MBZUAI researchers presented two studies at NAACL 2025 concerning how LLMs understand cultural differences, with one study winning the SAC award. One study, titled "Reading between the lines: Can LLMs identify cross-cultural communication gaps," assesses GPT-4o's ability to identify cultural references in Goodreads book reviews. The researchers created a benchmark dataset using annotations from 50 evaluators across different cultures to measure the LLM's ability to identify culture-specific items (CSIs). Why it matters: Improving LLMs' cross-cultural understanding is crucial for ensuring these models can be used effectively and equitably across diverse global contexts.
Maryam Ahmed Hassani, an MBZUAI graduate and head of trends and innovation at Abu Dhabi’s Early Childhood Authority (ECA), is integrating AI into early childhood development to create efficient and human-focused systems. She aims to develop tools that personalize support for parents and predict developmental risks early on. Hassani also co-founded Zealous, an AI startup focused on AI code generation and testing, launching AI-native products including an AI-automated tester for websites and web apps. Why it matters: This highlights the growing application of AI in public sector challenges within the UAE, specifically in early childhood development and software development.
MBZUAI researchers found that only 5.7% of music in existing datasets used to train generative music systems comes from non-Western genres. They discovered that 94% of the music represented Western music, while Africa, the Middle East, and South Asia accounted for only 0.3%, 0.4%, and 0.9% respectively. The team also tested whether parameter-efficient fine-tuning with adapters could improve generative music systems on underrepresented styles, presenting their findings at NAACL. Why it matters: This research highlights the critical need for more diverse datasets in AI music generation to better serve global musical traditions and audiences.
MBZUAI researchers developed AnomalyGen, a framework using foundation models to help household robots anticipate and react to dangerous scenarios. The system uses collaborative agents to brainstorm hazards, recreates scenarios in a 3D simulation, and develops mitigation methods. AnomalyGen will be presented at the upcoming NAACL conference. Why it matters: This research advances the development of trustworthy AI for real-world applications, specifically enabling robots to proactively ensure safety in home environments.
Dr. Farida Al Hosani, a UAE public health leader and MBZUAI Executive Program graduate, has been at the forefront of the nation’s public health strategy, specializing in infectious diseases. She emphasizes the growing importance of AI in healthcare, particularly in areas like early detection, drug discovery, and public health strategies. Al Hosani has worked on several AI initiatives, including building algorithms and predictive modeling systems to bridge gaps in human health, especially in prevention. Why it matters: This highlights the increasing role of AI in transforming healthcare in the UAE, with public health leaders leveraging AI tools to improve disease prevention and treatment.
MBZUAI graduate Svetlana Maslenkova worked with Assistant Professor Mohammad Yaqub on a project focused on the earlier detection of kidney failure using tabular data. Maslenkova's master's thesis involved predicting Acute Kidney Injury (AKI) using Electronic Health Records (EHR), specifically the MIMIC-IV v2.0 database. She found that patient weight distribution was a factor in the severity of kidney failure. Why it matters: This research highlights the potential of AI and machine learning to improve healthcare outcomes through the analysis of often-overlooked tabular data in electronic health records.
MBZUAI is hosting the Augmented Humans International Conference 2025 in the Middle East for the first time, in cooperation with the ACM. The conference focuses on physical, cognitive, and perceptual augmentations of humans through digital technologies. 30 papers were selected from 77 submissions, with participation from researchers from institutions like MIT Media Lab and the University of Tokyo. Why it matters: This event underscores the UAE's commitment to AI research and human-computer interaction, fostering collaboration and driving progress in augmentation technologies for societal benefit.
AI's energy consumption is a growing concern, with AI, data centers, and cryptocurrency consuming nearly 2% of the world's energy in 2022, potentially doubling by 2026. Training an LLM like GPT-3 uses the equivalent energy of 130 homes per year, and AI tasks consume 33 times more energy than task-specific software. MBZUAI's computer science department, led by Xiaosong Ma, is researching energy efficiency in AI hardware to address this problem. Why it matters: As AI adoption accelerates in the GCC, energy-efficient AI hardware and algorithms are critical for sustainable development and reducing carbon emissions in the region.
MBZUAI's executive programs (MEP and MEP-A) have trained nearly 240 senior leaders from the UAE's public and private sectors to implement AI solutions. Cohort six of the MEP begins in April, while the MEP-A will commence later in the year. The programs, taught by instructors from MBZUAI, UC Berkeley, Oxford, Harvard, and MIT, cover AI fundamentals, industry applications, strategy, policymaking, and ethics. Why it matters: These programs aim to empower leaders to contribute to the UAE's growing AI ecosystem and promote ethically-rooted innovation, aligning with the UAE's national AI strategy.
MBZUAI's Provost, Tim Baldwin, provides six predictions for AI in 2025, highlighting the rise of agentic AI systems capable of performing actions on behalf of users. He notes the recent release of open-weight reasoning models like DeepSeek's R1 and OpenAI's o3-mini, emphasizing the dynamic nature of the field. Baldwin stresses the potential benefits of agentic AI, such as automating complex tasks like travel planning, while also cautioning about the need for careful deployment due to unforeseen outcomes. Why it matters: The predictions provide insight into the near-term trajectory of AI development and deployment, particularly regarding AI agents, and highlights the role of a UAE university in shaping the discussion around AI innovation.
Søren Brunak presented deep learning approaches for analyzing disease trajectories using data from 7-10 million patients in Denmark and the USA. The models predict future outcomes like mortality and specific diagnoses, such as pancreatic cancer, using 15-40 years of patient data. Disease trajectories and explainable AI can generate hypotheses for molecular-level investigations into causal aspects of disease progression. Why it matters: This research demonstrates the potential of large-scale patient data and AI to improve disease prediction and generate hypotheses for further investigation into disease mechanisms relevant to regional healthcare systems.
Giovanni Puccetti from ISTI-CNR presented research on linguistic probing of language models like BERT and RoBERTa. The research investigates the ability of these models to encode linguistic properties, linking this ability to outlier parameters. Preliminary work on fine-tuning LLMs in Italian and detecting synthetic news generation was also presented. Why it matters: Understanding the inner workings and linguistic capabilities of LLMs is crucial for improving their reliability and adapting them to diverse languages like Arabic.
MBZUAI hosted a panel discussion in collaboration with the Manara Center for Coexistence and Dialogue. The discussion focused on the intersection of AI and medical image computing. Jiebo Luo, a professor at the University of Rochester, discussed his work on applying AI to healthcare, including moving beyond classification to semantic description and expanding use from hospitals to home telemedicine. Why it matters: This highlights the increasing focus on AI applications in healthcare within the Middle East, particularly at institutions like MBZUAI, which are fostering discussions on the ethical and practical implications of AI in medicine.
Niket Tandon from the Allen Institute for AI presented a talk at MBZUAI on enabling large language models to focus on human needs and continuously learn from interactions. He proposed a memory architecture inspired by the theory of recursive reminding to guide models in avoiding past errors. The talk addressed who to ask, what to ask, when to ask and how to apply the obtained guidance. Why it matters: The research explores how to align LLMs with human feedback, a key challenge for practical and ethical AI deployment.
This article discusses a talk by Houda Elmimouni on designing technology with user values in mind, using privacy and robotic telepresence research as examples. The first study examines privacy practices, while the second focuses on values in robotic telepresence in classrooms. Elmimouni highlights the importance of aligning technology design with social values like privacy. Why it matters: The emphasis on user-centered design and social values provides insights applicable to AI development in the Middle East, where cultural context and ethical considerations are paramount.
Thamar Solorio from the University of Houston presented preliminary work on multimodal representation learning for detecting objectionable content in videos at MBZUAI. The research investigates two multimodal pretraining mechanisms, finding contrastive learning more effective than unimodal representation prediction. The study also assesses the value of common multimodal corpora for this task. Why it matters: This research contributes to the development of AI techniques for content moderation, an important issue for online platforms in the Middle East and globally.
A talk will present two projects related to the use of NLP for estimating a client’s depression severity and well-being. The first project examines emotional coherence between the subjective experience of emotions and emotion expression in therapy using transformer-based emotion recognition models. The second project proposes a semantic pipeline to study depression severity in individuals based on their social media posts by exploring different aggregation methods to answer one of four Beck Depression Inventory (BDI) options per symptom. Why it matters: This research explores how NLP techniques can be applied to mental health assessment, potentially offering new tools for diagnosis and treatment monitoring.
Zeerak Talat, an independent scholar, gave a talk at MBZUAI on automated content moderation and the impacts of machine learning on society. Talat's research considers how machine learning interacts with and impacts societies through content moderation technologies, drawing from NLP, privacy preserving machine learning, science and technology studies, decolonize studies, and media studies. The talk highlighted research areas that can afford productive directions for the meeting between machine learning and society. Why it matters: The talk contributes to the discussion of ethical AI development and deployment in the region, particularly regarding content moderation and its societal impacts.
A new content improvement system has been developed to address issues of randomness and incorrectness in text generated by deep learning models like GPT-3. The system uses text mining to identify correct sentences and employs syntactic/semantic generalization to substitute problematic elements. The system can substantially improve the factual correctness and meaningfulness of raw content. Why it matters: Improving the quality of automatically generated content is crucial for ensuring reliability and trustworthiness across various AI applications.
NYU and NYU Abu Dhabi researchers are working on user-centric gender rewriting in NLP, especially for Arabic. They are building an Arabic Parallel Gender Corpus and developing models for gender rewriting tasks. The work aims to address representational harms caused by NLP systems that don't account for user preferences regarding grammatical gender. Why it matters: This research promotes fairness and inclusivity in Arabic NLP by enabling systems to generate gender-specific outputs based on user preferences, mitigating biases present in training data.
Project LITMUS explores predicting cross-lingual transfer accuracy in multilingual language models, even without test data in target languages. The goal is to estimate model performance in low-resource languages and optimize training data for desired cross-lingual performance. This research aims to identify factors influencing cross-lingual transfer, contributing to linguistically fair MMLMs. Why it matters: Improving cross-lingual transfer is vital for creating more equitable and effective multilingual AI systems, especially for languages with limited resources.
A partner at Oblon, Stefan Uwe Koschmieder, explained key points for patenting software and AI inventions. Koschmieder works with GCC universities on IP programs and advises foreign clients on IP portfolio management. He also lectured at Freie Universität Berlin on Intellectual Property. Why it matters: As software and AI innovation grows in the GCC, understanding patent law is increasingly important for protecting intellectual property and fostering local innovation.
Saber Salehkaleybar from EPFL presented a talk on causal discovery, focusing on learning causal relationships from observational data and through interventions. He discussed an approximation algorithm for experiment design under budget constraints, with applications in gene-regulatory networks. The talk also covered improvements to reduce the computational complexity of experiment design algorithms. Why it matters: Causal AI systems can lead to more intelligent decision-making in various fields.
This article discusses the use of artificial intelligence in precision oncology, particularly in understanding individual tumor mechanisms and aiding clinical decision-making. Dr. Xinghua Lu, with extensive experience in medicine and biomedical informatics, will present research on individualized Bayesian causal inference methods for investigating oncogenic mechanisms. These methods aim to provide clinical decision support at the cellular, tumor, and patient levels. Why it matters: AI-driven precision oncology can enable more personalized and effective cancer treatments, improving patient outcomes in the region and globally.
A talk at MBZUAI discussed federated learning, a distributed machine learning approach training models over devices while keeping data localized. The presentation covered a straggler-resilient federated learning scheme using adaptive node participation to tackle system heterogeneity. It also presented a robust optimization formulation for addressing data heterogeneity and a new algorithm for personalizing learned models. Why it matters: Federated learning is crucial for AI applications involving decentralized data sources, and research on improving its robustness and personalization is essential for real-world deployment in the region.
EURECOM researchers developed data-driven verification methods using structured datasets to assess statistical and property claims. The approach translates text claims into SQL queries on relational databases for statistical claims. For property claims, they use knowledge graphs to verify claims and generate explanations. Why it matters: The methods aim to support fact-checkers by efficiently labeling claims with interpretable explanations, potentially combating misinformation in the region and beyond.
Dr. Teresa Lynn from Dublin City University (DCU) discussed the challenges in developing NLP tools for Irish, a low-resource language facing digital extinction. She highlighted the lack of speech and language applications and fundamental language resources for Irish. Lynn also mentioned her work at DCU on the GaelTech project and her involvement in the European Language Equality project. Why it matters: The development of NLP tools for low-resource languages like Irish is crucial for preserving linguistic diversity and preventing digital marginalization in the AI era.
A research talk was given on privacy and security issues in speech processing, highlighting the unique privacy challenges due to the biometric information embedded in speech. The talk covered the legal landscape, proposed solutions like cryptographic and hashing-based methods, and adversarial processing techniques. Dr. Bhiksha Raj from Carnegie Mellon University, an expert in speech and audio processing, delivered the talk. Why it matters: As speech-based interfaces become more prevalent in the Middle East, understanding and addressing the associated privacy risks is crucial for ethical AI development and deployment.
A report discusses using AI to optimize healthcare delivery across the entire medical process cycle, including pre-hospital screening, in-hospital treatment, and post-hospital rehabilitation. It considers optimal management of workflow, medical resources, and comprehensive healthcare coverage. Dr. Jingshan Li from Tsinghua University is the author, with extensive publications and experience in production and healthcare systems. Why it matters: AI-driven improvements to healthcare processes could lead to better resource allocation and enhanced patient outcomes across the GCC region.
This article discusses the reliability of Deep Neural Networks (DNNs) and their hardware platforms, especially regarding soft errors caused by cosmic rays. It highlights that while DNNs are robust against bit flips, errors can still lead to miscalculations in AI accelerators. The talk, led by Prof. Masanori Hashimoto from Kyoto University, will cover identifying vulnerabilities in neural networks and reliability exploration of AI accelerators for edge computing. Why it matters: As DNNs are deployed in safety-critical applications in the region, ensuring the reliability of AI hardware is crucial for safe and trustworthy operation.
A professor from Nanyang Technological University (NTU), Singapore gave a talk at MBZUAI about "Just-Noticeable Difference (JND)" models in visual intelligence. The talk covered visual JND models, research and applications, and future opportunities for JND modeling. JND can help tackle big data challenges with limited resources by focusing on user-centric and green systems. Why it matters: Exploring JND could lead to advancements in AI applications related to visual signal processing, image synthesis, and generative AI in the region.
MBZUAI student Ahmed AlShamsi and his team won the Gulf Hackathon for Cybersecurity in Oman for their Secure+ platform. Secure+ uses AI to detect phishing links, identify the source, and provide users with statistics about malicious emails. The platform allows users to browse links safely on the Secure+ server. Why it matters: The award highlights the growing entrepreneurial ecosystem around cybersecurity and AI in the GCC, fostered by initiatives like CyberE71 and guidance from leaders like Dr. Mohamed Al Kuwaiti.
This research introduces a novel method using the Lateral Accretive Hybrid Network (LEARNet) to capture and analyze micro-expressions for mental health applications. The method refines both broad and subtle facial cues to detect mental health conditions like anxiety or depression. The authors also propose a neural architecture search (NAS) strategy to design a compact CNN for micro-expression recognition, improving performance and resource use. Why it matters: By integrating micro-emotion recognition with mental health estimation, the approach enables more accurate and early detection of emotional and mental health issues, potentially leading to improved well-being.
A talk explores multimodal approaches inspired by user behavior for detecting deepfakes, considering user studies on multicultural deepfakes and the ACM Multimedia 2024 benchmark. The research leverages insights into how different audiences perceive manipulated media. Abhinav Dhall from Flinders University will present findings and future directions in deepfake analysis at MBZUAI. Why it matters: Addressing deepfakes is crucial for maintaining trust in digital content, especially with the increasing sophistication and accessibility of AI-driven manipulation tools.
Hassan Sajjad from Dalhousie University presented research on exploring the latent space of AI models to assess their safety and trustworthiness. He discussed use cases where analyzing latent space helps understand the robustness-generalization tradeoff in adversarial training and evaluate language comprehension. Sajjad's work aims to build better AI models and increase trust in their capabilities by looking at model internals. Why it matters: Intrinsic evaluation of model internals will become important to improving AI safety and robustness.
Mykel Kochenderfer from Stanford University gave a talk on building robust decision-making systems for autonomous systems, highlighting the challenges of balancing safety and efficiency in uncertain environments. The talk addressed computational tractability and establishing trust in these systems. Kochenderfer outlined methodologies and research applications for building safer systems, drawing from his work on air traffic control, unmanned aircraft, and automated driving. Why it matters: The development of safe and reliable autonomous systems is crucial for various applications in the region, and insights from experts like Kochenderfer can guide research and development efforts at institutions like MBZUAI.
Eduardo da Veiga Beltrame, bioinformatics lead at ImYoo (a Caltech spinout), presented on scalable methods for single-cell omics data analysis, including kallisto|bustools and scvi-tools. He highlighted their use in ImYoo's decentralized longitudinal study on Inflammatory Bowel Disease (IBD), where patients self-collect capillary blood samples. Beltrame also discussed his research on STEM education programs in Brazil as a visiting scholar at UC Berkeley. Why it matters: This highlights the growing trend of decentralized clinical studies leveraging advanced single-cell technologies for precision medicine, showcasing the potential of remote data collection and analysis in understanding complex diseases.
MBZUAI's Dr. Artem Shelmanov is working on uncertainty quantification (UQ) methods for generative LLMs to detect unreliable generations. He aims to address the issue of LLMs fabricating facts, often called "hallucinating", without clear indicators of veracity. He systemizes existing UQ efforts, discusses caveats, and suggests novel techniques for safer LLM use. Why it matters: Improving the reliability of LLMs is crucial for responsible AI deployment in the region, especially in sensitive applications.
Dr. Jindong Wang from Microsoft Research Asia gave a talk at MBZUAI about the limitations of large foundation models, including adapting to real-world unpredictability and security concerns. He also discussed the need for interdisciplinary collaboration to evaluate the benefits and risks of these models. Dr. Wang shared his research and insights on how to harness the power of large foundation models while addressing their constraints and fostering responsible AI integration. Why it matters: This highlights MBZUAI's role in hosting discussions about responsible AI development and the challenges of deploying foundation models.
Iryna Gurevych from TU Darmstadt presented research on using large language models for real-world fact-checking, focusing on dismantling misleading narratives from misinterpreted scientific publications and detecting misinformation via visual content. The research aims to explain why a false claim was believed, why it is false, and why the alternative is correct. Why it matters: Addressing misinformation, especially when supported by seemingly credible sources, is critical for public health, conflict resolution, and maintaining trust in institutions in the Middle East and globally.
Adel Bibi, a KAUST alumnus and researcher at the University of Oxford, presented his research on AI safety, covering robustness, alignment, and fairness of LLMs. The research addresses challenges in AI systems, alignment issues, and fairness across languages in common tokenizers. Bibi's work includes instruction prefix tuning and its theoretical limitations towards alignment. Why it matters: This research from a leading researcher highlights the importance of addressing safety concerns in LLMs, particularly regarding alignment and fairness in the Arabic language.
Xiuying Chen from KAUST presented her work on improving the trustworthiness of AI-generated text, focusing on accuracy and robustness. Her research analyzes causes of hallucination in language models related to semantic understanding and neglect of input knowledge, and proposes solutions. She also demonstrated vulnerabilities of language models to noise and enhances robustness using augmentation techniques. Why it matters: Improving the reliability of AI-generated text is crucial for its deployment in sensitive domains like healthcare and scientific discovery, where accuracy is paramount.
Zeerak Talat, an independent scholar, gave a talk at MBZUAI on ethical concerns in NLP. The talk covered disparities in research on biases in NLP, performance differences based on socio-economic language variations, and risks of malicious reuse of NLP tools. Talat's research considers how machine learning interacts with and impacts societies through content moderation technologies. Why it matters: As NLP technologies become more integrated into society, understanding and addressing their potential harms and ethical implications is crucial for responsible development and deployment in the region and beyond.
Researchers are exploring methods for evaluating the outcome of actions using off-policy observations where the context is noisy or anonymized. They employ proxy causal learning, using two noisy views of the context to recover the average causal effect of an action without explicitly modeling the hidden context. The implementation uses learned neural net representations for both action and context, and demonstrates outperformance compared to an autoencoder-based alternative. Why it matters: This research addresses a key challenge in applying AI in real-world scenarios where data privacy or bandwidth limitations necessitate working with noisy or anonymized data.
Dr. Youcheng Sun from the University of Manchester presented on ensuring the trustworthiness of AI systems using formal verification, software testing, and explainable AI. He discussed applying these techniques to challenges like copyright protection for AI models. Dr. Sun's research has been funded by organizations including Google, Ethereum Foundation, and the UK’s Defence Science and Technology Laboratory. Why it matters: As AI adoption grows in the GCC, ensuring the safety, dependability, and trustworthiness of these systems is crucial for public trust and responsible innovation.
This article discusses the increasing concerns about the interpretability of large deep learning models. It highlights a talk by Danish Pruthi, an Assistant Professor at the Indian Institute of Science (IISc), Bangalore, who presented a framework to quantify the value of explanations and the need for holistic model evaluation. Pruthi's talk touched on geographically representative artifacts from text-to-image models and how well conversational LLMs challenge false assumptions. Why it matters: Addressing interpretability and evaluation is crucial for building trustworthy and reliable AI systems, particularly in sensitive applications within the Middle East and globally.
Dr. Yali Du from King's College London will give a presentation on learning to cooperate in multi-agent systems. Her research focuses on enabling cooperative and responsible behavior in machines using reinforcement learning and foundation models. She will discuss enhancing collaboration within social contexts, fostering human-AI coordination, and achieving scalable alignment. Why it matters: This highlights the growing importance of research into multi-agent systems and human-AI interaction, crucial for developing AI that integrates effectively and ethically into society.
Liangming Pan from UCSB presented research on building reliable generative AI agents by integrating symbolic representations with LLMs. The neuro-symbolic strategy combines the flexibility of language models with precise knowledge representation and verifiable reasoning. The work covers Logic-LM, ProgramFC, and learning from automated feedback, aiming to address LLM limitations in complex reasoning tasks. Why it matters: Improving the reliability of LLMs is crucial for high-stakes applications in finance, medicine, and law within the region and globally.
Abdulrahman Mahmoud, a postdoctoral fellow at Harvard University, discusses software-directed tools and techniques for processor design and reliability enhancement in ML systems. He emphasizes the need for a nuanced approach to numerical data formats supported by robust hardware. He advocates for integrating reliability as a foundational element in the design process. Why it matters: This research addresses the critical challenge of hardware reliability in AI processors, particularly relevant as the field moves towards hardware-software co-design for sustained growth.
MBZUAI alumnus Zain Muhammed Mujahid is pursuing a Ph.D. at the University of Copenhagen, focusing on factual text generation in LLMs to combat misinformation. During his master's at MBZUAI, he researched political bias and misinformation in media outlets using LLMs, under the mentorship of Professor Preslav Nakov. His master's thesis involved assessing a media outlet's factual reporting level and political leaning on topics like immigration and economy. Why it matters: This research addresses a critical challenge in AI, enhancing the reliability of LLMs and mitigating the spread of disinformation, an issue of global concern.