collaborators

9 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.SD2026

It Takes Few to TANGO: A Quantized Distributed Model for Binaural Speech Enhancement

Zahra Benslimane, Pierre Chouteau, Martyna Poreba +4

Neural network-based multichannel speech enhancement systems achieve strong enhancement performance, but their computational and memory requirements limit deployment on resource-co…

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.SD2026

RT-Tango: Real-Time Distributed Binaural Speech Enhancement for Low-Power Hearing Aid Devices

Z. Benslimane, P. Chouteau, M. Poreba +4

Real-time binaural speech enhancement is constrained by latency, computational cost, and inter-device communication, yet existing efficient solutions predominantly address single-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.CV2026

Token-Space Mask Prediction for Efficient Vision Transformer Segmentation

Calvin Galagain, Martyna Poreba, François Goulette

Query-based Vision Transformer segmentation models typically reconstruct dense spatial feature maps to predict masks, inheriting design patterns from convolutional architectures. W…