Embodied AI TopConf · NeuIPS2025

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

NeuIPS2025 / Vision-Language-Action Model

VLA感知
新标签打开 AlphaXiv新标签打开 Code
BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization figure
AlphaXiv 中文论文页面（可滚动查看）