1
AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models
用持久世界-自我状态建模破解VLA泛化难题，让机器人更懂环境与自身轨迹
arXiv:2608.06729v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models have advanced embodied AI, their fundamentally reactive pa…