Embodied AI TopConf · ICCV2025

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers

ICCV2025 / Vision-Language-Action Model

VLA感知加速/部署
新标签打开 AlphaXiv新标签打开 Project
VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers figure
AlphaXiv 中文论文页面（可滚动查看）