3 papers
cs.AI2026
Long-Horizon Autonomous Architecture Research with a Language-Model Agent: A Behavioural Case Study
Aon Safdar, Mohamed Saadeldin
We study what happens when a single general-purpose large language model acts as the sole researcher on a long-horizon neural architecture design problem. The agent receives a scie…
cs.CV2026
CAViT -- Channel-Aware Vision Transformer for Dynamic Feature Fusion
Aon Safdar, Mohamed Saadeldin
Vision Transformers (ViTs) have demonstrated strong performance across a range of computer vision tasks by modeling long-range spatial interactions via self-attention. However, cha…
cs.CV2025
CoMViT: An Efficient Vision Backbone for Supervised Classification in Medical Imaging
Aon Safdar, Mohamed Saadeldin
Vision Transformers (ViTs) have demonstrated strong potential in medical imaging; however, their high computational demands and tendency to overfit on small datasets limit their ap…