Embodied AI TopConf · ICLR2026

Interleave-VLA: Enhancing Robot Manipulation with Image-Text Interleaved Instructions

ICLR2026 / Vision-Language-Action Models

视觉语言动作感知
新标签打开 PDF新标签打开 Paper
Interleave-VLA: Enhancing Robot Manipulation with Image-Text Interleaved Instructions figure
在线论文 PDF（可滚动查看）