Embodied AI TopConf · ICLR2026

OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning

ICLR2026 / Vision-Language-Action Models

VLA规划/推理感知
新标签打开 AlphaXiv
OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning figure
AlphaXiv 中文论文页面（可滚动查看）