Embodied AI TopConf · NeuIPS2025

CogVLA: Cognition-Aligned Vision-Language-Action Models via Instruction-Driven Routing & Sparsification

NeuIPS2025 / Vision-Language-Action Model

VLA感知
新标签打开 AlphaXiv新标签打开 Project
CogVLA: Cognition-Aligned Vision-Language-Action Models via Instruction-Driven Routing & Sparsification figure
AlphaXiv 中文论文页面（可滚动查看）