AI@UNC
Team 01 · Pending
Title forthcoming
Lead to be announced
A description of this team's research and engineering work will appear here once the project is confirmed.
Technical AI research and applied machine learning initiatives at Carolina.
Current term
At least five project teams will run this semester. Titles, leads, and technical requirements will be posted here as they are confirmed. Additional teams may still join the roster before applications open.
Team 01 · Pending
Lead to be announced
A description of this team's research and engineering work will appear here once the project is confirmed.
Team 02 · Pending
Lead to be announced
A description of this team's research and engineering work will appear here once the project is confirmed.
Team 03 · Pending
Lead to be announced
A description of this team's research and engineering work will appear here once the project is confirmed.
Team 04 · Pending
Lead to be announced
A description of this team's research and engineering work will appear here once the project is confirmed.
Team 05 · Pending
Lead to be announced
A description of this team's research and engineering work will appear here once the project is confirmed.
Two further teams may be announced before membership applications open on Monday, August 24, 2026.
Past term
Completed technical projects from the previous semester.
Lead: Obed Pasha
Automatically flagging corrupt or mis-entered data across databases. Extension of last year’s work.
Lead: Dr. Bazzano
Aggregating N-of-1 experimental designs using machine learning and deep learning to model individualized treatment effects.
Lead: Dr. Bazzano
Building an AI agent translating a scoping review of AI in public health into an interactive, accessible system.
Lead: Dr. Bazzano
Designing a privacy-conscious AI prototype supporting women balancing work, caregiving, and health.
Lead: Dr. Bazzano
Developing a multimodal misinformation detection system focused on maternal and child health.
Lead: Dr. Sylvia
Coming soon
Lead: Dr. Sylvia
Coming soon
Lead: Dr. Templin
Build and evaluate models that learn user preferences from feedback (ratings, clicks, comparisons) to optimize rankings and recommendations. Work includes data cleaning, training preference/ranking models, metric-driven evaluation, and an end-of-semester demo/report.
Lead: Dr. Sola
Using NLP to classify how social scientists operationalize neoliberalism across published research.
Lead: Arsh Noman
Using evolutionary algorithms and reinforcement learning to discover QEC codes and reimplement research-grade systems.
Lead: Sam Bisaria
AI-powered course recommendations, autonomous registration tools, and UI improvements integrating ConnectCarolina data.
Lead: Rohan Phadke
Using video understanding models to caption and analyze sports videos. The end goal is to produce a full-stack application that can provide feedback on an athlete’s form as a virtual coach.