Get started
Author

Michal Szczepanski

J3DAI: A tiny DNN-Based Edge AI Accelerator for 3D-Stacked CMOS Image Sensor
2025 · Benoit Tain, Raphaël Millet, et al. · International Symposium on Low Power Electronics and Design (ISLPED) · 5
PDF
Where Do Tokens Go? Understanding Pruning Behaviors in STEP at High Resolutions
2026 · Michal Szczepanski, Martyna Poreba, et al. · SN Computer Science · 4
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) · 4
Online stereo camera calibration on embedded systems
2019 · Michał Szczepanski · theses.fr (ABES) · 2
RT-Tango: Real-Time Distributed Binaural Speech Enhancement for Low-Power Hearing Aid Devices
2026 · Zahra Benslimane, Pierre Chouteau, et al. · Interspeech (USB) · 1
PDF
I-Segmenter: Integer-only Vision Transformer for efficient semantic segmentation
2026 · Jordan Sassoon, Michal Szczepanski, et al. · Journal of Systems Architecture · 1
PDF
Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models
2026 · Apedo, Yvon, Poreba, Martyna, et al. · arXiv (Cornell University) · 1
PDF
G2TM: Single-Module Graph-Guided Token Merging for Efficient Semantic Segmentation
2026 · Victor Bercy, Martyna Poreba, et al. · International Conference on Computer Vision Theory and Applications · 1
SVD-Prune: Spectral Vision Token Pruning under Extreme Compression
2026 · Apedo, Yvon, Poreba, Martyna, et al. · arXiv (Cornell University)
PDF
Decoder-Agnostic Token Merging for Vision Transformers: A Systematic Study of G2TM
2026 · Bercy, Victor, Poreba, Martyna, et al. · arXiv (Cornell University)
PDF
From Complexity to Efficiency: Pruning Vision Transformers in Practice
2026 · Martyna Poreba, Ahmed Soulmani, et al. · River Publishers eBooks
Closing the Gap Between AI Models and Silicon: Application Deployment for Next-Generation Edge Accelerators
2026 · Michal Szczepanski, Benoit Tain, et al. · River Publishers eBooks
Multichannel Speech Enhancement under Low-Latency Constraints: Balancing Quality and Computational Cost
2026 · Zahra Benslimane, Fabrice Auzanneau, et al. · River Publishers eBooks
Enabling Fully Integer-Only Inference for Lightweight Detection Transformers
2026 · Le, Thanh Cong, Szczepanski, Michal, et al. · arXiv (Cornell University)
PDF
It Takes Few to TANGO: A Quantized Distributed Model for Binaural Speech Enhancement
2026 · Benslimane, Zahra, Chouteau, Pierre, et al. · arXiv (Cornell University)
PDF
Modèles vision-langage efficaces grâce à l’élagage de tokens : dimensions de conception, méthodes et challenges
2026 · Apedo, Komi Etse Yvon, Poreba, Martyna, et al. · HAL
Toward Embedded Vision-Language Perception for Long-Term Autonomous Robots via Training-Free Token Pruning
2026 · Apedo, Komi Etse Yvon, Poreba, Martyna, et al. · HAL
Are Superpixels the Missing Ingredient for Robust ViT Pruning?
2026 · Ahmed Soulmani, Martyna Poreba, et al. · International Conference on Computer Vision Theory and Applications
Optimising ViT for Edge Deployment: Hybrid Token Reduction for Efficient Semantic Segmentation
2025 · Mathilde Proust, Martyna Poreba, et al. · River Publishers eBooks
PDF
Works count: 19
Citation count: 19
H-index: 3
I10-index:
Year
Topic
Type