Embodied AI TopConf · NeuIPS2025

BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models

NeuIPS2025 / Vision-Language-Action Model

VLA3D 视觉感知加速/部署
新标签打开 AlphaXiv新标签打开 Project
BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models figure
AlphaXiv 中文论文页面（可滚动查看）