Avatar
Ph.D. student in CIS
University of Pennsylvania
Philadelphia, PA
ltyan@seas.upenn.edu

I am a fourth-year Ph.D. student in Computer and Information Science at the University of Pennsylvania, advised by Prof. Andrew Head.

My research bridges human-AI interaction and software engineering, focusing on AI-powered programming assistants that answer complex developer questions and enhance code understanding.

I design intelligent systems that combine large language models, vision-language models, and agent-based analysis. My recent work includes Trailblazer, which uses intelligent agents to trace program flow and explain behavior inside the IDE; InvisibleMentor, developed during my internship at Microsoft Research's PROSE team, which uses VLMs to infer user actions from spreadsheet screen recordings and recommend improved workflows; and Ivie, which provides lightweight in-situ explanations for AI-generated code.

I completed my master's in Computational Science and Engineering at Harvard, advised by Prof. Elena Glassman, where I developed interactive systems for code and model exploration, including ExampleNet and ParaLib.

Publications

The Invisible Mentor: Inferring User Actions from Screen Recordings to Recommend Better Workflows

Litao Yan, Andrew Head, Ken Milne, Vu Le, Sumit Gulwani, Chris Parnin, Emerson Murphy-Hill
arXiv preprint

PDF