9 papers
Amnesia: A Stealthy Replay Attack on Continual Learning Dreams
Ahmed Sharshar, Naveen Kumar Kummari, Mohsen Guizani
Continual learning (CL) models often use experience replay to reduce catastrophic forgetting, but their robustness to replay sampling interference remains underexplored. Existing C…
ChatENV: An Interactive Vision-Language Model for Sensor-Guided Environmental Monitoring and Scenario Simulation
Hosam Elgendy, Ahmed Sharshar, Ahmed Aboeitta +1
Understanding environmental changes from remote sensing imagery is vital for climate resilience, urban planning, and ecosystem monitoring. Yet, current vision language models (VLMs…
Constraint-Driven Warm-Freeze for Efficient Transfer Learning in Photovoltaic Systems
Yasmeen Saeed, Ahmed Sharshar, Mohsen Guizani
Detecting cyberattacks in photovoltaic (PV) monitoring and MPPT control signals requires models that are robust to bias, drift, and transient spikes, yet lightweight enough for res…
Not Only Grey Matter: OmniBrain for Robust Multimodal Classification of Alzheimer's Disease
Ahmed Sharshar, Yasser Ashraf, Tameem Bakr +4
Alzheimer's disease affects over 55 million people worldwide and is projected to more than double by 2050, necessitating rapid, accurate, and scalable diagnostics. However, existin…
Towards Inclusive NLP: Assessing Compressed Multilingual Transformers across Diverse Language Benchmarks
Maitha Alshehhi, Ahmed Sharshar, Mohsen Guizani
Although LLMs have attained significant success in high-resource languages, their capacity in low-resource linguistic environments like Kannada and Arabic is not yet fully understo…
Vision-Language Models for Edge Networks: A Comprehensive Survey
Ahmed Sharshar, Latif U. Khan, Waseem Ullah +1
Vision Large Language Models (VLMs) combine visual understanding with natural language processing, enabling tasks like image captioning, visual question answering, and video analys…