Harry Ye叶 润龙

Developing CopilotLens, a framework that transforms AI code generation from opaque suggestions into transparent, explainable interactions. By providing post-hoc summaries and on-demand explanations, we aim to foster more trustworthy human-AI collaboration in software development.

ScholarMate is an interactive system that augments qualitative research by blending AI assistance with human oversight. The tool enables researchers to work on a visual canvas, organizing and connecting text snippets while maintaining critical engagement and control over the analysis process.

ARC is an open-source tool designed to streamline systematic literature reviews in computing research. Developed through user-centered design with 20 experienced researchers, it automates literature searches, data extraction, and reference tracking while maintaining transparency and reproducibility standards.

This work introduces pedagogical prompting, a theoretically-grounded concept to teach students how to effectively prompt LLMs to improve their learning. An interactive system was designed and developed with scenario-based instruction to train these skills.

TreeReader revolutionizes academic paper navigation by transforming linear documents into an interactive, hierarchical tree, allowing users to selectively expand and collapse sections and sub-sections on the tree base on user intension. This structure, combined with on-demand access to source text and contextual information, offers a more focused and efficient way to engage with complex scholarly literature beyond summarization.