Akhil Arora from EPFL presented a framework for AI-assisted knowledge navigation, focusing on understanding and enhancing human navigation on Wikipedia. The framework includes methods for modeling navigation patterns, identifying knowledge gaps, and assessing their causal impact. He also discussed applications beyond Wikipedia, such as multimodal knowledge navigation assistants and multilingual knowledge gap mitigation. Why it matters: This research has the potential to improve information systems by making online knowledge more accessible and navigable, especially for platforms like Wikipedia that serve as critical resources for global knowledge sharing.
MASARAT SA has developed Mubeen, a proprietary Arabic language model specializing in Arabic linguistics, Islamic studies, and cultural heritage. Mubeen was trained using native Arabic sources, including digitized historical manuscripts processed via a proprietary Arabic OCR engine. The model employs a Practical Closure Architecture to improve user intent understanding and provide decisive guidance. Why it matters: Mubeen addresses the utility gap in current Arabic LLMs by focusing on native Arabic data and cultural authenticity, which is critical for heritage preservation and alignment with Saudi Vision 2030.
This paper presents six experiments evaluating personalization and user tracking in web search engine results. The experiments involve comparing search results based on VPN location (including UAE vs others), logged-in status, network type, search engine, browser, and trained Google accounts. The study measures total hits, first hit, and correlation between hits to identify patterns of personalization. Why it matters: The findings shed light on the extent of filter bubble effects and potential biases in search results for users in the UAE and globally.
This article discusses retrieval augmentation in text generation, where information retrieved from an external source is used to condition predictions. It references recent work on retrieval-augmented image captioning, showing that model size can be greatly reduced when training data is available through retrieval. The author intends to continue this work focusing on the intersection of retrieval augmentation and in-context learning, and controllable image captioning for language learning materials. Why it matters: This research direction has the potential to improve transfer learning in vision-language models, which could be especially relevant for downstream applications in Arabic NLP and multimodal tasks.
This paper introduces a mutually-regularized dual collaborative variational auto-encoder (MD-CVAE) for recommendation systems, addressing the limitations of user-oriented auto-encoders (UAEs) in handling sparse ratings and new items. MD-CVAE integrates item content and user ratings within a variational framework, regularizing UAE weights with item content to avoid non-optimal convergence. A symmetric inference strategy eliminates the need for retraining when introducing new items, enhancing efficiency in dynamic recommendation scenarios. Why it matters: The MD-CVAE approach offers a practical solution for improving recommendation accuracy and efficiency, especially in scenarios with data sparsity and frequent item updates, relevant to e-commerce and content platforms in the Middle East.
Justice Connect, an Australian charity, collaborated with MBZUAI's Prof. Timothy Baldwin to improve their legal intake tool using NLP. The tool helps route legal requests, but users struggled to identify the relevant area of law, leading to delays and frustration. By applying NLP, the collaboration aims to help users more easily navigate the tool and access appropriate legal resources. Why it matters: This project demonstrates how NLP can be applied to improve access to justice and address unmet legal needs, particularly for those unfamiliar with legal terminology.
A new paper at ICCV 2025, co-authored by MBZUAI Ph.D. student Dmitry Demidov, introduces Dense-WebVid-CoVR, a 1.6-million sample benchmark for composed video retrieval (CoVR). The benchmark features longer, context-rich descriptions and modification texts, generated using Gemini Pro and GPT-4o, with manual verification. The paper also presents a unified fusion approach that jointly reasons across video and text inputs, improving performance on fine-grained edit details. Why it matters: This work advances video search capabilities by enabling more human-like queries, which is crucial for creative and analytic workflows that require nuanced video retrieval.