# 面向视觉-语言-动作模型的单次人类视频引导适应

> 原文链接：https://robotics.hellobike.com/papers/2026-10-14-2610-19746
> 频道：papers | 更新日期：2026-10-14 | 标签：arxiv, cs.RO
> 核心摘要：针对VLA难以快速适应未见操作任务，CapPro用单个人类演示视频引导预训练策略，并在源任务和未见目标任务上验证。

# 面向视觉-语言-动作模型的单次人类视频引导适应

::: v-pre
> 原文链接：[One-shot Human Video-Guided Adaptation for Vision-Language-Action Models](https://arxiv.org/abs/2610.19746)（arXiv 2610.19746 · 发布日期：2026-10-14）

**One-shot Human Video-Guided Adaptation for Vision-Language-Action Models**

针对VLA难以快速适应未见操作任务，CapPro用单个人类演示视频引导预训练策略，并在源任务和未见目标任务上验证。

## 核心要点

- VLA依赖大规模机器人数据，但对训练分布外的新操作任务快速适应能力仍有限。
- CapPro通过相位感知视频表示和视频条件适应模块，将人类视频信息注入动作条件上下文。
- 该方法无需目标任务机器人演示或目标任务微调，人类演示提供任务执行指导。
- 实验显示其提升未见目标任务组平均表现，同时在源任务上保持相近表现。

**验证范围与局限**：验证范围为源任务和未见目标任务；摘要未说明仿真或真机设置。

## 英文摘要 (Abstract)

Vision-language-action (VLA) models have recently achieved remarkable progress by leveraging large-scale robot datasets and foundation models for general-purpose robot manipulation. However, their ability to rapidly adapt to novel manipulation tasks beyond the training distribution remains limited. Existing approaches often require task-specific robot demonstrations and additional training, which are labor- and compute-intensive, limiting the scalability of VLA adaptation to open-world scenarios. To reduce this dependence on target-task robot data, we propose CapPro, a framework that enables a VLA policy to adapt to previously unseen manipulation tasks using only a single human demonstration video. CapPro consists of two components. First, a phase-aware human video representation module constructs a compact video representation through learned visual token selection and learns task-relevant query representations under phase-caption supervision. Second, a video-conditioned adaptation module jointly incorporates the compact video and query-derived representations into the action-conditioning context of the pretrained VLA policy. % This design introduces task-specific guidance while largely preserving the original VLA action-generation backbone. In this way, the human demonstration provides task-specific execution guidance rather than an embodiment-aligned trajectory to imitate, without requiring target-task robot demonstrations or target-task fine-tuning. Experiments across source and unseen target tasks show that CapPro improves average performance across unseen target groups while maintaining comparable performance on the source tasks. These results demonstrate the effectiveness of human-video guidance for cross-task VLA adaptation.

作者：Qi Alfred Chen, Yuwei Wu, Quan Chen, Kunpeng Gao, Jin Chen, Che Sun, Zhi Gao, Yunde Jia
:::

## 原始参考来源 (Sources)

- [arXiv 2610.19746：One-shot Human Video-Guided Adaptation for Vision-Language-Action Models](https://arxiv.org/abs/2610.19746)