MBZUAI researchers created Open CaptchaWorld, a new benchmark to test AI agents on solving CAPTCHAs. The benchmark includes 20 modern CAPTCHA types that require perception, reasoning, and interactive actions within a browser. While humans achieve 93.3% accuracy, the best AI agent only reaches 40% on the benchmark. Why it matters: This research highlights a critical gap in current AI agent capabilities, as CAPTCHAs are gatekeepers to high-value web actions like e-commerce and secure logins.
MBZUAI researchers are presenting a new approach to open-world object detection at the AAAI conference. The method enables machines to distinguish between known and unknown objects in images, and then learn to classify the unknown objects. PhD student Sahal Shaji Mullappilly is the lead author of the study, titled "Semi-Supervised Open-World Detection". Why it matters: This research addresses a key limitation in current object detection systems, allowing for more adaptable and robust AI in real-world applications.
Researchers from Alexandria University introduce AlexU-Word, a new dataset for offline Arabic handwriting recognition. The dataset contains 25,114 samples of 109 unique Arabic words, covering all letter shapes, collected from 907 writers. The dataset is designed for closed-vocabulary word recognition and to support segmented letter recognition-based systems. Why it matters: This dataset can help advance Arabic handwriting recognition systems, addressing a need for high-quality Arabic datasets in NLP research.
MBZUAI researchers introduce DuwatBench, a new benchmark for multimodal understanding of Arabic calligraphy. The dataset contains 1,272 samples across six calligraphic styles with detailed annotations to evaluate visual-text alignment. Evaluation of 13 multimodal models reveals challenges in processing calligraphic variations and artistic distortions, highlighting the need for culturally grounded AI research.
MBZUAI researchers release OpenFactCheck, a unified framework to evaluate the factual accuracy of large language models. The framework includes modules for response evaluation, LLM evaluation, and fact-checker evaluation. OpenFactCheck is available as an open-source Python library, a web service, and via GitHub.
MBZUAI's Institute of Foundation Models has released K2, a 70-billion-parameter, reasoning-centric foundation model. K2 is designed to be fully inspectable, with open weights, training code, data composition, mid-training checkpoints, and evaluation harnesses. K2 outperforms Qwen2.5-72B and approaches the performance of Qwen3-235B. Why it matters: This release promotes transparency and reproducibility in AI development, providing researchers with the resources needed to study, adapt, and build upon a strong foundation model.