collaborators

5 papers

cs.CV2026

Enabling Fully Integer-Only Inference for Lightweight Detection Transformers

Thanh Cong Le, Michal Szczepanski, Martyna Poreba

Vision Transformer detectors now approach the accuracy of CNNs but remain difficult to deploy on NPUs and microcontrollers because key components, including deformable attention, f…

cs.CV2026

Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models

Yvon Apedo, Martyna Poreba, Michal Szczepanski +1

Vision-Language Models (VLMs) have revolutionized multi-modal learning by jointly processing visual and textual information. Yet, they face significant challenges due to the high c…

cs.CV2026

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

Jordan Sassoon, Michal Szczepanski, Martyna Poreba

Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained devices remains limited due to their high me…

cs.AR2026

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

Benoit Tain, Raphael Millet, Romain Lemaire +9

This paper presents J3DAI, a tiny deep neural network-based hardware accelerator for a 3-layer 3D-stacked CMOS image sensor featuring an artificial intelligence (AI) chip integrati…

cs.CV2025

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

Michal Szczepanski, Martyna Poreba, Karim Haroun

Vision Transformers (ViTs) achieve state-of-the-art performance in semantic segmentation but are hindered by high computational and memory costs. To address this, we propose STEP (…