Author

Karim Haroun

Observed name: Haroun, Karim

Institutions: Centre National de la Recherche Scientifique, Université Côte d'Azur, Laboratoire d'Informatique, Signaux et Systèmes de Sophia Antipolis, Université Paris 8

Observed institutions: Centre National de la Recherche Scientifique, Université de Versailles Saint-Quentin-en-Yvelines, Université Côte d'Azur, Commissariat à l'Énergie Atomique et aux Énergies Alternatives, Université Paris-Saclay, CEA Paris-Saclay - Etablissement de Saclay, Laboratoire d'Intégration des Systèmes et des Technologies, Laboratoire d'Informatique, Signaux et Systèmes de Sophia Antipolis, Laboratoire d'Ingénierie des Systèmes de Versailles, Université Paris 8

ORCID: 0009-0000-6972-6019

Observed ORCID: 0009-0000-6972-6019

OpenAlex ID: A5033172385

From Near-Sensor to In-Sensor: A State-of-the-Art Review of Embedded AI Vision Systems

2024 · William Fabre, Karim Haroun, et al. · Sensors · 46

PDF

Minimizing Subject-dependent Calibration for BCI with Riemannian Transfer Learning

2021 · Salim Khazem, Sylvain Chevallier, et al. · International IEEE/EMBS Conference on Neural Engineering · 12

PDF

Dynamic Hierarchical Token Merging for Vision Transformers

2025 · Karim Haroun, Thibault Allenet, et al. · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · 3

Leveraging Local Similarity for Token Merging in Vision Transformers

2025 · Karim Haroun, Jean Martinet, et al. · Communications in computer and information science · 2

PDF

STEP: SuperToken and Early-Pruning for Efficient Semantic Segmentation

2025 · Mathilde Proust, Martyna Poreba, et al. · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · 2

Where Do Tokens Go? Understanding Pruning Behaviors in STEP at High Resolutions

2026 · Michal Szczepanski, Martyna Poreba, et al. · SN Computer Science · 1

PDF

Exploiting Information Redundancy in Attention Maps for Extreme Quantization of Vision Transformers

2025 · Lucas Maisonnave, Karim Haroun, et al. · IEEE International Conference on Computer Vision Workshops · 1

Sparse Competition during Training For the Emergence of Specialized Modules

2026 · Rossigneux, Baptiste, Haroun, Karim · arXiv (Cornell University)

PDF

Sparse Attention to Emotion: Efficient Facial Emotion Recognition via Token Reduction

2026 · Aya Zitouni, Aicha Zenakhri, et al. · Proceedings - International Conference on Image Processing

PDF

Low-Bit Post-Training Quantization of State Space Models via Outlier-Aware Rotation