I completed a Master’s in Computer Science at the University of Alberta under the supervision of Levi Lelis. Currently, I am a Machine Learning researcher at the University of Alberta and Amii, working under Levi’s guidance.

My primary research interest revolves around answering the question: “How can we build systems that learn, reason, and understand the world like humans?” I approach this question through the lens of symbolic reasoning and neurosymbolic AI using techniques from reinforcement learning and imitation learning.

You can contact me via zbashir1 AT ualberta DOT ca.

Publications

Plastic Programming Languages: Learning Neuro-Augmented Domain-Specific Languages
Zahra Bashir, David Aleixo, Kevin Ellis, Levi Lelis (To be submitted to ICML 2025 in Jan)
abstract link - preprint will be out soon!

Revisiting the Assessment of Programmatic Policy Interpretability: Insights from Human Evaluation
Zahra Bashir, Michael Bowling, Levi Lelis (Under Review at IJCAI 2025)
paper link

Assessing the Interpretability of Programmatic Policies with Large Language Models
Zahra Bashir, Michael Bowling, Levi Lelis (RLC 2024 InterpPol Workshop)
paper link