Natural language processing research from GCC institutions, covering Arabic NLP, multilingual models, text classification, named entity recognition, and machine translation.
MBZUAI welcomed its second cohort of students for the Fall 2021 semester, totaling 74 students across master's and Ph.D. programs. The incoming class includes 41 students in Computer Vision, 24 in Machine Learning, and 9 in the inaugural Natural Language Processing program. The cohort represents 29 nationalities, including 10 UAE nationals, and includes graduates from universities such as Purdue, Edinburgh, and Khalifa University. Why it matters: This demonstrates MBZUAI's continued growth as a global AI research institution attracting international talent to Abu Dhabi.
An AI model from the University of New South Wales (UNSW) won the AI Eurovision Song Contest in 2020. Following this, UNSW researchers posed philosophical questions to an AI language model and found that respondents preferred some machine-generated answers over those from philosophers like the Dalai Lama. This raises the question of whether AI can outthink human philosophers, a topic explored through projects like Philosopher AI and attempts to emulate the human brain with neural networks. Why it matters: The exploration of AI's capacity for philosophical thought could revolutionize our understanding of intelligence and consciousness, with potential implications for AI ethics and the future of human-machine collaboration in intellectual fields within the Middle East and abroad.
MBZUAI students Mugariya Farooq and Sarah Al Barri created a machine learning framework that classifies plant diseases from images and predicts yield using data inputs. Their project won second place at the Agritech Hackathon organized by the Abu Dhabi Agriculture and Food Security Authority (ADAFSA). The algorithm boasts accuracy above 99% when tested against agricultural scientists. Why it matters: This work showcases AI's potential to revolutionize agriculture in the UAE and the broader MENA region by improving food security, reducing waste, and optimizing resource allocation.
MBZUAI student Karima Kadaoui is developing machine learning algorithms to help speech-impaired individuals communicate more easily. Her project aims to create an app that translates speech impediments into understandable language, facilitating communication with others and integration with voice-enabled technologies like Siri and Google Assistant. The AI-powered app could assist individuals with conditions such as strokes and cerebral palsy, who often struggle with muscle control affecting speech clarity. Why it matters: The research addresses a critical need for inclusive AI solutions, potentially improving the quality of life for speech-impaired individuals in the region and beyond.
MBZUAI hosted a virtual Student Opportunities Fair, connecting its AI students with UAE employers. 26 companies including ADNOC, Etihad, Huawei, and Majid Al Futtaim attended the fair. Students explored internships ranging from NLP to big data applications. Why it matters: The event highlights the growing demand for AI talent in the UAE and MBZUAI's role in developing a skilled workforce for the nation's AI ambitions.
MBZUAI's Associate Provost Mohsen Guizani and his co-authors won the IEEE ComSoc - CSIM Best Journal Paper Award for 2021 for their paper "Reliable Federated Learning for Mobile Networks." The award will be presented at the IEEE International Communications Conference in Seoul. The paper's findings are expected to improve the reliability of federated learning tasks in mobile networks. Why it matters: The award recognizes impactful research in federated learning, an area of growing importance for distributed AI applications, and highlights MBZUAI's increasing prominence in the field.
MBZUAI Visiting Professor Haiyan Huang is working on bridging biology and AI by incorporating domain knowledge into modeling frameworks. She combines statistical principles, AI tools, and domain expertise to develop scientifically informed and statistically grounded methods. Her work addresses the challenge of extracting meaningful signals from complex biological data.
The article from thenationalnews.com explores the premise that artificial intelligence is increasingly diminishing the role of English as the world's primary second language. It likely delves into how advanced AI translation and communication tools are enabling more direct interaction across linguistic barriers. The piece analyzes the potential societal and cultural implications of AI's growing linguistic capabilities. Why it matters: This discussion is significant for the Middle East as it touches on the future of language education, global communication access, and the preservation of regional languages in an AI-driven world.
Researchers proposed Utility-Aligned Embeddings (UAE), a new framework designed to enhance Retrieval-Augmented Generation (RAG) by merging the precision of LLM re-ranking with the efficiency of dense vector retrieval. UAE trains a bi-encoder to imitate an LLM utility distribution using a Utility-Modulated InfoNCE objective, injecting graded utility signals directly into the embedding space. On the QASPER benchmark, UAE improved retrieval Recall@1 by 30.59% and was over 180 times faster than efficient LLM re-ranking methods while preserving competitive performance. Why it matters: This approach offers a practical way to significantly improve the accuracy and speed of RAG systems by providing more reliable contexts at scale without heavy computational cost.
Researchers proposed Utility-Aligned Embeddings (UAE), a new framework to improve dense vector retrieval for Retrieval-Augmented Generation (RAG) by aligning it with LLM utility. UAE trains a bi-encoder to imitate an LLM's utility distribution, derived from perplexity reduction, using a Utility-Modulated InfoNCE objective. On the QASPER benchmark, UAE achieved a 30.59% improvement in Recall@1 and was over 180 times faster than efficient LLM re-ranking methods while preserving competitive performance. Why it matters: This approach offers a significant leap in RAG efficiency and accuracy, providing a method to align retrieval with generative utility without test-time LLM inference, which could enable more scalable and precise LLM applications.
John Giannandrea, Apple's head of artificial intelligence, has reportedly resigned from his position. This departure is cited amidst ongoing delays and challenges related to the development of Apple's Siri voice assistant and its new Apple Intelligence features. The news indicates a significant leadership change within the tech giant's critical AI division. Why it matters: This development, if confirmed, signifies a major shift in the leadership overseeing AI development at a global technology leader, potentially influencing the future direction and pace of its widely used AI products.
The HONOR Magic7 Pro smartphone is featured for its integration of artificial intelligence capabilities, according to a report in Gulf Business. The device reportedly leverages AI to enhance various user experiences, potentially across areas such as camera performance, system optimization, and user interface features. This highlights the ongoing trend of incorporating advanced AI functionalities into consumer electronics. Why it matters: The continuous emphasis on AI integration in mainstream consumer devices demonstrates the expanding reach of artificial intelligence into everyday technology used across the Middle East.
This research presents a post-hoc framework to explain, verify, and align semantic hierarchies within vision-language model (VLM) encoders like CLIP. The method involves agglomerative clustering of class centroids, naming internal nodes via dictionary matching, and quantifying plausibility against human ontologies. Findings across 13 VLMs and 4 datasets reveal that image encoders are more discriminative, while text encoders induce hierarchies better matching human taxonomies, showing a trade-off between zero-shot accuracy and ontological plausibility. Why it matters: This work provides critical insights into the internal organization of VLM embeddings, which is essential for improving their explainability, reliability, and alignment with human knowledge, leading to more trustworthy AI systems.
Associate Professor Anamaria Costache from the Norwegian University of Science and Technology (NTNU) will present a seminar on Fully Homomorphic Encryption (FHE). The talk will cover recent advancements in FHE, its mathematical foundations, and implementation results. It will also address remaining challenges in the field. Why it matters: FHE's growing importance is driven by Machine Learning as a Service and the increasing value of secure computation, though the seminar itself has no direct connection to the Middle East.
This article discusses distribution shifts in machine learning and the use of importance weighting methods to address them. Masashi Sugiyama from the University of Tokyo and RIKEN AIP presented recent advances in importance-based distribution shift adaptation methods. The talk covered joint importance-predictor estimation, dynamic importance weighting, and multistep class prior shift adaptation. Why it matters: Understanding and mitigating distribution shifts is crucial for deploying robust and reliable AI models in real-world scenarios within the GCC region and beyond.
VinAI Research presented research projects focused on advancing image generation and manipulation using GANs and Diffusion Models. The research aims to improve GANs regarding utility, coverage, and output consistency. For Diffusion Models, the work focuses on improving the models’ speed to approach real-time performance and prevent negative social impact of diffusion-based personalized text-to-image generation. Why it matters: This talk indicates ongoing research and development in generative AI in Southeast Asia, an area of growing interest globally.
Carlo Maj from the University of Marburg will discuss using polygenic modeling to analyze the genetic architecture of multifactorial traits. He will present how these approaches can be used to predict the genetically driven components of complex phenotypes. The talk highlights the potential of these methods to bridge genomic research and genetic epidemiology using biobank data. Why it matters: Such methods could improve disease risk assessment and advance personalized risk management in the region if applied to local biobanks or datasets.
A panel discussion hosted by MBZUAI in collaboration with the Manara Center for Coexistence and Dialogue addressed misinformation and its threat to elections. The talk covered the reasons behind the rise of misinformation, citizen perspectives, and the role of social media influencers. Two cases, the Indian general elections of 2024 and the upcoming US presidential elections in November 2024, were used to describe the contours of misinformation. Why it matters: Understanding the dynamics of misinformation, especially through social media influencers, is crucial for safeguarding democratic processes in the region and globally.
This article previews a talk by Gül Varol from Ecole des Ponts ParisTech on bridging natural language and 3D human motions. The talk will cover text-to-motion synthesis using generative models and text-to-motion retrieval models based on the ACTOR, TEMOS, TMR, TEACH, and SINC papers. Varol's research interests include video representation learning, human motion synthesis, and sign languages. Why it matters: Research in this area could enable more intuitive human-computer interaction and new applications in areas like virtual reality and robotics.
ParlaMint is a CLARIN ERIC flagship project focused on harmonizing multilingual corpora of parliamentary sessions. The newest version, published in October 2023, covers 26 European parliaments with linguistic annotations and machine translations to English. Maciej Ogrodniczuk, Head of Linguistic Engineering Group at the Institute of Computer Science, Polish Academy of Sciences, presented the project. Why it matters: While focused on European parliaments, the ParlaMint project provides a valuable model and infrastructure for creating comparable Arabic parliamentary corpora, which could enhance Arabic NLP research and political analysis in the Middle East.
A new mini-batch strategy using aggregated relational data is proposed to fit the mixed membership stochastic blockmodel (MMSB) to large networks. The method uses nodal information and stochastic gradients of bipartite graphs for scalable inference. The approach was applied to a citation network with over two million nodes and 25 million edges, capturing explainable structure. Why it matters: This research enables more efficient community detection in massive networks, which is crucial for analyzing complex relationships in various domains, but this article has no clear connection to the Middle East.
Machine learning (ML) algorithms use data to make decisions or predictions, improving over time as more data is provided. ML is a subset of AI, focused on models that learn from data, contrasting with rule-based systems. ML is superior in scenarios where rules are not exhaustive, such as medical scans, but rule-based systems and ML often complement each other. Why it matters: This overview clarifies the role of machine learning within the broader field of AI, highlighting its data-driven approach and its advantages over traditional rule-based systems in complex decision-making scenarios.
This article discusses a talk by Dr. David Xianfeng Gu at MBZUAI on gaining a geometric understanding of deep learning. The talk addresses questions such as what a DL system learns, how it learns, and how to improve the learning process. Dr. Gu is a professor at SUNY Stony Brook and affiliated with multiple prestigious institutions. Why it matters: Understanding the fundamentals of deep learning is crucial for advancing AI research and development in the region.
Francesco Orabona from Boston University, with a PhD from the University of Genova, researches online learning, optimization, and statistical learning theory. He previously worked at Yahoo Labs and Toyota Technological Institute at Chicago. MBZUAI hosted a panel discussion (topic not specified in provided text). Why it matters: Optimization algorithms are crucial for advancing machine learning and AI, and researchers like Orabona contribute to this field.
This article discusses methods for handling label noise in deep learning, including extracting confident examples and modeling label noise. Tongliang Liu from the University of Sydney presented these approaches. The talk aimed to provide participants with a basic understanding of learning with noisy labels. Why it matters: As AI models are increasingly trained on large, noisy datasets, techniques for robust learning become crucial for reliable real-world performance.
Iryna Gurevych from TU Darmstadt discussed challenges in using NLP for misinformation detection, highlighting the gap between current fact-checking research and real-world scenarios. Her team is working on detecting emerging misinformation topics and has constructed two corpora for fact checking using larger evidence documents. They are also collaborating with cognitive scientists to detect and respond to vaccine hesitancy using effective communication strategies. Why it matters: Addressing misinformation is crucial in the Middle East, especially regarding public health and socio-political issues, making advancements in NLP-based fact-checking highly relevant.
Dr. Munawar Hayat from Monash University gave a talk on the history of AI, recent breakthroughs in deep learning, and future research directions. The talk covered computer vision, NLP, autonomous driving, and reinforcement learning. Dr. Hayat also discussed the limitations of AI and challenges in the field. Why it matters: This lecture helps contextualize the rapid progress of AI for students in the region.
MBZUAI is hosting a public webinar on October 6 titled ‘Evolution of Artificial Intelligence: Past, Current and Future’. Dr. Munawar Hayat will discuss AI developments, breakthroughs, and future impact, highlighting deep learning, computer vision, NLP, autonomous driving, and reinforcement learning. The session will also cover AI limitations and future research directions. Why it matters: Public engagement initiatives like this webinar are crucial for fostering broader understanding and trust in AI technologies within the UAE community.
Professor Eran Segal presented The Human Phenotype Project, a longitudinal cohort study with over 10,000 participants. The project aims to identify molecular markers and develop prediction models for disease using deep profiling techniques including medical history, lifestyle, blood tests, and microbiome analysis. The study provides insights into drivers of obesity, diabetes, and heart disease, identifying novel markers at the microbiome, metabolite, and immune system level. Why it matters: Such large-scale phenotyping initiatives could inform personalized medicine approaches relevant to the Middle East's specific health challenges.
The provided article content is missing, preventing a factual summary of its details. Information regarding Fanar's initiative to advance Arabic presence in the digital space could not be extracted. Specific actions, partnerships, or funding related to this endeavor are not available. Why it matters: Without the article content, the significance of Fanar's potential contributions to Arabic digital presence cannot be evaluated.