Research

In enterprise analytics, most LLM-based tools merely retrieve facts or summarize charts. But insights that truly drive strategy—those rooted in domain expertise—still elude most automated systems. Our paper, Data-to-Dashboard, presents a novel agentic AI framework that simulates how human analysts think. By combining domain detection, concept extraction, multi-perspective analysis, and iterative reflection, this system transforms…

In many scientific problems — especially in fields like quantum mechanics and wave propagation — physics provides powerful constraints that can guide machine learning. But these constraints don’t always align; Optimizing for both at once can create tension in the training process. CoPhy-PGNN (Competing Physics-Guided Neural Networks) is a training approach designed to reconcile such…

What if we could see how a neural network learns—watching it navigate hills, valleys, and decision points as it optimizes? Loss landscape visualization tries to do just that, but common methods like PCA and t-SNE often miss the twists and turns that matter most, oversimplifying the training process and missing the full picture. Neuro-Visualizer is…