Has published multiple papers and given talks at various conferences and workshops, such as a talk on 'Agents for Software Development' at Berkeley and Stanford, and a presentation on 'Large Language Models: a Birds-eye View' at the CMU LTI Large Language Model Seminar. Developed open-source software and posts class and tutorial notes on his teaching page.
Research Experience
Associate Professor at the Carnegie Mellon University Language Technology Institute in the School of Computer Science, and leads the NeuLab. Also serves as the chief scientist at All Hands AI, working on building AI agents for software development.
Background
Research interests include machine learning and natural language processing, with a particular focus on fundamental research and applications of large language models, concentrating on question answering, code generation, multilingual processing, and evaluation/interpretability.
Miscellany
Enjoys development and occasionally discusses research on Twitter.