3 papers
cs.CL2026
I'm Sorry, but I Can't Help with Braille: Revealing Accessibility Failures in State-of-the-Art LLMs
Abdullah Abdullah
Large Language Models (LLMs) perform strongly on many language tasks, but their capability in structurally constrained, accessibility-critical modalities such as Braille remains un…
cs.CV2025
Activator: GLU Activation Function as the Core Component of a Vision Transformer
Abdullah Nazhat Abdullah, Tarkan Aydin
The transformer architecture has driven many successes in a variety of tasks within the field of deep learning, in particular the recent advances in natural language processing (NL…
cs.CV2025
NiNformer: A Network in Network Transformer with Token Mixing Generated Gating Function
Abdullah Nazhat Abdullah, Tarkan Aydin
The attention mechanism is the primary component of the transformer architecture; it has led to significant advancements in deep learning spanning many domains and covering multipl…