Embodied AI TopConf · NeuIPS2025

ChatVLA-2: Vision-Language-Action Model with Open-World Reasoning

NeuIPS2025 / Vision-Language-Action Model

视觉语言动作规划/推理感知
新标签打开 AlphaXiv新标签打开 Project
ChatVLA-2: Vision-Language-Action Model with Open-World Reasoning figure
AlphaXiv 中文论文页面（可滚动查看）