activity
20242026
collaborators

6 papers

cs.LG2026

Topology-Preserving Deep Joint Source-Channel Coding for Semantic Communication

Omar Erak, Omar Alhussein, Fang Fang +1

Many wireless vision applications, such as autonomous driving, require preservation of global structural information rather than only per-pixel fidelity. However, existing Deep joi…

cs.LG2025

Adaptive Pareto-Optimal Token Merging for Edge Transformer Models in Semantic Communication

Omar Erak, Omar Alhussein, Hatem Abou-Zeid +1

Large-scale transformer models have emerged as a powerful tool for semantic communication systems, enabling edge devices to extract rich representations for robust inference across…

cs.LG2025

Adaptive Token Merging for Efficient Transformer Semantic Communication at the Edge

Omar Erak, Omar Alhussein, Hatem Abou-Zeid +2

Large-scale transformers are central to modern semantic communication, yet their high computational and communication costs hinder deployment on resource-constrained edge devices.…

cs.LG2025

Contrastive Learning and Adversarial Disentanglement for Privacy-Aware Task-Oriented Semantic Communication

Omar Erak, Omar Alhussein, Wen Tong

Task-oriented semantic communication systems have emerged as a promising approach to achieving efficient and intelligent data transmission in next-generation networks, where only i…

cs.CL2025

Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards

Omar Erak, Nouf Alabbasi, Omar Alhussein +4

Recent studies show that large language models (LLMs) struggle with technical standards in telecommunications. We propose a fine-tuned retrieval-augmented generation (RAG) system b…

cs.CL2024

TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network

Nouf Alabbasi, Omar Erak, Omar Alhussein +3

The telecommunications industry's rapid evolution demands intelligent systems capable of managing complex networks and adapting to emerging technologies. While large language model…