3 papers
cs.LG2025
Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression
Lorenzo Nikiforos, Luciano Prono, Charalampos Antoniadis +3
The increasing scale of Deep Neural Networks (DNNs) introduces the need for compression techniques such as pruning, quantization, and low-rank decomposition. While these methods ar…
cs.CV2025
Unsupervised Transcript-assisted Video Summarization and Highlight Detection
Spyros Barbakos, Charalampos Antoniadis, Gerasimos Potamianos +1
Video consumption is a key part of daily life, but watching entire videos can be tedious. To address this, researchers have explored video summarization and highlight detection to…
cs.AR2023
Best Memory Architecture Exploration under Parameters Variations accelerated with Machine Learning
Antonios Tragoudaras, Charalampos Antoniadis, Yehia Massoud
The design of effective memory architecture is of utmost importance in modern computing systems. However, the design of memory subsystems is even more difficult today because proce…