Skip to content

Karim Haroun

Publication record assembled from the DBLP archive of ranked conferences.

Papers indexed

3

Venues

2

Active years

2025–2025

Best venue rank

A*

Where they publish

Papers

3 indexed papers, newest first.

YearVenueTitleAuthors
2025ICCVExploiting Information Redundancy in Attention Maps for Extreme Quantization of Vision Transformers.Lucas Maisonnave, Karim Haroun, Tom Pgeot
2025VISIGRAPPDynamic Hierarchical Token Merging for Vision Transformers.Karim Haroun, Thibault Allenet, Karim Ben Chehida, Jean Martinet
2025VISIGRAPPSTEP: SuperToken and Early-Pruning for Efficient Semantic Segmentation.Mathilde Proust, Martyna Poreba, Michal Szczepanski, Karim Haroun