5 papers
Enhancing Communication Efficiency in FL with Adaptive Gradient Quantization and Communication Frequency Optimization
Asadullah Tariq, Tariq Qayyum, Mohamed Adel Serhani +3
Federated Learning (FL) enables participant devices to collaboratively train deep learning models without sharing their data with the server or other devices, effectively addressin…
Task-based Loss Functions in Computer Vision: A Comprehensive Review
Omar Elharrouss, Yasir Mahmood, Yassine Bechqito +4
Loss functions are at the heart of deep learning, shaping how models learn and perform across diverse tasks. They are used to quantify the difference between predicted outputs and…
Domain Specific Benchmarks for Evaluating Multimodal Large Language Models
Khizar Anjum, Muhammad Arbab Arshad, Kadhim Hayawi +10
Large language models (LLMs) are increasingly being deployed across disciplines due to their advanced reasoning and problem solving capabilities. To measure their effectiveness, va…
Intelligent Task Offloading in VANETs: A Hybrid AI-Driven Approach for Low-Latency and Energy Efficiency
Tariq Qayyum, Asadullah Tariq, Muhammad Ali +3
Vehicular Ad-hoc Networks (VANETs) are integral to intelligent transportation systems, enabling vehicles to offload computational tasks to nearby roadside units (RSUs) and mobile e…
Blockchain and Distributed Ledger Technologies for Cyberthreat Intelligence Sharing
Asadullah Tariq, Tariq Qayyum, Saed Alrabaee +1
Cyberthreat intelligence sharing is a critical aspect of cybersecurity, and it is essential to understand its definition, objectives, benefits, and impact on society. Blockchain an…