4 papers
Bern2Edge: A Neurosymbolic Compiler for Edge Deployment via Bernstein Polynomial Networks
Malak Gamal El-Din, Yifan Zhang, Yasser Shoukry +2
Deploying high-accuracy neural networks on resource-constrained edge devices remains challenging, as existing approaches treat training, compression, and hardware synthesis as sepa…
Exponential Approximation Rates and Parameter Efficiency of Learnable Bernstein Activations
Ibrahim Albool, Malak Gamal El-Din, Salma Elmalaki +1
The choice of activation function fundamentally shapes the representational capacity and parameter efficiency of deep neural networks, yet most widely used activations lack rigorou…
PACIFIC: Can LLMs Discern the Traits Influencing Your Preferences? Evaluating Personality-Driven Preference Alignment in LLMs
Tianyu Zhao, Siqi Li, Yasser Shoukry +1
User preferences are increasingly used to personalize Large Language Model (LLM) responses, yet how to reliably leverage preference signals for answer generation remains under-expl…
KoALA: KL-L0 Adversarial Detector via Label Agreement
Siqi Li, Yasser Shoukry
Deep neural networks are highly susceptible to adversarial attacks, which pose significant risks to security- and safety-critical applications. We present KoALA (KL-L0 Adversarial…