Browsing by Discipline
Now showing items 1-3 of 3
-
Enhancing semantic segmentation: architectural innovations and strategies for label-efficient learning
(2025)Semantic segmentation is a fundamental component of modern computer vision applications. Although supervised learning models have achieved state-of-the-art performance in this domain, they rely heavily on large volumes ... -
Improving performance of NOMA and RSMA systems with improper Gaussian signaling
(2025)With the new wave of beyond fifth generation (B5G) and sixth generation (6G) communication systems, there is a perpetual demand for more wireless services with higher data rates, lower latency, and greater connectivity. ... -
Zero-shot pruning of transformer language models using non-dominated sorting genetic algorithm
(2025)Large Language Models (LLMs) are advanced neural networks trained on massive text corpora to understand and generate human language. While they have grown significantly in power and capability, their extensive parameter ...
