PhD Candidate

Mostafa ElAraby

Mila — Quebec AI Institute, Université de Montréal

I research the foundations of robustness and reliable AI. My current work focuses on out-of-distribution (OOD) detection and uncertainty estimation, ensuring machine learning models remain safe when deployed in unpredictable real-world environments.

Mostafa ElAraby

Latest Updates

View All News

Recent Publications

  1. GROOD: GRadient-aware Out-Of-Distribution detection in interpolated manifolds

    TMLR · 2025

    arXiv Code Blog
  2. BACS: Background Aware Continual Semantic Segmentation

    CRV · 2024

    arXiv Code Blog
  3. Identifying efficient sub-networks using mixed integer programming

    OPT Workshop @ NeurIPS · 2020

    arXiv Code Blog

View all publications →

Recent Posts

View all posts →