Hello! I am an AI researcher and educator. My goal is to help build AI systems that can keep learning over time without forgetting what they have already learned.
I currently focus on continual learning, developing methods for efficient and lifelong learning in deep learning systems, alongside teaching and mentoring in machine learning.
Beyond research, I enjoy playing tennis and travelling.
06/2026, Our paper "Coresets are More Than a Replay" has been published in Neural Computing and Applications (NCAA).
05/2026, I gave a talk at Fontys about "Continual Learning and What it Takes to Publish a Paper".
04/2026, I led the interactive lab sessions for the Machine Learning Engineering course at TU Eindhoven.
03/2026, PAM has been presented at CPAL 2026.
02/2026, Our paper TOSCA has been published in TMLR.
12/2025, Our papers PAM and TOSCA are presented at the NeurIPS workshop "Scalable Continual Learning for Lifelong Foundation Models".
10/2025, I have taken on a temporary lecturer position at TU Eindhoven.
Keeps a pre-trained backbone frozen and adds small sparse task-specific adapters, giving a lightweight yet strong baseline for continual learning with foundation models.
Introduces TOSCA, a sparse adapter-calibrator module on the classification token that lets foundation models keep learning new tasks without losing prior knowledge.
Shows that coreset selection can be applied to the whole training set, not just a small replay buffer, substantially cutting the amount of data needed for continual learning.
Uses Bayesian optimization to automatically tune each new task's hyperparameters, improving accuracy and reducing forgetting in class-incremental learning.
