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…
PACIFIC: Can LLMs Discern the Psychometric Traits Influencing Your Preferences? 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 reliably leveraging preference signals remains under-explored. In practice, preferen…
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…
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…