Tag
This paper presents AIMC, a visual analytics framework for human oversight of autonomous scientific discovery, enabling monitoring and understanding of AI-generated research artifacts.
This paper presents a graph-to-answer mechanism-tracing case study for Graph-PRefLexOR-8B, a materials-science hypothesis generation model, using visualization and activation-based diagnostics to localize where mechanism support is lost or recovered during generation.
Crystalis is a framework that uses query-centric modeling and two mechanisms (progressive nucleation and semantic annealing) to enable LLMs to generate structurally correct coordinated multi-view visualizations, achieving up to 75% end-to-end success on benchmarks.
LatentFlow is a visual analytics system for analyzing latent spaces in molecular graph neural networks, helping scientists understand how clusters of molecular embeddings evolve across layers and model states.