VAST Challenge

Coordinated-view systems built by our student teams for the IEEE VAST Challenge

Every year since 2024 our student teams enter the IEEE VAST Challenge, building visual analytics systems that uncover hidden behavior in large, heterogeneous event logs and knowledge graphs: suspicious vessels in fishing records, unreliable sources in a news corpus, covert coordination in maritime radio communications, partiality in a committee's decisions, or a worm-like instruction propagating through a multi-agent system. The challenge changes every year, but the method does not: coordinated views that combine temporal pattern analysis, network and topic modeling, anomaly detection, and, increasingly, large language models that extract structured evidence from text. The 2025 entry received the Innovative Display of Daily Communication Patterns Award. The challenge is the lab's training ground for visual analytics design and teamwork.

VAST Challenge

RESEARCHERS

PUBLICATIONS