M.S. Student in Computer Science
William & Mary
My research interests span human-computer interaction, machine learning, and software engineering. I am particularly interested in the reliability of intelligent systems and how technology interacts with people.
4 of 4 entries
No entries match these filters.
This research investigates the robustness of code language models by examining whether their predictions remain consistent when the source code is unchanged but its token representation varies. It develops search-based metamorphic testing techniques to identify representation-invariance violations in code understanding tasks.
PsyArXiv Preprint · December 2025
This scoping review synthesizes 76 studies examining the use of large language models as psychotherapists. It investigates therapeutic approaches, model development methods, and evaluation practices, identifying important gaps in clinical grounding, safety, privacy, and human-centered evaluation.
This research investigates the needs, experiences, and perspectives of blind and low-vision users regarding smart glasses. Drawing on survey and interview data, it explores considerations for designing accessible and human-centered wearable technologies.
This research examines how humans contribute to the development and evaluation of LLM-based psychotherapy systems. Through a systematic literature review, it explores the roles of users, clinicians, and other stakeholders in shaping these technologies and assessing their therapeutic capabilities.
4 of 4 entries
No entries match these filters.
An ongoing Chrome extension project exploring how Google Calendar events can be represented through personalized visual imagery. The application uses browser extension technologies and a Python-based backend, with image generation capabilities for representing people, activities, and places.
A course project investigating key-value cache reuse in large language model inference. The project explores the mechanisms and potential efficiency benefits of reusing cached computations through experimental implementation and evaluation.
Save It! turns everyday sustainable actions into achievable goals, playful rewards, and a garden that grows with your progress.
A collection of course projects involving the development, adaptation, and evaluation of machine learning and language models for different tasks. Details about the individual models, datasets, and results will be added later.