PTF Testing Lower Bounds for Non-Gaussian Component Analysis
非高斯成分分析的PTF测试下界
机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； University of California, San Diego（加州大学圣地亚哥分校）
AI总结 本文首次为非高斯成分分析等统计任务建立了非平凡的PTF测试下界，通过连接伪随机生成器工作和新技术，证明了接近最优的下界。
高校专区
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
The Geometry of Cortical Computation: Manifold Disentanglement and Predictive Dynamics in VCNet
卷积计算的几何学：VCNet中的流形解缠与预测动态
机构 * Department of Computer Science University of Wisconsin-Madison（计算机科学系 威斯康星大学麦迪逊分校） ； Department of Computer Science National University of Singapore（计算机科学系 新加坡国立大学）
AI总结 VCNet通过融合神经科学原理和几何框架，实现了更高效且鲁棒的视觉计算，展示了在图像分类任务中优于现有模型的性能。
Comments Published in the proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Symmetry and Geometry in Neural Representations (NeurReps). Additionally accepted for presentation in NeurIPS 2025 Workshop: Interpreting Cognition in Deep Learning Models (CogInterp)
Communicating Plans, Not Percepts: Scalable Multi-Agent Coordination with Embodied World Models
传达计划，而非感知：基于具身世界模型的可扩展多智能体协调
机构 * Department of Computer Science University of Wisconsin-Madison（计算机科学系 明尼苏达大学） ； Department of Computer Science National University of Singapore（计算机科学系 新加坡国立大学）
AI总结 本文提出基于具身世界模型的意图通信方法，通过端到端学习与工程化设计对比，展示在复杂环境下更优的协调能力。
Comments Published in the Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Scaling Environments for Agents (SEA). Additionally accepted for presentation in the NeurIPS 2025 Workshop: Embodied World Models for Decision Making (EWM) and the NeurIPS 2025 Workshop: Optimization for Machine Learning (OPT)
Bayesian Experimental Design for Model Discrepancy Calibration: An Auto-Differentiable Ensemble Kalman Inversion Approach
贝叶斯实验设计用于模型偏差校准：一种自动可微的集合卡尔曼反演方法
机构 * Department of Mechanical Engineering, University of Wisconsin–Madison（威斯康星大学麦迪逊分校机械工程系）
AI总结 本文提出了一种基于自动可微集合卡尔曼反演的混合贝叶斯实验设计框架，用于高效校准模型偏差并推断未知物理参数。
Comments 36 pages, 13 figures
Journal ref Journal of Computational Physics, Volume 545, 2026, Article 114469
