I perform AI research as a graduate student at Johns Hopkins University.
Below are a few recent research papers I have authored:
– The Effect of Sampling Temperature on Problem Solving in Large Language Models
– The Benefits of a Concise Chain-of-Thought on Problem-Solving in Large Language Models
– Natural Language Explanations for Explainable AI Systems Using Self-correcting LLMs
– Automatically Generating Lecture Slides with Generative Pretrained Transformers
I make all of my code, data, and research publicly available as open-source projects on GitHub.
To see more of my research, please visit my Google Scholar and Semantic Scholar profiles.