collaborators

6 papers

cs.LG2026

PILOT: Policy-Informed Learned Optimization for Adaptive Deep Network Training

Sattam Altuuaim, Lama Ayash, Muhammad Mubashar +1

Despite the central role of optimization in deep learning, most optimizers rely on update structures whose functional form is fixed before training begins. This static design can l…

cs.CV2026

GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs

Mohamed Eltahir, Lama Ayash, Ali Habibullah +2

Long-video understanding in VLMs is bottlenecked by a single monolithic forward pass over thousands of frames at quadratic attention cost. A common mitigation is to first select a…

cs.CV2026

VideoAtlas: Navigating Long-Form Video in Logarithmic Compute

Mohamed Eltahir, Ali Habibullah, Yazan Alshoibi +3

Extending language models to video introduces two challenges: representation, where existing methods rely on lossy approximations, and long-context, where caption- or agent-based p…

cs.CV2025

Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers

Mohamed Eltahir, Ali Habibullah, Lama Ayash +2

In the retrieval domain, candidates' fusion from heterogeneous retrievers is a long-standing challenge, particularly for complex, multi-modal data such as videos. While typical fus…

cs.CL2025

AraHealthQA 2025: The First Shared Task on Arabic Health Question Answering

Hassan Alhuzali, Walid Al-Eisawi, Muhammad Abdul-Mageed +9

We introduce AraHealthQA 2025, the Comprehensive Arabic Health Question Answering Shared Task, held in conjunction with ArabicNLP 2025 (co-located with EMNLP 2025). This shared tas…

cs.CL2025

SaudiCulture: A Benchmark for Evaluating Large Language Models Cultural Competence within Saudi Arabia

Lama Ayash, Hassan Alhuzali, Ashwag Alasmari +1

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing; however, they often struggle to accurately capture and reflect cultural nuanc…