研究人员提出了一种新的AI世界模型中预测的表述方式，将其视为定义未来轨迹上的概率测度，而非仅仅一步条件分布。这种路径空间方法，特别是在潜在动力学是马尔可夫的区域，将预测、规划和不确定性构建为对单一动作泛函的操作。基于注意力模型的实验表明，不可逆性可能作为预测性世界模型的计算资源，注意力不对称与数据不可逆性相关。 AI
影响 引入了理解AI世界模型中预测和规划的新理论框架，可能对这些领域的未来研究产生影响。
排序理由 学术论文，详细介绍了AI世界模型的新理论表述。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2607.02403v1 Announce Type: cross Abstract: Decision-time planning with action-conditioned world models has become a popular paradigm for embodied control. However, the standard planning cost judges a candidate solely by how close its predicted terminal state lies to the go…
arXiv:2606.13092v3 Announce Type: replace Abstract: Scale buys interpolation; structure buys certifiable transfer. A world model's average error does not say whether a particular rollout can be trusted, or for how long. For equivariant latent world models we give a predictability…
Decision-time planning with action-conditioned world models has become a popular paradigm for embodied control. However, the standard planning cost judges a candidate solely by how close its predicted terminal state lies to the goal, leaving the realizability of the intermediate …
arXiv:2606.28751v1 Announce Type: new Abstract: We propose a path-space formulation of prediction in AI world models. Rather than sequences of one-step conditional distributions, we argue that a world model implicitly defines a probability measure over future trajectories. In the…