研究人员开发了一种名为域算术（Domain ARiThmetic, DART）的新方法，能够以最少的数据高效地将视觉-语言-动作（VLA）模型适应到新环境。DART利用权重向量算术和特定域信息添加，仅需一次演示即可完成适应。该方法在模拟和真实世界场景中均优于现有方法，解决了相机姿态或机器人实体变化带来的挑战。 AI
影响 该方法可以显著降低在新的机器人环境中部署VLA模型的数据需求。
排序理由 该集群包含一篇详细介绍新AI模型适应方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.00666v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models often fail to perform the same learned tasks under environmental shifts, such as changes in camera pose and shifts to a different but similar robot (e.g., from Panda to UR5e). Adapting these mod…
Vision-Language-Action (VLA) models often fail to perform the same learned tasks under environmental shifts, such as changes in camera pose and shifts to a different but similar robot (e.g., from Panda to UR5e). Adapting these models to the shifted environment (i.e., target domai…
Vision-Language-Action models can be efficiently adapted to new environments using a single demonstration through weight vector arithmetic that isolates domain-specific information via subspace alignment.