General AI research publications from MBZUAI, KAUST, TII, QCRI, and other GCC institutions, including conference papers, journal articles, and preprints.
This article discusses MBZUAI's efforts in advancing Arabic language AI, including the development of advanced linguistic models using deep learning techniques. Key initiatives include Jais, a 13B parameter Arabic LLM developed in collaboration with G42's Inception, and Atlas-Chat, which understands the Moroccan dialect. The university is also incorporating Arabic in practical AI solutions like BiMediX2, a healthcare multi-modal model that understands medical queries in both English and Arabic. Why it matters: These initiatives are crucial for preserving Arabic cultural heritage, enabling future discovery, and addressing linguistic challenges specific to the Arabic language in AI applications.
MBZUAI researchers introduced Web2Code, a new dataset suite, at NeurIPS to enhance multimodal LLM performance in web page analysis and HTML generation. The suite includes a fine-tuning dataset and two benchmark datasets. Instruction tuning with Web2Code improved performance on specialized tasks without affecting general capabilities. Why it matters: This contribution addresses a key limitation in current multimodal LLMs, potentially boosting productivity in web design and development by providing targeted training data.
Researchers from MBZUAI and King's College London have developed a new prompting strategy called self-guided exploration to improve LLM performance on combinatorial problems. The method was tested on complex challenges like the traveling salesman problem. The findings will be presented at the 38th Annual Conference on Neural Information Processing Systems (NeurIPS) in Vancouver. Why it matters: This research could lead to practical applications of LLMs in industries like logistics, planning, and scheduling by offering new approaches to computationally complex problems.
Researchers at MBZUAI have developed LLM-DetectAIve, a tool to classify the degree of machine involvement in text generation. The system categorizes text into four types: human-written, machine-generated, machine-written and machine-humanized, and human-written and machine-polished. A demo website allows users to test the tool's ability to detect machine involvement. Why it matters: This research addresses the growing need to identify and classify AI-generated content in academic and professional settings, particularly in light of increasing LLM misuse.
A study co-authored by researchers from UC Berkeley, University of the Witwatersrand, Lelapa AI, and MBZUAI received the Outstanding Paper Award at EMNLP 2024. The paper critiques the term "low-resource" languages in NLP, highlighting its limitations in capturing the diverse challenges faced by different languages. The authors propose a more detailed analysis of resourcedness to encourage targeted support for languages currently underserved by technology. Why it matters: The research challenges assumptions in NLP and promotes more nuanced approaches to supporting the world's many languages, including Arabic, in AI systems.
MBZUAI doctoral student Mai A. Shaaban and colleagues developed MedPromptX, a system that analyzes chest X-rays and patient data to aid lung disease diagnoses. MedPromptX uses multimodal large language models with visual grounding and few-shot prompting, trained on a new dataset of 6,000 patient records (MedPromptX-VQA) derived from MIMIC-IV and MIMIC-CXR. The system addresses the challenge of incomplete electronic health records by leveraging the knowledge embedded in large language models to interpret lab results. Why it matters: This research advances AI-driven medical diagnostics by integrating diverse data sources and addressing data gaps, potentially leading to quicker and more accurate diagnoses.
MBZUAI researchers developed a new deep learning method for rapid and accurate estimation of clinical measurements from echocardiograms. The method focuses on improving the measurement of the left ventricle ejection fraction, a key indicator of heart health. Their deep learning approach improves upon previous methods by better organizing data representation, enhancing performance and transferability. Why it matters: The AI-driven solution can potentially reduce analysis time for cardiologists, improve patient care, and be particularly beneficial in regions with limited healthcare resources.
MBZUAI researchers developed a method to adapt Meta's Segment Anything Model (SAM) for medical image segmentation, addressing its performance gap with natural images. Their approach improves SAM's accuracy without requiring extensive retraining or large medical image datasets. The research, led by Chao Qin, was nominated for the Best Paper Award at the MICCAI conference in Marrakesh. Why it matters: This offers a more efficient and effective way to leverage foundation models in specialized medical imaging applications, potentially improving diagnostic accuracy and reducing the need for large-scale, domain-specific training data.
MBZUAI has launched a full robotics program focusing on robot learning, humanoid robotics, human-computer interaction, and sensory awareness. The program includes research and teaching labs for experimentation and aims to address challenges in agriculture, logistics, and healthcare. The robotics department, founded in 2023, welcomed 18 students in August and is expected to grow to more than 15 faculty members over the next two years. Why it matters: This program signifies a major investment in AI for physical systems in the UAE, potentially leading to innovations across sectors and strengthening MBZUAI's position as a leading AI research institution.
MBZUAI researchers developed a machine-learning method to predict antimicrobial resistance (AMR) by analyzing electronic health records. The system predicts if a patient will experience AMR when prescribed an antibiotic or if infected with a bacterium. Published in Scientific Reports, the innovation helps physicians identify patients at risk for AMR by using patient demographics, lab results, and physician notes. Why it matters: This approach can help combat the rise of drug-resistant bacteria by providing timely predictions and supporting more informed prescription decisions.
MBZUAI, in partnership with IBM Research, is developing GeoChat+, a vision-language model (VLM) for multi-modal, temporal remote sensing image analysis. GeoChat+ builds on the previous GeoChat model, enhancing capabilities with multi-modal images from various Earth observation systems like Sentinel-1, Sentinel-2, Landsat, and high-resolution imagery. GeoChat+ will integrate data from multiple satellites at different times to detect environmental changes and analyze the impact on soil quality, air quality, and erosion. Why it matters: This advancement promises to revolutionize geographic data analysis, providing detailed reports for high-risk regions and aiding reforestation efforts.
MBZUAI researchers have created ArabicMMLU, the first benchmark dataset in Modern Standard Arabic for evaluating language understanding across multiple tasks. The dataset contains over 14,000 multiple-choice questions from school exams across the Arabic-speaking world and addresses the limitations of translated English datasets. It was presented at the 62nd Annual Meeting of the Association for Computational Linguistics in Bangkok. Why it matters: This benchmark enables a more accurate and culturally relevant evaluation of LLMs' capabilities in Arabic, which is crucial for developing AI tailored to the Arab world.
MBZUAI researchers presented EXAMS-V, a new benchmark dataset for evaluating the reasoning and processing abilities of vision language models (VLMs). EXAMS-V contains over 20,000 multiple-choice questions across 26 subjects and 11 languages, including Arabic. The dataset presents the questions within images, testing the VLM's ability to integrate visual and textual information. Why it matters: This dataset fills a gap in VLM evaluation, providing a valuable resource for assessing and improving the multimodal reasoning capabilities of these models, particularly in diverse languages like Arabic.
MBZUAI published over 300 papers at top-tier AI venues between January and June 2024, including 39 papers at ICLR 2024, building on 612 papers published in 2023. MBZUAI is now ranked among the world's top 100 universities in computer science and top 20 globally in AI-related fields. One standout paper, 'M4,' won the Best Resource Paper Award at EACL 2024 for its work on detecting LLM-generated text across multiple languages and domains. Why it matters: This continued research output and rising rankings solidify MBZUAI's position as a leading AI research institution in the GCC region and globally.
MBZUAI researchers found that ImageNet performance isn't always indicative of real-world task performance for computer vision models. The study analyzed four popular model configurations, revealing variations in behavior on specific image types despite similar overall ImageNet accuracy. It indicates that certain model configurations are better suited for particular tasks, even with lower ImageNet scores. Why it matters: This challenges the reliance on ImageNet as a sole benchmark and highlights the need for task-specific evaluations in computer vision.
A study by MBZUAI's Preslav Nakov and Cornell co-authors examines how to develop systems that detect fake news in a landscape where text is generated by humans and machines. The research, presented at the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics, analyzes fake news detectors' ability to identify human- and machine-written content. The study highlights biases in current detectors, which tend to classify machine-written news as fake and human-written news as true. Why it matters: Addressing these biases is crucial as machine-generated content becomes more prevalent in both real and fake news, requiring more nuanced detection methods.
MBZUAI M.Sc. graduate Mohammad Hanan Ghani developed new techniques to improve text-to-image generation from long text prompts, combining large language models and diffusion models. Advised by Dr. Salman Khan, Ghani published three papers at ICLR, BMVC, and NeurIPS, with the ICLR paper focusing on generating images that accurately reflect detailed text descriptions. The new system improves upon existing techniques to generate images that closely follow the details of the input text. Why it matters: This research addresses a key limitation in current T2I models and advances the field of multimodal AI, potentially improving the capabilities of robots and autonomous devices.
MBZUAI, Petuum, and LLM360 have launched K2-65B, an open-source 65B parameter LLM, trained on 1.4T tokens using 480 A100 GPUs. K2-65B outperforms Llama 2 70B while using 35% fewer resources, emphasizing sustainable AI development. The model and its chat variant, K2-Chat, excel in math, coding, medicine, and human-like response generation, with the model available under the Apache 2.0 license. Why it matters: This launch highlights the UAE's increasing capabilities in developing efficient and high-performing LLMs, promoting open-source collaboration and setting new standards for sustainable AI practices in the region.
Researchers from MBZUAI presented a new algorithm at ICLR 2024 that identifies causal relationships involving both observed and latent variables. The algorithm addresses limitations of existing methods that struggle with latent variables or assume observed variables don't directly influence latent variables. The proposed algorithm can accommodate both scenarios, offering a more generalizable approach to causal discovery. Why it matters: This research advances the development of AI systems that can analyze complex data and identify causal relationships, with potential applications in fields like medicine where understanding causality is crucial for developing treatments and preventative measures.
MBZUAI researchers collaborated with Carnegie Mellon University and the Broad Institute of MIT and Harvard to develop a new statistical method for analyzing data used for gene regulatory network inference. The method addresses the challenge of distinguishing true zero expression values from dropouts in single-cell RNA sequencing data. This research will be presented at the Twelfth International Conference on Learning Representations (ICLR 2024). Why it matters: Improving gene regulatory network inference can lead to better understanding of disease mechanisms and inform the development of new medicines.
MBZUAI and the University of Michigan Ann Arbor have announced a new collaboration in AI research, sponsored by the U.S. Mission to the UAE. The partnership focuses on projects addressing the cultural divide in AI, with research teams from both institutions collaborating throughout the 2023/2024 academic year. A workshop titled “Bridging the Cultural Divide in AI: Analyzing Fairness, Bias, and Transparency across Cultures” will be held on April 29-30. Why it matters: The collaboration strengthens ties between the UAE and the U.S. in AI, addressing critical issues of fairness and cultural sensitivity in AI development.
MBZUAI's Institute of Foundation Models (IFM) has launched five new specialized language and multimodal models, including BiMediX, PALO, GLaMM, GeoChat, and MobiLLaMA. These models address real-world applications in healthcare, visual reasoning, multilingual capabilities, geospatial analysis, and mobile device efficiency. BiMediX is a bilingual medical LLM, while GLaMM generates natural language responses related to objects in an image at the pixel level. Why it matters: This launch demonstrates MBZUAI's commitment to advancing AI research and developing practical AI solutions for various industries, especially with a focus on Arabic language capabilities.
MBZUAI and the UNDP have partnered to advance the use of AI for sustainable development, with MBZUAI becoming the founding knowledge partner for the UNDP’s AI for Sustainable Development Platform (AI4SDP). The partnership, formalized at the World Governments Summit 2024, will focus on environmental resilience, water resources management, climate adaptation, social cohesion, and reducing inequalities. MBZUAI will contribute climate research, use cases, and scenarios to the AI4SDP for implementation in the real world. Why it matters: This collaboration signifies a commitment to leveraging AI for addressing critical global challenges and sustainable development goals in the Arab region.
MBZUAI and Silal, an Abu Dhabi-based agri-food company, signed an MoU at COP28 to bring AI innovation to agriculture and food production. The agreement establishes a joint AI Center of Excellence to develop the UAE's food production sector, improve food security, and enhance sustainability. Both parties will conduct joint research, exchange expertise, and support startups focused on improving efficiency and innovation in the UAE’s food sector. Why it matters: The partnership aligns with the UAE's National Strategy for Food Security 2051 and aims to leverage AI for sustainable food production, addressing critical challenges like climate change and resource management.
MBZUAI Professor Agathe Guilloux developed the SigLasso model to forecast hospitalizations using real-time data from Google and Météo France during the COVID-19 pandemic. The model integrates mobility data and weather patterns to predict hospitalization rates 10-14 days in advance. SigLasso outperformed industry standards like GRU and Neural CDE in reducing reconstruction error. Why it matters: This research demonstrates the potential of AI to improve healthcare resource allocation and crisis management by accurately predicting patient flow using readily available data.
MBZUAI increased faculty diversity and worked with global partners on application projects in 2023, including developing Jais (with Core42 and Cerebras) and Vicuna (with UC San Diego, UC Berkeley, CMU, and Stanford). They also launched Jais Climate, a bilingual LLM for climate intelligence, and LLM360, a framework for transparent LLM research. Why it matters: MBZUAI's involvement in open-source GenAI initiatives and partnerships positions the UAE as a key player in responsible AI development and talent creation.
MBZUAI researchers are developing spiking neural networks (SNNs) to emulate the energy efficiency of the human brain. Traditional deep learning models like those powering ChatGPT consume significant energy, with a single query using 3.96 watts. SNNs aim to mimic biological neurons more closely to reduce energy consumption, as the human brain uses only a fraction of the energy compared to these models. Why it matters: This research could lead to more sustainable and energy-efficient AI technologies, addressing a major challenge in deploying large-scale AI systems.
MBZUAI faculty and students will present 44 papers at the Empirical Methods in Natural Language Processing (EMNLP) conference in Singapore. Research topics include disinformation detection, social media analysis, dialogue generation, and Arabic LLMs. Preslav Nakov, Iryna Gurevych, Timothy Baldwin, Alham Fikri Aji, and Muhammad Abdul-Mageed are among the MBZUAI researchers presenting at the conference. Why it matters: MBZUAI's strong presence at a top NLP conference highlights the UAE's growing contributions to cutting-edge AI research and its increasing global prominence in the field.
An MBZUAI team won the best paper award at the inaugural Arabic Natural Language Processing Conference for their work on processing Arabic speech. Their study establishes a new approach to tackle the complexities of spoken Arabic, which differs significantly from text-based language models. The team's approach aims to advance new tools for Arabic speakers by addressing challenges like intonation and the continuous nature of speech. Why it matters: This award highlights the importance of specialized research in Arabic NLP, as mainstream LLMs often face limitations in accurately processing the nuances of Arabic speech.
MBZUAI researchers created Bactrian-X, a new dataset to improve LLM instruction following in low-resource languages. The dataset leverages instruction tuning, pairing instructions in various languages with expected responses. Bactrian-X builds upon existing open-source instruction tuning models. Why it matters: This work aims to democratize access to LLMs by enabling users to interact with them in their native languages, even when English proficiency is limited.
MBZUAI and Core42 have launched Jais Climate, the first bilingual (Arabic/English) LLM dedicated to climate and sustainability. It is fine-tuned with 1.4 million climate-related instructions and trained on the ClimaInstruct dataset. Jais Climate is built on Jais 13B and incorporates technology from Vicuna, an open-source LLM. Why it matters: This model provides accessible climate data to a wide audience, including decision-makers and the general public, and highlights the UAE's focus on using AI for sustainability.
MBZUAI researchers developed FeSViBS, a new federated split learning technique for vision transformers that addresses data scarcity and privacy concerns in healthcare image classification. The method combines federated learning and split learning to train models collaboratively without sharing sensitive patient data directly. It overcomes limitations of traditional centralized training and vulnerabilities in federated learning. Why it matters: This approach enables the development of AI-powered healthcare applications while adhering to stringent data privacy regulations, unlocking the potential of machine learning in medical imaging.
MBZUAI and Sheikh Shakbout Medical City researchers developed PECon, a deep learning method for pulmonary embolism detection using CT scans and electronic health records. PECon uses neural networks and contrastive learning to encode and align image and text data. The method aims to improve diagnosis accuracy and speed, potentially saving lives. Why it matters: This research demonstrates AI's potential to enhance medical diagnostics in the UAE, addressing a critical healthcare challenge.
IBM and MBZUAI have partnered to create an AI Center of Excellence, with the goal of driving sustainability in the region. The center will use AI to monitor, model, and visualize climate change, providing decision-makers with data to address issues like the urban heat island effect. Dr. Fahad Khan, Dr. Salman Khan, and Dr. Levente Klein from MBZUAI are leading the research. Why it matters: This collaboration highlights the UAE's commitment to using AI to tackle critical climate challenges and supports the upcoming COP28 in Dubai.
MBZUAI faculty and students will present 53 papers at NeurIPS 2023. Key faculty include Eric Xing, Kun Zhang, and Tongliang Liu, each contributing to nine papers. One paper was selected for oral presentation and two for spotlight presentations. Why it matters: MBZUAI's strong presence at NeurIPS highlights its growing influence in the global AI research community and its focus on high-impact AI research.
MBZUAI launched the Institute of Foundation Models, the MBZUAI Metaverse Center (MMC), and the MBZUAI Incubation and Entrepreneurship Center (MIEC) at GITEX 2023. The university also signed MoUs with Abu Dhabi Customs and the Department of Municipalities and Transport to collaborate on AI applications. MBZUAI faculty participated in panel discussions on generative AI and large language models, including the Jais Arabic LLM. Why it matters: These initiatives and partnerships signal MBZUAI's central role in advancing AI research, development, and adoption across key sectors in the UAE.
MBZUAI has launched the Institute of Foundation Models to advance generative AI research and development. The institute will focus on developing large-scale AI models adaptable to various applications, building on MBZUAI's existing work with models like Jais, Llama 2, and Vicuna. It will focus on multi-modal foundation models applicable to areas like healthcare, finance and environmental engineering. Why it matters: This initiative further solidifies the UAE's position as a leader in AI, particularly in the development and application of foundation models for diverse industries.
MBZUAI has launched the MBZUAI Metaverse Center (MMC) and the MBZUAI Incubation and Entrepreneurship Center (MIEC). The Metaverse Center focuses on AI-driven immersive technologies for communication, healthcare, entertainment, and education. The Incubation and Entrepreneurship Center will focus on catalyzing AI innovation and adoption in industry. Why it matters: These centers signal MBZUAI's commitment to expanding AI research and fostering a startup ecosystem in the UAE.
MBZUAI is a global partner in Meta's release of Llama 2, joining organizations like IBM, AWS, Microsoft, and NVIDIA. MBZUAI will provide early feedback and help build the software as a global community. MBZUAI is working on large language models, developing a sustainable LLM named Vicuna, and strengthening infrastructure for LLM-chat evaluation. Why it matters: MBZUAI's involvement promises to bring about a new generation of UAE-born AI advancements built around the Llama 2 ecosystem and fact-checking capabilities.
MBZUAI is now ranked 24th globally in AI, computer vision, machine learning, and natural language processing, according to CSRankings. This ranking is attributed to the addition of faculty like Preslav Nakov, Hanan Al Darmaki, and Samuel Horvath. MBZUAI now ranks ahead of universities like the University of Michigan and Imperial College London in specific AI fields. Why it matters: This ranking establishes MBZUAI as the top CS institution in the Arab World and highlights the UAE's growing prominence in AI research.
MBZUAI has been ranked 127th globally among institutions conducting computer science research and ranks 30th globally in AI, computer vision, machine learning, and NLP. This places MBZUAI ahead of universities such as the University of Michigan, Georgia Tech, Imperial College London and others. MBZUAI is now the top-ranked CS institution in the Arab World and the Middle East and Africa according to CSRankings. Why it matters: This ranking highlights the rapid growth and increasing prominence of AI research in the UAE and the broader Middle East.
G42's Inception has open-sourced Jais, a 13-billion parameter Arabic large language model (LLM). Jais was trained on a 395-billion-token Arabic and English dataset and outperforms existing Arabic models. The model is a collaboration between Inception, MBZUAI, and Cerebras Systems, and was trained on the Condor Galaxy supercomputer. Why it matters: This release establishes a new standard for Arabic language AI, providing over 400 million Arabic speakers access to generative AI and fostering innovation in the region.
Researchers from MBZUAI, University of British Columbia, and Monash University have created LaMini-LM, a collection of small language models distilled from ChatGPT. LaMini-LM is trained on a dataset of 2.58M instructions and can be deployed on consumer laptops and mobile devices. The smaller models perform almost as well as larger counterparts while addressing security concerns. Why it matters: This work enables the deployment of LLMs in resource-constrained environments and enhances data security by reducing reliance on cloud-based LLMs.
Researchers from MBZUAI, UC Berkeley, CMU, Stanford, and UC San Diego collaborated to create Vicuna, an open-source chatbot that costs $300 to train, unlike ChatGPT which costs over $4 million. Vicuna achieves 90% of ChatGPT's subjective language quality while being far more energy-efficient and can run on a single GPU. It was fine-tuned from Meta AI’s LLaMA model using user-shared conversations and has gained significant traction on GitHub. Why it matters: This research demonstrates that high-quality chatbots can be developed at a fraction of the cost and environmental impact, opening up new possibilities for sustainable AI development in the region.
MBZUAI has established new robotics and computer science departments, launching master’s and Ph.D. programs in each discipline. The new departments will complement MBZUAI’s existing CV, ML, and NLP departments. The robotics department will focus on robot learning and algorithms, while computer science will focus on foundational technologies with an emphasis on entrepreneurship and sustainability. Why it matters: This expansion strengthens the UAE's AI ecosystem and positions MBZUAI as a hub for AI research and innovation, addressing the growing global demand for AI talent.
MBZUAI researchers had 26 papers accepted at ACL 2023, a top NLP conference. Assistant Professor Alham Fikri Aji co-authored eight papers, including one on crosslingual generalization through multitask finetuning (MTF). Deputy Department Chair Preslav Nakov co-authored a paper on a Bulgarian language understanding benchmark dedicated to the memory of Yale Computer Scientist Dragomir R. Radev. Why it matters: MBZUAI's strong presence at ACL highlights its growing influence in the NLP field and its contributions to multilingual AI research.
MBZUAI President Eric Xing led a global collaboration to develop Vicuna, an LLM alternative to GPT-3 addressing the unsustainable costs of training LLMs. OpenAI CEO Sam Altman acknowledged Abu Dhabi's role in the global AI conversation, building off of achievements like Vicuna. Xing and colleagues are publishing research at MLSys 2023 on "cross-mesh resharding" to improve computer communication in deep learning, aiming for low-carbon, affordable, and miniaturized AI. Why it matters: This research signals a push towards sustainable AI development in the region, emphasizing efficiency and reduced environmental impact.
A new paper from MBZUAI researchers explores using ChatGPT to combat the spread of fake news. The researchers, including Preslav Nakov and Liangming Pan, demonstrate that ChatGPT can be used to fact-check published information. Their paper, "Fact-Checking Complex Claims with Program-Guided Reasoning," was accepted at ACL 2023. Why it matters: This research highlights the potential of large language models to address the growing challenge of misinformation, with implications for maintaining information integrity in the digital age.
Researchers from MBZUAI, KAUST, and Mila are collaborating to develop methods for identifying and mitigating the impact of malicious actors in federated learning systems used for health data analysis. These systems aggregate anonymized data from numerous devices to generate insights for healthcare improvements. The team's research, accepted at ICLR 2023, focuses on using variance reduction techniques to counteract the disruptive effects of skewed or corrupted data submitted by dishonest users. Why it matters: Protecting the integrity of AI-driven health systems is crucial for ensuring the reliability and safety of insights derived from sensitive patient data in the GCC region and globally.
MBZUAI and OurCrowd Arabia signed an MoU to accelerate the growth of the AI technology ecosystem at MBZUAI's campus in Abu Dhabi. The initiatives will focus on incubating startups and creating opportunities for AI talent, particularly MBZUAI graduates and researchers. OurCrowd Arabia is also establishing a VC investment center in Abu Dhabi to manage deals for its platform. Why it matters: This partnership aims to foster entrepreneurship and position Abu Dhabi as a global AI center by providing funding and support for AI startups.