PhD Thesis Defense

 This thesis examines three complementary roles of motion in computer vision.

This thesis develops and analyzes compact formulations for decision-making problems characterized by large action and large state sets.

This dissertation advances conversational AI by showing how multi-agent chatbots, thoughtful avatar design, and personalized interactions enhance engagement...

The central task developed in this work is to learn a global probabilistic model, often a graphical model, that is consistent with these observed marginals.

In this thesis, we revisit the task of data selection through the lens of social-oriented metrics like diversity and fairness.

In this thesis I present computational methods for transforming large-scale, unstructured data into rich semantic structures to support human decision-making.

In this thesis, we identify and rectify some limitations of such cryptographic constructions and their proofs of security.

This dissertation studies the fundamental limits of covert activity across communication, network attack, and sequential detection settings.

This thesis addresses challenges of dataset scarcity and energy efficiency.

The dissertation addresses the fundamental challenge of deploying machine learning models on resource-constrained autonomous systems

This dissertation presents five systems that jointly optimize computation and communication across two workload regimes.

In this thesis, I address this problem by introducing multiple approaches for aligning LLMs with student behavior and knowledge.