研究人员引入了一个名为任务无关预训练（TAP）的新框架，旨在克服视觉-语言-动作（VLA）模型中的数据稀缺瓶颈。TAP采用两阶段方法：首先，它利用无标签交互数据通过自监督逆动力学目标学习可迁移的运动技能，然后用最少的专家语言数据来巩固这些技能。这种方法显著减少了对昂贵专家演示的需求，在标记数据量少几个数量级的情况下，达到了与在数百万专家轨迹上训练的模型相当的性能。 AI
影响 通过减少对昂贵、专家标记数据的依赖，这种方法可以显著加速具身AI系统的开发和部署。
排序理由 该集群包含一篇详细介绍新研究框架和方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.02466v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are fundamentally bottlenecked by the scarcity of expert demonstrations -- triplets of observations, instructions, and actions that are costly to collect at scale. We argue that this bottleneck …
Vision-Language-Action (VLA) models are fundamentally bottlenecked by the scarcity of expert demonstrations -- triplets of observations, instructions, and actions that are costly to collect at scale. We argue that this bottleneck stems from conflating two distinct learning object…
Task-Agnostic Pretraining framework trains robotic models using self-supervised inverse dynamics on unlabeled data followed by lightweight language grounding, achieving superior performance with minimal expert demonstrations.