世界引导：基于条件空间的世界建模与动作生成

摘要

利用未来观测建模来促进动作生成，为提升视觉-语言-动作（VLA）模型能力提供了新思路。然而现有方法难以在保持高效、可预测的未来表征与保留足够细粒度信息以指导精确动作生成之间实现平衡。为此，我们提出世界引导框架（WoG），通过将未来观测映射为紧凑条件并注入动作推理流程，使VLA模型在预测未来动作的同时学习预测这些压缩条件，从而在条件空间内实现高效的世界建模用于动作推理。我们证明，对此条件空间的建模与预测不仅能促进细粒度动作生成，还展现出卓越的泛化能力，且能有效从大规模人类操作视频中学习。在仿真与现实环境中的大量实验表明，本方法显著优于基于未来预测的现有方法。项目页面详见：https://selen-suyue.github.io/WoGNet/

English

Leveraging future observation modeling to facilitate action generation presents a promising avenue for enhancing the capabilities of Vision-Language-Action (VLA) models. However, existing approaches struggle to strike a balance between maintaining efficient, predictable future representations and preserving sufficient fine-grained information to guide precise action generation. To address this limitation, we propose WoG (World Guidance), a framework that maps future observations into compact conditions by injecting them into the action inference pipeline. The VLA is then trained to simultaneously predict these compressed conditions alongside future actions, thereby achieving effective world modeling within the condition space for action inference. We demonstrate that modeling and predicting this condition space not only facilitates fine-grained action generation but also exhibits superior generalization capabilities. Moreover, it learns effectively from substantial human manipulation videos. Extensive experiments across both simulation and real-world environments validate that our method significantly outperforms existing methods based on future prediction. Project page is available at: https://selen-suyue.github.io/WoGNet/

世界引导：基于条件空间的世界建模与动作生成

World Guidance: World Modeling in Condition Space for Action Generation

摘要

Support