Researchers have introduced BloomBench, a new cognitively human-grounded, bilingual (English-Arabic) multimodal benchmark for Vision-Language Models (VLMs), as part of the Almieyar benchmarking series. Grounded in Bloom's Taxonomy, it systematically evaluates six levels of cognition—Remember, Understand, Apply, Analyze, Evaluate, Create—through carefully designed image-question-answer tasks. A comprehensive study using BloomBench revealed that state-of-the-art VLMs exhibit strong semantic understanding but struggle significantly with factual recall and creative synthesis, alongside a critical performance gap between Arabic and English. Why it matters: This benchmark provides a crucial tool for diagnosing cognitive weaknesses in current VLMs and lays the groundwork for developing more cognitively aligned and inclusive multimodal AI, particularly for cross-lingual applications.
A new study compares vision-language models (VLMs) to YOLOv8 for wastewater treatment plant (WWTP) identification in satellite imagery across the MENA region. VLMs like Gemma-3 demonstrate superior zero-shot performance compared to YOLOv8, trained on a dataset of 83,566 satellite images from Egypt, Saudi Arabia, and UAE. The research suggests VLMs offer a scalable, annotation-free alternative for remote sensing of WWTPs.
This paper introduces MOTOR, a multimodal retrieval and re-ranking approach for medical visual question answering (MedVQA) that uses grounded captions and optimal transport to capture relationships between queries and retrieved context, leveraging both textual and visual information. MOTOR identifies clinically relevant contexts to augment VLM input, achieving higher accuracy on MedVQA datasets. Empirical analysis shows MOTOR outperforms state-of-the-art methods by an average of 6.45%.
MBZUAI researchers introduce UniMed-CLIP, a unified Vision-Language Model (VLM) for diverse medical imaging modalities, trained on the new large-scale, open-source UniMed dataset. UniMed comprises over 5.3 million image-text pairs across six modalities: X-ray, CT, MRI, Ultrasound, Pathology, and Fundus, created using LLMs to transform classification datasets into image-text formats. UniMed-CLIP significantly outperforms existing generalist VLMs and matches modality-specific medical VLMs in zero-shot evaluations, improving over BiomedCLIP by +12.61 on average across 21 datasets while using 3x less training data.
Researchers introduce PALO, a polyglot large multimodal model with visual reasoning capabilities in 10 major languages including Arabic. A semi-automated translation approach was used to adapt the multimodal instruction dataset from English to the target languages. The models are trained across three scales (1.7B, 7B and 13B parameters) and a multilingual multimodal benchmark is proposed for evaluation.
Researchers at MBZUAI have developed GeoChat, a new vision-language model (VLM) specifically designed for remote sensing imagery. GeoChat addresses the limitations of general-domain VLMs in accurately interpreting high-resolution remote sensing data, offering both image-level and region-specific dialogue capabilities. The model is trained on a novel remote sensing multimodal instruction-following dataset and demonstrates strong zero-shot performance across tasks like image captioning and visual question answering.
MBZUAI researchers introduce XrayGPT, a conversational medical vision-language model for analyzing chest radiographs and answering open-ended questions. The model aligns a medical visual encoder (MedClip) with a fine-tuned large language model (Vicuna) using a linear transformation. To enhance performance, the LLM was fine-tuned using 217k interactive summaries generated from radiology reports.
A new paper from MBZUAI introduces JEEM, a benchmark dataset for evaluating vision-language models on their understanding of images grounded in four Arabic-speaking societies (Jordan, UAE, Egypt, and Morocco) and their ability to use local dialects. The dataset comprises 2,178 images and 10,890 question-answer pairs reflecting everyday life and culturally specific scenes. Evaluation of several Arabic-capable models (Maya, PALO, Peacock, AIN, AyaV) and GPT-4o revealed that while models can generate fluent language, they struggle with genuine understanding, consistency, and relevance, especially when cultural context is important. Why it matters: This research highlights the challenges of building AI systems that can truly understand and interact with diverse cultures, emphasizing the need for culturally grounded datasets and evaluation metrics.