About
I am a Principal Research Software Engineer at the Human-AI eXperiences (HAX) team, at Microsoft Research where I focus on Generative AI. My interests are at the intersection of human-computer interaction (HCI), computational social science, and applied machine learning. My research has been published at conferences such as EMNLP, AAAI, and CHI and has received best paper awards. My work has also been featured in outlets such as the Wall Street Journal and VentureBeat.
At Microsoft Research I have led efforts to develop and understand metrics used to evaluate code generation models (GitHub Copilot) (ACL 2023 paper, patent), helped lead efforts in LLMs for Automated Data Visualization (ACL 2023, Code on GitHub) and have contributed to tools for multi-agent AI application development (AutoGen).
Additional details on my work and interests can be found on my personal website – https://victordibia.com.