Spatio-temporal fluid dynamics modeling via physical-awareness and parameter diffusion guidance

H Wu, F Xu, Y Duan, Z Niu, W Wang, G Lu… - arxiv preprint arxiv …, 2024 - arxiv.org
This paper proposes a two-stage framework named ST-PAD for spatio-temporal fluid
dynamics modeling in the field of earth sciences, aiming to achieve high-precision …

Get Rid of Task Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework

Z Yi, Z Zhou, Q Huang, Y Chen, L Yu, X Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Spatiotemporal learning has become a pivotal technique to enable urban intelligence.
Traditional spatiotemporal models mostly focus on a specific task by assuming a same …

Enhancing Traffic Flow Forecasting With Delay Propagation: Adaptive Graph Convolution Networks for Spatio-Temporal Data

Z Yingran, L Chao, S Rui - IEEE Transactions on Intelligent …, 2024 - ieeexplore.ieee.org
Traffic flow Forecasting is essential in intelligent transportation systems. Although graph
neural networks perform well with non-Euclidean traffic data, they exhibit limits in accurately …

Pattern-oriented Attention Mechanism for Multivariate Time Series Forecasting

H Hu, Z Han, S Qian, D Yang, J Cao… - ACM Transactions on …, 2025 - dl.acm.org
Multivariate time series forecasting is applied in many domains, such as finance,
transportation and industry. The main challenge of precise forecasting lies in accurately …

Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework

Z Yi, Z Zhou, Q Huang, Y Chen, L Yu… - The Thirty-eighth …, 2024 - openreview.net
Spatiotemporal learning has become a pivotal technique to enable urban intelligence.
Traditional spatiotemporal models mostly focus on a specific task by assuming a same …

Improving Generalization of Dynamic Graph Learning via Environment Prompt

K Yang, Z Zhou, Q Huang, L Li, Y Liang… - The Thirty-eighth Annual … - openreview.net
Out-of-distribution (OOD) generalization issue is a well-known challenge within deep
learning tasks. In dynamic graphs, the change of temporal environments is regarded as the …

P-Align: Self-Alignment in Physical Dynamical System Modeling

Z Xu, F Xu, H Wang, X ZHOU, L Peng, Q Wen, K Wang… - openreview.net
Deep learning has emerged as the new paradigm in modeling complex physical dynamical
systems. Nevertheless, data-driven methods learn patterns by optimizing statistical metrics …