Pourya Shamsolmoali

Achieve state-of-the-art aerial object detection by learning specialized representations across diverse datasets and within complex scenes, and even detect novel object categories without retraining.

Decoupling learning and memory lets models learn new tasks without catastrophic forgetting, outperforming standard regularization techniques.

Ditch the learned router: a global scheduler for Mixture-of-Experts models unlocks state-of-the-art multi-domain learning by explicitly optimizing dataset-to-expert assignments.