Hannah Janmohamed

Papers

Total Citations

H-Index

About

Hannah Janmohamed is an emerging researcher specializing in Quality-Diversity (QD) algorithms and evolutionary optimization methods. Her work addresses some of the most pressing challenges in applying QD approaches to real-world problems, particularly around uncertainty, reproducibility, and multi-objective optimization. In her 2025 paper, "Exploring the Performance-Reproducibility Trade-Off in Quality-Diversity," she investigates the critical tension between solution performance and reliable reproducibility when QD algorithms encounter uncertain fitness and behaviour estimations in complex environments — a paper that has already garnered 3 citations since publication. Her earlier 2023 contribution, "Improving the Data Efficiency of Multi-Objective Quality-Diversity through Gradient Assistance and Crowding Exploration," advances the Multi-Objective MAP-Elites (MOME) framework by enhancing data efficiency through gradient-based techniques and improved diversity exploration, earning 2 citations. Janmohamed's research is particularly valuable for the optimization and machine learning communities, as she bridges theoretical QD advancements with practical scalability concerns. Though early in her career, her focus on robust, diverse solution generation positions her as a promising voice in neuroevolution and black-box optimization research.