collaborators

20 papers

cs.CV2026

The Professor: Multi-Teacher Unsupervised Prompt Distillation for Vision-Language Models

Ahmad Algadhi, Ahmed Alzuhair, Omar Alkhulaif +1

Prompt distillation compresses large vision-language models (VLMs) such as CLIP into lightweight student models by matching teacher predictions on unlabeled domain images. PromptKD…

cs.AI2026

Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints

Omar Alshahrani, Muzammil Behzad

AI systems are being deployed across medical imaging faster than their failure modes are understood. At this point in time, the failure of greatest clinical concern is hallucinatio…

cs.CV2026

Spatio-Semantic Expert Routing Architecture with Mixture-of-Experts for Referring Image Segmentation

Alaa Dalaq, Muzammil Behzad

Referring image segmentation aims to produce a pixel-level mask for the image region described by a natural-language expression. Although pretrained vision-language models have imp…

cs.CV2026

XAI-CLIP: ROI-Guided Perturbation Framework for Explainable Medical Image Segmentation in Multimodal Vision-Language Models

Thuraya Alzubaidi, Sana Ammar, Maryam Alsharqi +2

Medical image segmentation is a critical component of clinical workflows, enabling accurate diagnosis, treatment planning, and disease monitoring. However, despite the superior per…

cs.CV2025

SwinTF3D: A Lightweight Multimodal Fusion Approach for Text-Guided 3D Medical Image Segmentation

Hasan Faraz Khan, Noor Fatima, Muzammil Behzad

The recent integration of artificial intelligence into medical imaging has driven remarkable advances in automated organ segmentation. However, most existing 3D segmentation framew…

cs.CV2025

Attack-Aware Deepfake Detection under Counter-Forensic Manipulations

Noor Fatima, Hasan Faraz Khan, Muzammil Behzad

This work presents an attack-aware deepfake and image-forensics detector designed for robustness, well-calibrated probabilities, and transparent evidence under realistic deployment…