3 papers
cs.CL2026
Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG
Saadeldine Eletter, Owais Aijaz, Preslav Nakov
Multimodal retrieval-augmented generation (RAG) is often evaluated with clean evidence, yet real retrieval can return topically relevant but unreliable content: false text and misl…
cs.CL2026
UrduMMLU: A Massive Multitask Benchmark for Urdu Language Understanding
Ahmer Tabassum, Sarfraz Ahmad, Hasan Iqbal +3
Meaningful multilingual evaluation must test models in the target language and educational context. Urdu, spoken by more than 230 million people, lacks a broad MMLU-style benchmark…
math.NA2024
Analysis of Different Algorithmic Design Techniques for Seam Carving
Owais Aijaz, Syed Muhammad Ali, Yousuf Uyghur
Seam carving, a content-aware image resizing technique, has garnered significant attention for its ability to resize images while preserving important content. In this paper, we co…