Embodied AI TopConf · ICLR2026

WMPO: World Model-based Policy Optimization for Vision-Language-Action Models

ICLR2026 / World Models

视觉语言动作世界模型策略学习感知
新标签打开 AlphaXiv
WMPO: World Model-based Policy Optimization for Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）