arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.16229cs.LG
收藏

因子化潜在动作世界模型

Factored Latent Action World Models

University of Texas at Austin(德克萨斯大学奥斯汀分校)

Zizhao Wang, Chang Shi, Jiaheng Hu, Kevin Rohling, Roberto Martín-Martín, Amy Zhang, Peter Stone

AI总结:

提出因子化潜在动作模型(FLAM),通过将场景分解为独立因子并学习各自的潜在动作,提升了无动作视频中多实体动态建模的准确性和视频生成质量。

摘要:

从无动作视频中学习潜在动作已成为扩展可控世界模型学习的强大范式。潜在动作为用户迭代生成和操作视频提供了自然接口。然而,大多数现有方法依赖整体逆动态和正动态模型,学习单一潜在动作来控制整个场景,因此在多个实体同时行动的复杂环境中表现不佳。本文引入因子化潜在动作模型(FLAM),一种因子化动态框架,将场景分解为独立因子,每个因子推断自己的潜在动作并预测自己的下一步因子值。与整体模型相比,这种因子化结构能够更准确地建模复杂多实体动态,并提高无动作视频设置中的视频生成质量。基于模拟和真实世界多实体数据集的实验,我们发现FLAM在预测准确性和表示质量方面优于先前工作,并促进了下游策略学习,展示了因子化潜在动作模型的优势。

英文摘要:

Learning latent actions from action-free video has emerged as a powerful paradigm for scaling up controllable world model learning. Latent actions provide a natural interface for users to iteratively generate and manipulate videos. However, most existing approaches rely on monolithic inverse and forward dynamics models that learn a single latent action to control the entire scene, and therefore struggle in complex environments where multiple entities act simultaneously. This paper introduces Factored Latent Action Model (FLAM), a factored dynamics framework that decomposes the scene into independent factors, each inferring its own latent action and predicting its own next-step factor value. This factorized structure enables more accurate modeling of complex multi-entity dynamics and improves video generation quality in action-free video settings compared to monolithic models. Based on experiments on both simulation and real-world multi-entity datasets, we find that FLAM outperforms prior work in prediction accuracy and representation quality, and facilitates downstream policy learning, demonstrating the benefits of factorized latent action models.

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。

↑