PhD Dissertation Proposal Defense

In this thesis, we explore how recent progress in generative modeling improves solutions to inverse problems.

This proposal provides a unified framework for developing more accurate, scalable, and privacy-aware personalized LLMs.

This thesis develops and analyzes principled, efficient, and scalable algorithms for answering marginal queries under differential privacy.

This dissertation evaluates curriculum aware adaptive tutoring systems and computational learning platforms.

This thesis investigates motion planning and learning based control methods with the goal of developing robust controllers for dynamic legged robots.

This thesis develops datasets, methods and theory to support the peer review process in both the pre- and post-LLM paradigms. 

This thesis reframes low dimensional representation as a coordinate-learning problem.

This dissertation addresses this limitation by developing AI and clinical natural language processing (NLP) methods that transform longitudinal narrative data.

This dissertation develops methods for accurately measuring user trust in software and creates automated techniques for making software more trustworthy.

This thesis explores the design and implementation of ultrasonic sensing systems allowing devices to perceive and interpret signals beyond the audible spectrum.

This thesis explores new spatial shifting techniques to reduce carbon emissions while maintaining performance.

In this proposal our goal is to make generative retrieval scalable and practical for real-world information retrieval systems.