Multi-Horizon Consistency as Geometry: When Latent Dynamics Contract, and When They Do Not
多时间尺度一致性即几何:潜在动力学何时收缩,何时不收缩
机构 * Vishwakarma Institute of Technology(维斯瓦卡玛理工学院)
专题命中 模型式强化学习 :latent dynamics(title);world model(abstract);world models(abstract);world model(abstract)
AI总结 研究视频预测器和世界模型中多时间尺度潜在一致性权重λ对过渡几何的作用,通过实验测量L20,q95和E20等指标,发现λ能改善移动MNIST数据集相关指标,且软一致性作用有域限制,还得出随机强迫定律统一控制域。
Comments 22 pages, 9 figures. Diagnostic study of multi-horizon latent consistency, expansion proxies (L20), and a stochastic-forcing law for world-model geometry. Code and experiment logs to be released publicly