ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving
ExploreVLA: 为端到端自动驾驶的密集世界建模与探索
机构 * University of Wisconsin–Madison(威斯康星大学麦迪逊分校)
AI总结 本文提出基于世界建模的统一理解与生成框架,通过密集监督和内在奖励提升自动驾驶策略探索能力,在NAVSIM和nuScenes基准上取得优异性能。
Comments Accepted to ECCV 2026. The code is available at https://zihaosheng.github.io/ExploreVLA/