2 papers
cs.CV2026
Variance-Based Pruning for Accelerating and Compressing Trained Networks
Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache
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 late…
cs.CV2025
Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks
Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache
Vision Transformers have emerged as the state-of-the-art models in various Computer Vision tasks, but their high computational and resource demands pose significant challenges. Whi…