Embodied AI TopConf · ICLR2026

PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model

ICLR2026 / Vision-Language-Action Models

VLA感知
新标签打开 AlphaXiv
PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model figure
AlphaXiv 中文论文页面（可滚动查看）