Embodied AI TopConf · ICLR2026

Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Diffusion Diffusion Process

ICLR2026 / Vision-Language-Action Models

VLA策略学习感知
新标签打开 AlphaXiv
Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Diffusion Diffusion Process figure
AlphaXiv 中文论文页面（可滚动查看）