11 papers
DeeAD: Dynamic Early Exit of Vision-Language Action for Efficient Autonomous Driving
Haibo HU, Lianming Huang, Nan Guan +1
Vision-Language Action (VLA) models unify perception, reasoning, and trajectory generation for autonomous driving, but suffer from significant inference latency due to deep transfo…
On-Demand Multi-Task Sparsity for Efficient Large-Model Deployment on Edge Devices
Lianming Huang, Haibo Hu, Qiao Li +2
Sparsity is essential for deploying large models on resource constrained edge platforms. However, optimizing sparsity patterns for individual tasks in isolation ignores the signifi…
MMRHP: A Miniature Mixed-Reality HIL Platform for Auditable Closed-Loop Evaluation
Mingxin Li, Haibo Hu, Jinghuai Deng +3
Validation of autonomous driving systems requires a trade-off between test fidelity, cost, and scalability. While miniaturized hardware-in-the-loop (HIL) platforms have emerged as…
Nav-EE: Navigation-Guided Early Exiting for Efficient Vision-Language Models in Autonomous Driving
Haibo Hu, Lianming Huang, Xinyu Wang +4
Vision-Language Models (VLMs) are increasingly applied in autonomous driving for unified perception and reasoning, but high inference latency hinders real-time deployment. Early-ex…
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…
GM-Skip: Metric-Guided Transformer Block Skipping for Efficient Vision-Language Models
Lianming Huang, Haibo Hu, Qiao Li +3
Transformer-based Vision-Language Models (VLMs) have achieved impressive performance on tasks such as image captioning, object recognition, and visual reasoning, but their high com…