arXiv Machine Learning August 19, 2026 By Jonas Braun, Fabian Fischbach, Daniel K\"oglmayr, Sebastian Baur, Christoph R\"ath

Causal Local States: Scalable Simultaneous Causal Network Inference and Forecasting for Dynamical Systems

Read the original on arXiv Machine Learning →

arXiv:2608. 17452v1 Announce Type: new Abstract: Machine learning methods predict many real-world systems with remarkable accuracy, but they are typically treated as black boxes that offer no insight into which interactions drive the dynamics.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

benchmarks

arXiv AI

Jun 12

CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts

arXiv:2606. 13024v1 Announce Type: cross Abstract: Granger Causal Discovery (GCD) is fundamental for analyzing temporal dependencies in complex systems.

By Bo Liu, Di Dai, Jingwei Liu, Jiarui Jin, Xiaocheng Fang, Guangkun Nie, Hongyan Li, Shenda Hong

llms multimodal benchmarks

arXiv AI

Jun 17

A Gradient-based Causal Discovery Framework with Applications to Complex Industrial Processes

arXiv:2507. 11178v3 Announce Type: replace-cross Abstract: With the advancement of deep learning technologies, various neural network-based Granger causality models have been proposed.

By Meiliang Liu, Huiwen Dong, Xiaoxiao Yang, Yunfang Xu, Mingbao Yang, Zijin Li, Zhengye Si, Xinyue Yang, Zhiwen Zhao

efficiency

arXiv Machine Learning

Jun 5

From Causal Discovery to Dynamic Causal Inference in Neural Time Series

arXiv:2603. 20980v3 Announce Type: replace Abstract: Time-varying causal models provide a powerful framework for studying dynamic scientific systems, yet most existing approaches assume that the underlying causal network is known a priori - an assumption rarely satisfied in real-world domains where causal structure is uncertain, evolving, or only indirectly observable.

By Dmitry Zaytsev, Valentina Kuskova, Michael Coppedge

arXiv Machine Learning

Jul 14

DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms

arXiv:2607. 11510v1 Announce Type: new Abstract: Causal discovery from observational tabular data remains fundamentally challenging, primarily due to the heterogeneity of underlying causal mechanisms and the high-dimensional combinatorial search space of Directed Acyclic Graphs (DAGs).

By Yikang Chen, Zhengkang Guan, Haoyuan Qian, Peng Cui, Yi Yang, Kun Kuang

llms benchmarks

arXiv Machine Learning

Jun 10

Interpretable deep convolutional model for nonlinear multivariate time series in complex systems

arXiv:2501. 04339v2 Announce Type: replace-cross Abstract: We introduce the Deep Convolutional Interpreter for Time Series (DCIts), a deep-learning architecture for nonlinear multivariate time series that provides sample-specific, locally interpretable descriptions of the underlying interaction structure.

By Domjan Baric, Davor Horvatic

benchmarks safety

arXiv Machine Learning

Jul 7

Knowledge-Informed Local Causal Discovery of Optimal Adjustment Sets

arXiv:2607. 04447v1 Announce Type: new Abstract: Local causal discovery is a scalable alternative to global structure learning.

By Seong Woo Ahn, Alessandro Leite, Jos\'e Lucas De Melo Costa, Fabrice Popineau, Bich-Li\^en Doan, Arpad Rimmel

Related stories

CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts

A Gradient-based Causal Discovery Framework with Applications to Complex Industrial Processes

From Causal Discovery to Dynamic Causal Inference in Neural Time Series

DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms

Interpretable deep convolutional model for nonlinear multivariate time series in complex systems

Knowledge-Informed Local Causal Discovery of Optimal Adjustment Sets