Embodied AI TopConf · ICLR2026

TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models

ICLR2026 / Vision-Language-Action Models

VLA灵巧操作感知数据加速/部署
新标签打开 AlphaXiv
TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）