论文/arXiv 2610.20019·14 天前

MorphAct：随其作用世界变化而变形的机器人策略

MorphAct通过上下文低秩参数生成动态调整机器人策略，并在LIBERO、Meta-World和真实评估中验证性能提升。

AI 整理

• 具身模型
• 评测与安全

原文链接：MorphAct: Robot Policies Morphing with the Worlds They Act In（arXiv 2610.20019 · 发布日期：2026-10-14）

MorphAct: Robot Policies Morphing with the Worlds They Act In

MorphAct通过上下文低秩参数生成动态调整机器人策略，并在LIBERO、Meta-World和真实评估中验证性能提升。

核心要点

• 现有机器人策略在不同交互情境中参数固定，混合拟合会使单项操作适应不足。
• MorphAct用两个耦合生成器，为视觉语言和动作模块生成上下文相关低秩更新。
• 生成器按策略计算依赖耦合，并通过原生动作目标联合训练，无需操作标签或专家适配器目标。
• 在三个VLA骨干、LIBERO和Meta-World上最高提升16.30%，真实评估较π_{0.5}最高提升14%。

验证范围与局限：验证范围包括LIBERO、Meta-World和真实世界评估，摘要未说明具体任务或机器数量。

英文摘要 (Abstract)

Progress toward general intelligence in the physical world requires scaling robot learning across diverse environments and interactions. However, existing robot policies use shared parameters that remain fixed across interaction contexts. When different operations favor competing parameter adjustments, fitting their mixture can leave individual operations insufficiently adapted. Our atomic-task diagnostics reveal competing update directions in both vision-language and action parameters, with source-improving updates increasing loss on other tasks. This motivates MorphAct, a contextual parameterization framework that dynamically adjusts robot policy parameters as interaction contexts change. Two coupled generators produce context-dependent low-rank updates for the vision-language and action modules. Their coupling follows the policy's computational dependency: vision-language updates shape the representations that condition action-side parameter generation. Both generators are trained jointly through the native action objective, without operation labels or expert-adapter targets. MorphAct improves performance across three VLA backbones on LIBERO and Meta-World, with gains of up to 16.30%. In real-world evaluation, it achieves gains of up to 14% over $π_{0.5}$. Ablations support the benefits of contextual parameter generation and representation coupling.

作者：Ziyan Liu, Jiting Liu, Weihong Zhong, Wenda Yu, Yeqiu Chen, Jason Li, Xiaojiang Peng, Shuyuan Hu, Kai Wang, Bo Zhao

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.20019：MorphAct: Robot Policies Morphing with the Worlds They Act In访问 2026-10-21