I am currently a student at the College of William and Mary. I am also fortunate to be supervised by Hy Truong Son, Anh Totti Nguyen and Thiago Serra. My research focuses on applications of LLMs in the domains of Healthcare, and quantifying and understanding the limitations and biases of LLMs and VLMs.

1. LLMs in Healthcare: I worked on improving speech summarization with LLM synthetic data (link) and leveraging LLM reasoning to enhance the interpretability and performance of medical sentiment analysis (link).
2. Vision-Language Models: Some tasks are simple for humans yet hard for VLMs. My current project aims to quantify, understand and close this performance gap.

Selected Publications

♠ denotes equal contribution

Sentiment Reasoning for Healthcare
Khai-Nguyen Nguyen^♠, Khai Le-Duc^♠, Bach Phan Tat, Duy Le, Long Vo-Dang, Truong-Son Hy
ACL 2025, Industry Track (Oral)

Medical Spoken Named Entity Recognition
Khai Le-Duc, David Thulke, Hung-Phong Tran, Long Vo-Dang, Khai-Nguyen Nguyen, Truong-Son Hy, Ralf Schluter
NAACL 2025, Industry Track (Oral)

Real-time Speech Summarization for Medical Conversations
Khai Le-Duc^♠, Khai-Nguyen Nguyen^♠, Long Vo-Dang, Truong-Son Hy
Interspeech 2024 (Oral)

Getting away with more network pruning: From sparsity to geometry and linear regions
Jeffrey Cai^♠, Khai-Nguyen Nguyen^♠, Nishant Shrestha, Aidan Good, Ruisen Tu, Xin Yu, Shandian Zhe, Thiago Serra
Workshop on Sparsity in Neural Networks, ICLR 2023