PhD Thesis Defense

In this thesis, we study methods and tools for learning from uncertain and incomplete longitudinal data.

This thesis investigates how LLMs can assist, transform, and extend human work across three specific tasks: translation, editing, and literary interpretation.

This dissertation categorizes skills that fall under computational thinking and describes our work towards improving student learning and engagement.

This dissertation argues for a different approach to sorting and filtering social media feeds.

In this defense, I outline a program to move from post-hoc explanations toward a principled science of reverse-engineering LLM internals.

This research investigates the design and implementation of ultrasonic sensing systems that allow everyday devices to perceive and interpret signals beyond the

This thesis seeks to understand the extent of health inequity captured in EHR data and investigate how ML models can be redesigned to ensure they maintain...

This thesis studies questions from three complementary perspectives for real-world scenarios.

This thesis proposes an alternative path toward intelligent control by  drawing inspiration from biological systems and exploring the concept of time-aware...

This thesis focuses on addressing the challenges of sleep monitoring at the community level by developing scalable, personalizable, and robust sleep detection..

I develop a Gumbel random process-based approach that improves the optimization  landscape, resulting in a more stable and expressive variant of Box Embedding.

This thesis develops scalable, accurate tools and benchmarks for factuality assessment that set higher standards for AI evaluation.