autonomous driving systems. Due to the high cost of labeling and maintenance…
A First Physical-World Trajectory Prediction Attack via LiDAR-induced Deceptions in Autonomous Driving
Yang Lou, Yi Zhu, Qun Song +4
Trajectory prediction forecasts nearby agents' moves based on their historical trajectories. Accurate trajectory prediction is crucial for autonomous vehicles. Existing attacks com…