Complex networks pervade various real-world systems, from the natural environment to
human societies. The essence of these networks is in their ability to transition and evolve …

Accurate understanding and prediction of human behaviors are critical prerequisites for
autonomous vehicles, especially in highly dynamic and interactive scenarios such as …

Effective interaction modeling and behavior prediction of dynamic agents play a significant
role in interactive motion planning for autonomous robots. Although existing methods have …

Recent graph-based methods achieve significant success in multivariate time series
modeling and forecasting due to their ability to handle relationships among time series …

Dynamical systems with interacting agents are universal in nature, commonly modeled by a
graph of relationships between their constituents. Recently, various works have been …

Forecasting vehicular motions in autonomous driving requires a deep understanding of
agent interactions and the preservation of motion equivariance under Euclidean geometric …

Maintaining temporal stability is crucial in multi-agent trajectory prediction. Insufficient
regularization to uphold this temporal stability often results in fluctuations in kinematic states …

Graph neural networks (GNNs) have proven to be effective tools for the rapid and accurate
prediction of crystal properties. While most existing methods focus on enriching …

Improving the performance of flocking control policies in practical scenarios is of great value
in promoting the practical application of multiagent flocking collaborative control algorithms …

Multi-agent systems often face challenges such as elevated communication demands,
intricate interactions, and difficulties in transferability. To address the issues of complex …