MBZUAI researchers have developed MAviS, a new multimodal dataset, benchmark, and chatbot for fine-grained bird species recognition. MAviS includes images, audio, and text to help models identify subtle differences between species, especially rare and regional varieties. The related study was presented at EMNLP 2025 and selected as a "Senior Area Chair Highlight". Why it matters: This work addresses a key limitation in AI's ability to support biodiversity conservation and ecological monitoring in the region and globally.
A photography exhibition titled "KAUST, an Oasis for Birds" showcased the 240 bird species residing on the KAUST campus during the 2017 Winter Enrichment Program. The exhibition featured the work of Marios Mantzourogiannis and Brian James, highlighting common and rare bird species in KAUST's habitats. Mantzouroglannis noted that KAUST's cultural and avian diversity surprised him. Why it matters: The exhibition increased awareness of the rich biodiversity within KAUST and promoted engagement with nature and birding.
Professor Kimberly Smith from the University of Arkansas gave a lecture on ornithology to the KAUST community as part of the Enrichment in Fall Program. The lecture covered bird diversity, unique features such as feathers and bills, and various adaptations. Birds have developed unique features, including feathers, bills (or beaks), a flexible upper jaw and egg laying during reproduction. Why it matters: Such lectures can foster interest in biodiversity and conservation within the KAUST community, potentially leading to increased environmental awareness and research.
The paper introduces a framework for camel farm monitoring using a combination of automated annotation and fine-tune distillation. The Unified Auto-Annotation framework uses GroundingDINO and SAM to automatically annotate surveillance video data. The Fine-Tune Distillation framework then fine-tunes student models like YOLOv8, transferring knowledge from a larger teacher model, using data from Al-Marmoom Camel Farm in Dubai.
A public talk announcement features Professor Anil K. Jain from Michigan State University discussing biometric recognition. The talk will cover automated recognition of individuals based on biological and behavioral traits. It will also address challenges, research opportunities, and ongoing projects in Jain's lab related to biometrics. Why it matters: As biometric technologies become increasingly integrated into daily life across the Middle East, understanding their limitations and ethical implications is crucial for responsible development and deployment.
This paper proposes a machine learning method for early detection and classification of date fruit diseases, which are economically important to countries like Saudi Arabia. The method uses a hybrid feature extraction approach combining L*a*b color features, statistical features, and Discrete Wavelet Transform (DWT) texture features. Experiments using a dataset of 871 images achieved the highest average accuracy using Random Forest (RF), Multilayer Perceptron (MLP), Naïve Bayes (NB), and Fuzzy Decision Trees (FDT) classifiers.
This paper introduces a hybrid deep learning and machine learning pipeline for classifying construction and demolition waste. A dataset of 1,800 images from UAE construction sites was created, and deep features were extracted using a pre-trained Xception network. The combination of Xception features with machine learning classifiers achieved up to 99.5% accuracy, demonstrating state-of-the-art performance for debris identification.