Coarse-to-Fine Learning of Dynamic Causal Structures
School of Software（软件学院）；Shandong University（山东大学）；Department of Computer Science（计算机科学系）；New York University（纽约大学）；George Mason University（乔治·马歇尔大学）；Shandong Institutes of Industrial Technology（山东省工业技术研究院）
Dezhi Yang, Qiaoyu Tan, Carlotta Domeniconi, Jun Wang, Lizhen Cui, Guoxian Yu
Learning the dynamic causal structure of time series is a challenging problem. Most existing approaches rely on distributional or structural invariance to uncover underlying causal dynamics, assuming stationary or partially stationary causality. However, these assumptions often conflict with the complex, time-varying causal relationships observed in real-world systems. This motivates the need for methods that address fully dynamic causality, where both instantaneous and lagged dependencies evolve over time. Such a setting poses significant challenges for the efficiency and stability of causal discovery. To address these challenges, we introduce DyCausal, a dynamic causal structure learning framework. DyCausal leverages convolutional networks to capture causal patterns within coarse-grained time windows, and then applies linear interpolation to refine causal structures at each time step, thereby recovering fine-grained and time-varying causal graphs. In addition, we propose an acyclic constraint based on matrix norm scaling, which improves efficiency while effectively constraining loops in evolving causal structures. Comprehensive evaluations on both synthetic and real-world datasets demonstrate that DyCausal achieves superior performance compared to existing methods, offering a stable and efficient approach for identifying fully dynamic causal structures from coarse to fine.
Causal Data Augmentation for Robust Fine-Tuning of Tabular Foundation Models
Department of Computer Science University of Freiburg（计算机科学系弗赖堡大学）；University of Freiburg（弗赖堡大学）；Prior Labs ELLIS Institute Tübingen University of Freiburg（Prior实验室ELLIS研究所弗赖堡大学）
Department of Technology, Management and Economics, Danish Technical University（丹麦技术大学技术、管理与经济学系）；Department of Mathematics and Statistics, Binghamton University, State University of New York（纽约州立大学宾汉姆顿分校数学与统计系）；Department of Mathematical Sciences, University of Copenhagen（哥本哈根大学数学科学系）
Coarsening Linear Non-Gaussian Causal Models with Cycles
Department of Technology, Management and Economics, Technical University of Denmark（技术、管理与经济系，丹麦技术大学）；Department of Mathematical Sciences, University of Copenhagen（数学科学系，哥本哈根大学）
Causal Discovery with Fewer Conditional Independence Tests
Eric and Wendy Schmidt Center, Broad Institute（埃里克和温迪·施密特中心，布罗德研究所）；Laboratory for Information & Decision Systems, Massachusetts Institute of Technology（麻省理工学院信息与决策系统实验室）
从粗到细的Q-注意力通过以从粗到细的方式离散化平移空间来实现样本高效的机器人操作，其中分辨率在层次结构中的每一层逐渐增加。虽然有效，但Q-attention遭受“粗糙的模糊性”-当体素化非常粗糙时，如果不首先以更精细的分辨率进行检查，就无法区分外观相似的对象。为了解决这个问题，我们建议将Q-attention设想为一棵树，它可以扩展并用于在每个Q-attention深度处累积前k个体素的值估计。当我们的扩展，Q-attention with Tree Expansion（QTE），在注意力驱动的机器人操作（ARM）系统中取代标准的Q-attention时，我们能够完成更大的任务集;特别是那些遭受“粗糙模糊”的任务。除了在12个RLBench任务中评估我们的方法外，我们还表明，在涉及小对象的现实任务中，性能的提高是显而易见的。
PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds
CORIS Institute, Oregon State University（俄勒冈州立大学CORIS研究所）；Nuro, Inc.（Nuro公司）
我们提出了一种新的端到端的深度场景流模型，称为PointPWC-Net，在3D点云上以粗到细的方式。在粗略级别计算的流被上采样并扭曲到更精细的级别，使得该算法能够适应大的运动而没有禁止的搜索空间。我们引入了新的成本体积，上采样和扭曲层，以有效地处理3D点云数据。与传统的成本卷需要在高维网格上穷尽计算所有成本值不同，我们的基于点的公式将成本卷离散化到输入3D点上，PointConv操作有效地计算成本卷上的卷积。在FlyingThings 3D上的实验结果大大优于现有技术。我们进一步探索了新的自我监督损失来训练我们的模型，并取得了与最先进的监督损失训练相当的结果。在没有任何微调的情况下，我们的方法在KITTI Scene Flow 2015数据集上也表现出了很好的泛化能力，优于所有以前的方法。
Fine-grained Population Mapping from Coarse Census Counts and Open Geodata
ETH Zurich（苏黎世联邦理工学院）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；Yale University（耶鲁大学）；International Committee of the Red Cross（红十字国际委员会）；Hamad Bin Khalifa University（哈马德·本·哈利法大学）
Combining Fine- and Coarse-Grained Classifiers for Diabetic Retinopathy Detection
Technische Universität Kaiserslautern（凯泽斯劳滕工业大学）；German Research Center for Artificial Intelligence GmbH (DFKI)（德国人工智能研究中心（DFKI））；Osaka Prefecture University（大阪府立大学）；National University of Science and Technology (NUST)（国立科技大学（NUST））；Opthalmology Clinic（眼科诊所）
