发现并修复世界模型中的物理守恒量，显著提升预测准确性。
Correcting a learned physical invariant improves world-model rollouts
- 从像素中自动发现隐变量的守恒量，无需标签
- 修复守恒量后，三组保守模型滚动预测误差下降
- 适合研究世界模型与物理规律一致性的人看
世界模型可在不显式学习动力学的情况下可靠预测视频。我们测试了仅在单摆视频上训练的冻结版DreamerV3是否学会了一个其隐状态转移视为近似守恒的标量。无标签搜索在独立训练的保守模型中均恢复出相同的类能量守恒量，而在匹配的阻尼模型中未发现类似量。自主滚动预测中，该量出现漂移。将隐状态投影回初始值集可降低所有三组保守模型的预测误差，而随机约束通常会增加误差。结果区分了动态有意义的守恒量与仅可解码的关联量，并揭示了一个具体缺陷：世界模型可能从像素中学会物理约束，但在想象未来时却违背该约束。
原文摘要 · Abstract (English)
World models can predict video without learning dynamics that they reliably preserve. We test whether a frozen DreamerV3 trained only on pendulum video learns a scalar that its own latent transition treats as approximately conserved. A label-free search recovers the same energy-like invariant across independently trained conservative models, while the same procedure finds no comparable invariant in matched damped models. During autonomous rollouts, this quantity drifts. Projecting the latent state back toward its initial level set reduces rollout error in all three conservative models, whereas matched random constraints usually increase it. These results distinguish a dynamically meaningful invariant from a merely decodable correlate and reveal a concrete failure mode: a world model can learn a physical constraint from pixels yet violate that constraint when it imagines forward.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。