Vincent Hellendorn

The goal of Vincent Hellendorn's work is to make safe, effective programming more accessible through intelligent software assistance tools. AI-based tools hold great promise for extracting expertise from public data about software (on GitHub, StackOverflow, etc.) and presenting this in a timely fashion to help new and inexperienced developers.

His research works towards this goal across three frontiers: 

1. investigating new applications of AI in SE to understand the community’s needs broadly and provide practical value (e.g., FSE’18, FSE’21 IRV, EMSE’21)
2. analyzing current models and trends to make sure our results are impactful (ICSE’19, FSE’21, CACM’22)
3. building new models based on these insights (ICLR’20, NeurIPS’21, ICLR’22), including PolyCoder, currently the largest open-source model trained exclusively on source code