Ongoing · 2026–present
Multimodal Visualization Authoring
Exploring How Students Design Visualizations with Integrated Sketching, Natural Language, and Code Editing
Projects
In addition to our ongoing funded and independent research projects, we are always interested in listening to new ideas and forming new collaborations, so if nothing that we ware currently doing sounds like what you are interested in, please reach out!
Ongoing research
Ongoing · 2026–present
Interactive Synthetic Data Tool for User Evaluation of Exploratory Data Analysis Methods
Developing a tool to study how well dimensionality reduction techniques enable effective truth tracking data exploration when given to actual users.
Ongoing · 2026–present
Interactive Visualization of Bayes Networks
Developing an interactive visualization tool for Probabilistic Graphical Models as an interface towards general purpose probabilistic programing in a visual mode. Ongoing work includes both tool design and development as well as empirical studies to understand the strengths and weaknesses of visual as opposed to code based workflows.
Ongoing · 2026–present
Multimodal and Multiscale Latent Representation of Biodiversity Data
Extending work on the Biocube biodiversity dataset to build multimodal and multi-scale latent representations of complex relational data, and studying ways to interactively build interpretable scientific visualizations on top of the representation.
Ongoing · 2026–present
Multi-Agent Reinforcement Learning Visual Environment
Reinforcement learning is famously difficult to train, and multi-agent environments doubly so. A key aspect of effective training is visibility in to the emergent patterns and behaviors that agents exhibit in the RL environment. This project is studying ways to gain better real time visibility into the multi-agent RL environment to better enable the rapid identification and analysis of learned behaviours.
Past projects
Past · 2026
Cognitive Effects of AI Authorship labels on Interpretive Domains
An empirical study of how perceptions of AI attribution to analysis affects how people respond to analysis in open interpretive domain of art criticism.