https://auto-driving-blog.pages.dev/tags/-vla%E7%BB%BC%E8%BF%B0/ Recent content in 🤖 VLA综述 on Elon's AD Insight https://auto-driving-blog.pages.dev/images/share.png https://auto-driving-blog.pages.dev/images/share.png Hugo zh-cn Tue, 28 Jul 2026 00:00:00 +0000 https://auto-driving-blog.pages.dev/posts/paper-reading/vla-survey-2024/ Tue, 28 Jul 2026 00:00:00 +0000 https://auto-driving-blog.pages.dev/posts/paper-reading/vla-survey-2024/ 首篇系统性综述视觉-语言-动作（VLA）模型的文章，从组件、控制策略和任务规划三个维度全面梳理了VLA模型的技术脉络，涵盖CLIP/R3M/DINOv2等视觉表征、RT-1/RT-2/OpenVLA等控制策略、SayCan/Code as Policies等任务规划方法，并深入探讨了安全、数据集、基础模型等挑战与未来方向。