arXiv AI June 17, 2026 By Meiliang Liu, Huiwen Dong, Xiaoxiao Yang, Yunfang Xu, Mingbao Yang, Zijin Li, Zhengye Si, Xinyue Yang, Zhiwen Zhao

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

Read the original on arXiv AI →

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.

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

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

Aug 4

Large Causal Models for Temporal Causal Discovery

arXiv:2602. 18662v2 Announce Type: replace Abstract: Causal discovery for both cross-sectional and temporal data has traditionally followed a dataset-specific paradigm, where a new model is fitted for each individual dataset.

By Nikolaos Kougioulis, Nikolaos Gkorgkolis, MingXue Wang, Bora Caglayan, Dario Simionato, Andrea Tonon, Ioannis Tsamardinos

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 Machine Learning

Jul 31

Re-examining Granger Causality with Causal Bayesian Networks and Reichenbachs Principles

arXiv:2501. 02672v4 Announce Type: replace-cross Abstract: Granger causality (GC) is widely used to infer directed relationships in time-series data.

By S. A. Adedayo

benchmarks

arXiv Machine Learning

Jul 31

Causal Discovery with Inverted Self-attention for Multivariate Time Series

arXiv:2607. 28212v1 Announce Type: cross Abstract: Causal discovery in multivariate time series data is challenging due to complex interactions, high dimensionality, and nonlinear dependencies among variables.

By Yusen Liu, Yong Wang, Yifan Yin, Tianqing Zhu, Xiufeng Liu, Huan Huo

llms efficiency benchmarks

arXiv Machine Learning

Jun 3

Your Autoregressive Model Already Reveals the Causal Graph

arXiv:2602. 01135v3 Announce Type: replace Abstract: Autoregressive models trained via next-token prediction implicitly learn the conditional independence structure of their data-generating process.

By Hugo Math, Rainer Lienhart

Related stories

From Causal Discovery to Dynamic Causal Inference in Neural Time Series

Large Causal Models for Temporal Causal Discovery

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

Re-examining Granger Causality with Causal Bayesian Networks and Reichenbachs Principles

Causal Discovery with Inverted Self-attention for Multivariate Time Series

Your Autoregressive Model Already Reveals the Causal Graph