Projects

RISE: Interactive Visual Diagnosis of Fairness in Machine Learning Models. An interactive system that converts sorted residuals into interpretable patterns for post-hoc fairness diagnosis under domain shift.

This project centers on machine interpretation of Mixtec codexs left to history by the precolonial and early colonial peoples of mesoamerica. It is a continuation of work for our Mixtec NLP grant.

This project is about Accented Speech and Audio Processing using Audio Language models.

This project is about utilizing vision language models (VLMs) to read comic book pages for blind and visually impaired users.

This project searches for the intersection of natural language processing and semasiographic writing systems.

Integrating Humans and Technology for Fast and Fair Labeling