PhD Dissertation Proposal Defense

This dissertation explores machine learning techniques for molecular property prediction, with a focus on modeling and understanding mycomembrane permeability.

Overall, this thesis details how LLMs can support mnemonic generation for vocabulary learning through both sound-based and shape-based associations.

This thesis addresses both specification and scalability challenges in agentic system alignment.

In this thesis, we study how LLMs can generate and assess educational content for open-ended learning of 21st century skills in alignment with human judgment.

This thesis studies patient education grounded in digital health records.

This dissertation aims to explore the different learning approaches on three domains.

 This thesis addresses the need for better understanding of non-ME user-generated data.

This thesis examines such language-specific considerations through case studies on Latin.

This thesis presents a comprehensive framework for developing an autonomous quadruped guide dog robot while aligning with the practical needs of BLV users.

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