人形世界模型：面向人形机器人的开放世界基础模型
Humanoid World Models: Open World Foundation Models for Humanoid Robotics
AI总结：
本文提出人形世界模型（HWM），一种轻量级开源模型，基于控制令牌预测自我中心视频，在100小时演示上训练掩码Transformer和流匹配，通过参数共享减少33-53%模型大小，适用于1-2 GPU的学术环境。
摘要：
人形机器人凭借其类人形态，特别适合在为人设计的环境中交互。然而，使人形机器人能够在复杂的开放世界环境中进行推理、规划和行动仍然是一个挑战。世界模型，即预测给定行动未来结果的模型，可以通过在长时程规划中充当动力学模型以及为策略学习生成合成数据来支持这些能力。我们引入了人形世界模型（HWM），这是一系列轻量级、开源模型，能够根据人形控制令牌预测未来的自我中心视频。我们在100小时的人形演示数据上训练了两种类型的生成模型：掩码Transformer和流匹配。此外，我们探索了具有不同注意力机制和参数共享策略的架构变体。我们的参数共享技术将模型大小减少了33%至53%，同时对性能或视觉保真度的影响极小。HWM旨在能够在实际的学术和小型实验室环境中进行训练和部署，例如使用1至2个GPU。
英文摘要：
Humanoid robots, with their human-like form, are uniquely suited for interacting in environments built for people. However, enabling humanoids to reason, plan, and act in complex open-world settings remains a challenge. World models, models that predict the future outcome of a given action, can support these capabilities by serving as a dynamics model in long-horizon planning and generating synthetic data for policy learning. We introduce Humanoid World Models (HWM), a family of lightweight, open-source models that forecast future egocentric video conditioned on humanoid control tokens. We train two types of generative models, Masked Transformers and Flow-Matching, on 100 hours of humanoid demonstrations. Additionally, we explore architectural variants with different attention mechanisms and parameter-sharing strategies. Our parameter-sharing techniques reduce model size by 33-53% with minimal impact on performance or visual fidelity. HWMs are designed to be trained and deployed in practical academic and small-lab settings, such as 1-2 GPUs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
