Hey, I'm Adam!
I'm a professor at
Stevens Institute of Technology. I design and develop interactive systems for data visualization and analysis. I am also the founding
director of the Stevens Visualization Lab.
Read this if you want to join my
group!
I received my PhD from the
School of Interactive Computing at
Georgia Tech, where I worked with Alex Endert in the
Visual Analytics Lab. My dissertation was on
Detecting and Mitigating Pedagogical Risks in Large Language Models with Visual Analytics.
Over the years, I've collaborated with many incredible designers, researchers, engineers, and scientists
at
MIT Lincoln
Laboratory, 
National
Security Agency (NSA),
Laboratory for
Analytic Sciences (LAS),
Adobe Research,
NASA Jet Propulsion
Laboratory (JPL),
Caltech,
Vanderbilt,
Georgia State,
Tufts,
Emory,
ArtCenter
College of Design, and the
Monterey Bay
Aquarium Research Institute (MBARI).
Research Themes
At Stevens, I lead the Stevens Visualization Lab. Our mission is to help people make sense of complex data. We combine methods from AI, data science, and human-computer interaction to develop new interactive systems for data visualization and analysis. We engage in iterative co-design and longitudinal field deployments with domain experts across intelligence analysis, education, and robotics to study how such systems impact data-driven decision-making. Our work contributes open-source software, empirical research, and design guidelines to visualization, HCI, and AI communities. See all of our projects on our lab website. Our research thrusts include:
Visualizations for Traceable and Defensible Human-AI Collaboration
How can we verify and steer AI reasoning against underlying data using interactive visualizations? Examples include: goal tracking in LLM conversations (OnGoal) and traceable document analysis with LLMs and knowledge graphs (VisPile).
Making AI Trustworthy in Education Through Interactive Visualization
How can visualizations help us develop, integrate, and evaluate AI in the learning process? Examples include: debugging AI essay scoring (iScore), provenance analytics for intelligent tutors (VisTA), and in-text traces of AI assistance in writing (DraftMarks).
Visual Analytics for Expert-Driven Scientific Discovery
Co-designing interactive systems with scientists to help them explore sparse, multidimensional scientific data using AI (DeepSee).
Bias-Aware Visual Analytics Using Interaction Traces
Studying how showing analysts a live record of their own interactions and interactions with AI can make them aware of unconscious bias and help them adjust how they analyze data (Lumos; Left, Right, and Gender).
