activity
20242026
collaborators

13 papers

cs.LG2026

Learning Spatio-Temporal Foundation Models from Pure Synthetic Data

Yutong Feng, Shiyuan Piao, Yutong Xia +5

Spatio-Temporal Foundation Models (STFMs) aim to learn generalizable representations of complex dynamical systems across space and time. However, existing approaches suffer from di…

cs.LG2026

Causal Time Series Generation via Diffusion Models

Yutong Xia, Chang Xu, Yuxuan Liang +4

Time series generation (TSG) synthesizes realistic sequences and has achieved remarkable success. Among TSG, conditional models generate sequences given observed covariates, howeve…

cs.LG2025

FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation

Yutong Feng, Xu Liu, Yutong Xia +1

Accurately modeling complex dynamic spatio-temporal systems requires capturing flow-mediated interdependencies and context-sensitive interaction dynamics. Existing methods, predomi…

cs.LG2025

CaPulse: Detecting Anomalies by Tuning in to the Causal Rhythms of Time Series

Yutong Xia, Yingying Zhang, Yuxuan Liang +3

Time series anomaly detection has garnered considerable attention across diverse domains. While existing methods often fail to capture the underlying mechanisms behind anomaly gene…

cs.LG2025

AirRadar: Inferring Nationwide Air Quality in China with Deep Neural Networks

Qiongyan Wang, Yutong Xia, Siru ZHong +6

Monitoring real-time air quality is essential for safeguarding public health and fostering social progress. However, the widespread deployment of air quality monitoring stations is…

cs.CL2025

Reimagining Urban Science: Scaling Causal Inference with Large Language Models

Yutong Xia, Ao Qu, Yunhan Zheng +8

Urban causal research is essential for understanding the complex, dynamic processes that shape cities and for informing evidence-based policies. However, current practices are ofte…