1 citations · 1 across the 8 of their papers we have counts for
12 papers
Channel-Adaptive Region Adjacency Graph Carriers for Semantic Image Communication
Karim Abdallah, Maria Slim, Mariette Awad +1
Semantic image communication seeks to preserve task-relevant scene structure under limited channel resources, but carriers are often dense latent tensors or grid-aligned semantic l…
Krum-Inspired Central Teacher Selection and Residual Channel Bottlenecks for Efficient DeepSC
Rami Eid, Mostafa Jammoul, Omar Kaaki +3
Deploying transformer-based semantic communication models on edge devices requires compression that preserves semantic fidelity under channel variability. We study a compressed dee…
Privacy-Preserving Deep Joint Source-Channel Coding with In-Loop Concept Erasure
Rami Eid, Maria Slim, Mariette Awad +1
Deep joint source-channel coding (DeepJSCC) transmits learned semantic features efficiently but can leak sensitive attributes such as gender, race, or speaker identity. We propose…
Where to Defend? Layer-Wise Adversarial Training for Robust Transformer-Based Semantic Communications
Maria Slim, Razane Tajeddine, Mariette Awad +1
Deep learning-based semantic communication (DeepSC), a Transformer-based encoder-decoder, achieves semantic fidelity over noisy channels but remains vulnerable to adversarial pertu…
Extractive Summarization for Arabic Documents Using SAraBERT with a Semantic Siamese Similarity Evaluation Metric
Sami Shames El Deen, Mariette Awad
In this research, we introduce SAraBERT, an enhanced version of AraBERT which proposes inter-sentence transformer layers for extractive summarization tasks. To ensure that the summ…
The Forward-Backward Disconnect: State Dynamics, Credit Assignment, and Biological Grounding in Neural Computation
Hadi Al Mubasher, Mariette Awad
A recurring pattern in neural computation is the reintroduction of dynamical and biological structure into models originally simplified for scalable optimization. Early feedforward…
RRFC: Recursive Refinement via Feedback Conditioning for Iterative Image-to-Image Generation
Kareem Hassani, Chaymaa Abbas, Hadi Al Mubasher +1
Conditional image-to-image generators are single-shot: they map input features to an output in one forward pass and treat it as final, with no opportunity to improve on it. Althoug…
THESIS-MoE: Trainable Hierarchical Extraction and SteerIng of Sycophancy in Mixture-of-Experts
Kareem Hassani, Chaymaa Abbas, Lama Mawlawi +1
Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure. Existing activation steering methods typically app…
Obscuring Data Contamination Through Translation: Evidence from Arabic Corpora
Chaymaa Abbas, Nour Shamaa, Nour Shammaa +1
Data contamination can invalidate benchmark evaluation when a model benefits from memorized evaluation content rather than genuine generalization. Yet contamination is difficult to…
ChartComplete: A Taxonomy-based Inclusive Chart Dataset
Ahmad Mustapha, Charbel Toumieh, Mariette Awad
With advancements in deep learning (DL) and computer vision techniques, the field of chart understanding is evolving rapidly. In particular, multimodal large language models (MLLMs…
Can Small-Scale Data Poisoning Exacerbate Dialect-Linked Biases in Large Language Models?
Chaymaa Abbas, Mariette Awad, Razane Tajeddine
Style-conditioned data poisoning is identified as a covert vector for amplifying sociolinguistic bias in large language models. Using small poisoned budgets that pair dialectal pro…
AraSTEM: A Native Arabic Multiple Choice Question Benchmark for Evaluating LLMs Knowledge In STEM Subjects
Ahmad Mustapha, Hadi Al-Khansa, Hadi Al-Mubasher +5
Large Language Models (LLMs) have shown remarkable capabilities, not only in generating human-like text, but also in acquiring knowledge. This highlights the need to go beyond the…