AI RESEARCH
GEM: Generating LiDAR World Model via Deformable Mamba
arXiv CS.CV
•
ArXi:2605.07326v1 Announce Type: new World models, which simulate environmental dynamics and generate sensor observations, are gaining increasing attention in autonomous driving. However, progress in LiDAR-based world models has lagged behind those built on camera videos or occupancy data, primarily due to two core challenges: the inherent disorder of LiDAR point clouds and the difficulty of distinguishing dynamic objects from static structures.