STM-Graph is a Python framework for analyzing spatial-temporal urban data and doing predictions using Graph Neural Networks. It provides a complete end-to-end pipeline from raw event data to trained ...

Abstract: Pathfinding on grid maps is a cornerstone problem in robotics, autonomous navigation, and game development. Classical algorithms such as A*, Dijkstra’s, and Breadth-First Search (BFS) are ...

Abstract: Efficient Multi-Agent Path Finding (MAPF) is pivotal for warehouse logistics. While existing learning-based methods primarily rely on computationally intensive grid-based representations, ...

StaR (Stateful Root Cause Analysis) is a deep learning framework for root cause analysis and causal discovery in dynamic multivariate time-series systems. This repository provides the official ...