Justine Gehring
Justine Gehring is a researcher in the field of Machine Learning for code (ML4Code) and Graph Neural Networks (GNNs). Justine obtained her master's from McGill and Mila where her research focused on generating code under challenging circumstances such as library-specific code. Presently, Justine is a research engineer at Moderne, focusing on leveraging AI for large-scale code refactoring and impact analysis. She also oversees the partnership with Mila.
Sessions Montréal 2025
Efficient Code Searching for Large Codebases
Session en anglais - Intermédiaire
This session covers how embedding models can retrieve relevant method matches more effectively than traditional search. We’ll explore real-world examples, like migrating identity providers, where we can use embeddings to identify all HTTP authorization headers across libraries. Additionally, we’ll cover how the top-k selection technique improves search speed and accuracy, by leveraging code-as-data models which use Lossless Semantic Trees.
Transforming Code: AI-Assisted Refactoring with OpenRewrite
Session en anglais - Débutant
Discover automated code remediation with the OpenRewrite refactoring engine, a deterministic, rule-based system. By manipulating the Lossless Semantic Tree (LST) representation of code, OpenRewrite ensures accurate, style-preserving transformations. We’ll demonstrate how AI enhances this process by performing impact analysis, searching through codebases, and assisting in refactoring, ultimately providing a scalable solution for modernization.
