Embodied AI TopConf · ICLR2026

On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations

ICLR2026 / Vision-Language-Action Models

视觉语言动作感知
新标签打开 AlphaXiv
On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations figure
AlphaXiv 中文论文页面（可滚动查看）