With the rapid advancements of sensor technology and deep learning, autonomous driving
systems are providing safe and efficient access to intelligent vehicles as well as intelligent …

Image modality is not perfect as it often fails in certain conditions, eg, night and fast motion.
This significantly limits the robustness and versatility of existing multi-modal (ie, Image+ X) …

Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen
driving scenarios, largely stemming from the non-interpretability and poor generalization of …

Fusing an arbitrary number of modalities is vital for achieving robust multi-modal fusion of
semantic segmentation yet remains less explored to date. Recent endeavors regard RGB …

Learning unsupervised world models for autonomous driving has the potential to improve
the reasoning capabilities of today's systems dramatically. However, most work neglects the …

Abstract Large Language Models (LLMs) have shown significant promise in decisionmaking
tasks when fine-tuned on specific applications, leveraging their inherent common sense and …

Complex 3D scene understanding has gained increasing attention, with scene encoding
strategies playing a crucial role in this success. However, the optimal scene encoding …

Low-cost, vision-centric 3D perception systems for autonomous driving have made
significant progress in recent years, narrowing the gap to expensive LiDAR-based methods …

Bird's-eye-view (BEV) representation is crucial for the perception function in autonomous
driving tasks. It is difficult to balance the accuracy, efficiency and range of BEV …

Multi-view counting (MVC) methods have shown their superiority over single-view
counterparts, particularly in situations characterized by heavy occlusion and severe …