Michal Szczepanski

According to our database, Michal Szczepanski authored at least 8 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

SVD-Prune: Training-Free Token Pruning For Efficient Vision-Language Models.

Yvon Apedo, Martyna Poreba, Michal Szczepanski, Samia Bouchafa

CoRR, April, 2026

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

Michal Szczepanski, Martyna Poreba, Karim Haroun

SN Comput. Sci., February, 2026

Are Superpixels the Missing Ingredient for Robust ViT Pruning?

Ahmed Soulmani, Martyna Poreba, Michal Szczepanski

Proceedings of the 21st International Conference on Computer Vision Theory and Applications, 2026

G2TM: Single-Module Graph-Guided Token Merging for Efficient Semantic Segmentation.

Victor Bercy, Martyna Poreba, Michal Szczepanski, Samia Bouchafa

Proceedings of the 21st International Conference on Computer Vision Theory and Applications, 2026

2025

I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation.

Jordan Sassoon, Michal Szczepanski, Martyna Poreba

CoRR, September, 2025

STEP: SuperToken and Early-Pruning for Efficient Semantic Segmentation.

Mathilde Proust, Martyna Poreba, Michal Szczepanski, Karim Haroun

Proceedings of the 20th International Joint Conference on Computer Vision, 2025

J3DAI: A tiny DNN-Based Edge AI Accelerator for 3D-Stacked CMOS Image Sensor.

Benoît Tain, Raphael Millet, Romain Lemaire, Michal Szczepanski, Laurent Alacoque, Emmanuel Pluchart, Sylvain Choisnet, Rohit Prasad, Jérôme Chossat, Pascal Pierunek, Pascal Vivet, Sébastien Thuries

Proceedings of the IEEE/ACM International Symposium on Low Power Electronics and Design, 2025

2019

Online stereo camera calibration on embedded systems. (Calibrage en ligne des caméras stéréo sur les systèmes embarqués).

Michal Szczepanski

PhD thesis, 2019