Embodied AI TopConf · ICCV2025

Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy

ICCV2025 / Vision-Language-Action Model

VLA策略学习感知
新标签打开 AlphaXiv新标签打开 Project
Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy figure
AlphaXiv 中文论文页面（可滚动查看）