Temporal causal representation learning methods assume that causal mechanisms switch instantaneously between discrete domains, yet real-world systems often exhibit continuous mechanism transitions. For example, a vehicle's dynamics evolve gradually through a turning maneuver, and human gait shifts smoothly from walking to running. We formalize this setting by modeling transitional mechanisms as convex combinations of finitely many atomic mechanisms, governed by time-varying mixing coefficients. Our theoretical contributions establish that both the latent causal variables and the continuous mixing trajectory are jointly identifiable. We further propose TRACE, a Mixture-of-Experts framework where each expert learns one atomic mechanism during training, enabling recovery of mechanism trajectories at test time. This formulation generalizes to intermediate mechanism states never observed during training. Experiments on synthetic and real-world data demonstrate that TRACE recovers mixing trajectories with up to 0.99 correlation, substantially outperforming discrete-switching baselines.
Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning
Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Science and Technology of China（中国科学技术大学）；Beijing Institute of Technology（北京理工大学）
LightTR: A Lightweight Framework for Federated Trajectory Recovery
University of Electronic Science and Technology of China（电子科技大学）；Aalborg University（奥尔堡大学）；Nanyang Technological University（南洋理工大学）；Zhejiang University（浙江大学）
Micro-Macro Spatial-Temporal Graph-based Encoder-Decoder for Map-Constrained Trajectory Recovery
School of Computer and Information Technology, Beijing Jiaotong University（北京交通大学计算机与信息技术学院）；Beijing Key Laboratory of Traffic Data Analysis and Mining（北京市交通数据分析与挖掘重点实验室）
PLMTrajRec: A Scalable and Generalizable Trajectory Recovery Method with Pre-trained Language Models
School of Computer and Information Technology, Beijing Jiaotong University（北京交通大学计算机与信息技术学院）；School of Data Science and Engineering, East China Normal University（华东师范大学数据科学与工程学院）；Nanyang Technological University（南洋理工大学）
CausalTAD: Causal Implicit Generative Model for Debiased Online Trajectory Anomaly Detection
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；DiDi Global Inc.（滴滴全球公司）
Learning Spatio-Temporal Dynamics for Trajectory Recovery via Time-Aware Transformer
School of Computer Science, Fudan University（复旦大学计算机科学学院）；Shanghai Key Laboratory of Data Science, Fudan University（复旦大学数据科学重点实验室）；Shanghai Institute of Intelligent Electronics & Systems（上海智能电子与系统研究所）；School of Computing and Information Systems, Singapore Management University（新加坡国立大学计算与信息系统学院）
Stability of Linear Structural Equation Models of Causal Inference
University of Maryland, College Park（马里兰大学帕克分校）；Indian Institute of Science, Bangalore（印度科学理工学院班加罗尔分校）；Microsoft Research, India（微软印度研究院）
研究了因果推理的线性结构方程模型（$\LSEM$）中参数恢复问题的数值稳定性。从Wright（1920）开始的一长串工作集中于理解$\LSEM$的哪些子类允许有效的参数恢复。尽管经过了几十年的研究，这个问题仍未完全解决。本文的目标是补充这条线的工作，我们想了解的情况下，有效的恢复是可能的恢复问题的稳定性。Pearl因果关系概念的数值稳定性首先在Schulman和Srivastava（2016）中使用条件数的概念进行了研究，其中他们提供了病态的例子。在这项工作中，我们为$\LSEM$提供了条件数分析。首先证明了在一个充分条件下，对于$\LSEM$的某个子类\emph{bow-free}（Brito and Pearl（2002）），参数恢复是稳定的.我们进一步证明，\emph{randomly}选择的输入参数为这个家庭满足的条件，具有很大的概率。因此，对于这个家庭，在参数空间的一个大的子集，恢复是数值稳定的。接下来，我们构造一个例子$\LSEM$的四个顶点与\emph{unbounded}条件数。然后，我们通过模拟以及现实世界的实验社会学应用证实了我们的理论研究结果。最后，我们提供了一个通用的启发式估计任何$\LSEM$实例的条件数。
Efficient Methods for Accurate Sparse Trajectory Recovery and Map Matching
Department of Computing Hong Kong Polytechnic University（计算学系香港理工大学）；Department of Computing Smart Cities Research Institute Hong Kong Polytechnic University（计算学系智慧城市研究院香港理工大学）
VisionTraj: A Noise-Robust Trajectory Recovery Framework based on Large-scale Camera Network
SenseTime Research（商汤科技研究院）；University of Cologne（科隆大学）；China Telecom Cloud Technology Co., Ltd（中国电信云技术有限公司）；Shanghai AI Lab（上海人工智能实验室）；Qing Yuan Research Institute（清源研究院）
Relaxed Sparsest-Permutation Formulation for Causal Discovery at Scale
Department of Statistics（统计学系）；Seoul National University（首尔国立大学）；Department of Statistics and Applied Probability（统计学与应用概率系）；University of California Santa Barbara（加州大学圣芭芭拉分校）；Scientific Data Division（科学数据部）；Lawrence Berkeley National Laboratory（伯克利国家实验室）；Interdisciplinary Program in Artificial Intelligence（人工智能跨学科项目）；Institute for Data Innovation in Science（科学数据创新研究所）
Causal Graph Recovery in Neuroimaging through Answer Set Programming
Georgia Institute of Technology（佐治亚理工学院）；Georgia State University（佐治亚州立大学）；Center for Translational Research in Neuroimaging and Data Science (TReNDS)（神经影像与数据科学转化研究中心）；University of California San Diego（加州大学圣地亚哥分校）
Causal Discovery from Heteroscedastic Stochastic Dynamical Systems under Imperfect Physical Models
Department of Mechanical & Industrial Engineering（机械与工业工程系）；Northeastern University（东北大学）；Department of Industrial Engineering and Management Sciences（工业工程与管理科学系）；Department of Mechanical Engineering（机械工程系）；Northwestern University（西北大学）
Learning Neural Causal Models from Unknown Interventions
Mila, Université de Montréal（蒙特利尔大学 Mila 研究院）；Mila, Polytechnique Montréal（蒙特利尔理工学院 Mila 研究院）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Google AI（谷歌人工智能）；Element AI
