2 papers
cs.RO2026
CogAD: Cognitive-Hierarchy Guided End-to-End Autonomous Driving
Zhennan Wang, Jianing Teng, Canqun Xiang +4
While end-to-end autonomous driving has advanced significantly, prevailing methods remain fundamentally misaligned with human cognitive principles in both perception and planning.…
cs.CV2026
IBCapsNet: Information Bottleneck Capsule Network for Noise-Robust Representation Learning
Canqun Xiang, Chen Yang, Jiaoyan Zhao
Capsule networks (CapsNets) are superior at modeling hierarchical spatial relationships but suffer from two critical limitations: high computational cost due to iterative dynamic r…