Uranik Berisha

2 accepted papers

2025

Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks

Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache

CVPR 2025poster

Vision Transformers (ViTs) have emerged as the state-of-the-art models in various Computer Vision (CV) tasks, but their high computational and resource demands pose significant challenges. While Mixture of Experts (MoE) can make these models more efficient, they often require costly retraining or ev…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Variance-Based Pruning for Accelerating and Compressing Trained Networks

Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache

ICCV 2025poster

Increasingly expensive training of ever larger models such as Vision Transfomers motivate reusing the vast library of already trained state-of-the-art networks. However, their latency, high computational costs and memory demands pose significant challenges for deployment, especially on resource-cons…

Cited by 0 Source ↗PDF ↗Scholar ↗