Tag
The paper proposes Wiki Foundation Model (WFM), a novel foundation model for scalable, agent-native representation and retrieval using LLM Wiki, which couples dense text with link structure, achieving strong performance on benchmarks and 10.5x training acceleration.
GPEvac is a GNN-based PPO framework that computes adaptive evacuation routes during shooting events, significantly reducing threat exposure compared to baselines.
SAGE-XGBoost is a machine learning framework that uses spatially augmented graph embeddings and data augmentation to enhance natural hazard susceptibility mapping under data scarcity, demonstrating superior performance over conventional models.
This paper analyzes distance-preserving embeddings in inhomogeneous random graphs, providing tighter distortion bounds than classical worst-case results and introducing a GNN-augmented variant that learns universal features from small graphs.
MABLE combines masked reconstruction with cosine-similarity losses to learn node and graph embeddings from large heterogeneous graphs, demonstrated on geospatial mineral-exploration data. It unifies masked autoencoding and metric learning in a self-supervised framework without requiring labeled data.