研究人员推出 ODEWorld，这是一种新颖的连续时间潜在世界模型，它利用物理时间流 (PT-Flow) 来学习连续潜在速度场。这种方法由常微分方程 (ODE) 参数化，允许在压缩潜在空间中进行时间积分以进行未来预测。ODEWorld 解决了表示崩溃问题，能够实现长时域的高质量图像重建，并支持任意时间分辨率和向后预测。该模型通过平衡面向规划的动力学抽象与视觉真实感，在视频生成和机器人控制方面展现出有效性。 AI
影响 这种连续时间方法可以提高世界模型在人工智能中的效率和能力，特别是在需要长时域预测和机器人控制的任务中。
排序理由 该集群描述了一篇关于用于世界建模的新型机器学习架构的最新研究论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2607.27924v1 Announce Type: new Abstract: In the physical world we inhabit, space and time are fundamentally continuous. However, existing machine learning paradigms for world modeling are largely confined to discrete-time prediction, thereby exhibiting significant ineffici…
In the physical world we inhabit, space and time are fundamentally continuous. However, existing machine learning paradigms for world modeling are largely confined to discrete-time prediction, thereby exhibiting significant inefficiency in capturing the dynamics of physical world…
In the physical world we inhabit, space and time are fundamentally continuous. However, existing machine learning paradigms for world modeling are largely confined to discrete-time prediction, thereby exhibiting significant inefficiency in capturing the dynamics of physical world…