arXiv subjects

Ahmed Elmagarmid

Publications and source records attributed to Ahmed Elmagarmid.

8 recordsLinked to original sources

arXiv2026

Fanar 2.0: Arabic Generative AI Stack

We present Fanar 2.0, the second generation of Qatar's Arabic-centric Generative AI platform. Sovereignty is a first-class design principle: every component, from data pipelines to deployment infrastructure, was designed and operated entirely at QCRI, Hamad Bin Khalifa University. Fanar 2.0 is a story of resource-constrained excellence: the effort ran on 256 NVIDIA H100 GPUs, with Arabic having only ~0.5% of web data despite 400 million native speakers. Fanar 2.0 adopts a disciplined strategy of data quality over quantity, targeted continual pre-training, and model merging to achieve substantial gains within these constraints. At the core is Fanar-27B, continually pre-trained from a Gemma-3-27B backbone on a curated corpus of 120 billion high-quality tokens across three data recipes. Despite using 8x fewer pre-training tokens than Fanar 1.0, it delivers substantial benchmark improvements: Arabic knowledge (+9.1 pts), language (+7.3 pts), dialects (+3.5 pts), and English capability (+7.6 pts). Beyond the core LLM, Fanar 2.0 introduces a rich stack of new capabilities. FanarGuard is a state-of-the-art 4B bilingual moderation filter for Arabic safety and cultural alignment. The speech family Aura gains a long-form ASR model for hours-long audio. Oryx vision family adds Arabic-aware image and video understanding alongside culturally grounded image generation. An agentic tool-calling framework enables multi-step workflows. Fanar-Sadiq utilizes a multi-agent architecture for Islamic content. Fanar-Diwan provides classical Arabic poetry generation. FanarShaheen delivers LLM-powered bilingual translation. A redesigned multi-layer orchestrator coordinates all components through intent-aware routing and defense-in-depth safety validation. Taken together, Fanar 2.0 demonstrates that sovereign, resource-constrained AI development can produce systems competitive with those built at far greater scale.

cs.CL↗

arXiv2026

HCT-QA: A Benchmark for Question Answering on Human-Centric Tables

Tabular data embedded in PDF files, web pages, and other types of documents is prevalent in various domains. These tables, which we call human-centric tables (HCTs for short), are dense in information but often exhibit complex structural and semantic layouts. To query these HCTs, some existing solutions focus on transforming them into relational formats. However, they fail to handle the diverse and complex layouts of HCTs, making them not amenable to easy querying with SQL-based approaches. Another emerging option is to use Large Language Models (LLMs) and Vision Language Models (VLMs). However, there is a lack of standard evaluation benchmarks to measure and compare the performance of models to query HCTs using natural language. To address this gap, we propose the HumanCentric Tables Question-Answering extensive benchmark (HCTQA) consisting of thousands of HCTs with several thousands of natural language questions with their respective answers. More specifically, HCT-QA includes 1,880 real-world HCTs with 9,835 QA pairs in addition to 4,679 synthetic HCTs with 67.7K QA pairs. Also, we show through extensive experiments the performance of 25 and 9 different LLMS and VLMs, respectively, in an answering HCT-QA's questions. In addition, we show how finetuning an LLM on HCT-QA improves F1 scores by up to 25 percentage points compared to the off-the-shelf model. Compared to existing benchmarks, HCT-QA stands out for its broad complexity and diversity of covered HCTs and generated questions, its comprehensive metadata enabling deeper insight and analysis, and its novel synthetic data and QA generator.

cs.IR↗

arXiv2025

Fanar: An Arabic-Centric Multimodal Generative AI Platform

We present Fanar, a platform for Arabic-centric multimodal generative AI systems, that supports language, speech and image generation tasks. At the heart of Fanar are Fanar Star and Fanar Prime, two highly capable Arabic Large Language Models (LLMs) that are best in the class on well established benchmarks for similar sized models. Fanar Star is a 7B (billion) parameter model that was trained from scratch on nearly 1 trillion clean and deduplicated Arabic, English and Code tokens. Fanar Prime is a 9B parameter model continually trained on the Gemma-2 9B base model on the same 1 trillion token set. Both models are concurrently deployed and designed to address different types of prompts transparently routed through a custom-built orchestrator. The Fanar platform provides many other capabilities including a customized Islamic Retrieval Augmented Generation (RAG) system for handling religious prompts, a Recency RAG for summarizing information about current or recent events that have occurred after the pre-training data cut-off date. The platform provides additional cognitive capabilities including in-house bilingual speech recognition that supports multiple Arabic dialects, voice and image generation that is fine-tuned to better reflect regional characteristics. Finally, Fanar provides an attribution service that can be used to verify the authenticity of fact based generated content. The design, development, and implementation of Fanar was entirely undertaken at Hamad Bin Khalifa University's Qatar Computing Research Institute (QCRI) and was sponsored by Qatar's Ministry of Communications and Information Technology to enable sovereign AI technology development.

cs.CL↗

arXiv2023

Cross Modal Data Discovery over Structured and Unstructured Data Lakes

Organizations are collecting increasingly large amounts of data for data driven decision making. These data are often dumped into a centralized repository, e.g., a data lake, consisting of thousands of structured and unstructured datasets. Perversely, such mixture of datasets makes the problem of discovering elements (e.g., tables or documents) that are relevant to a user's query or an analytical task very challenging. Despite the recent efforts in data discovery, the problem remains widely open especially in the two fronts of (1) discovering relationships and relatedness across structured and unstructured datasets where existing techniques suffer from either scalability, being customized for a specific problem type (e.g., entity matching or data integration), or demolishing the structural properties on its way, and (2) developing a holistic system for integrating various similarity measurements and sketches in an effective way to boost the discovery accuracy. In this paper, we propose a new data discovery system, named CMDL, for addressing these two limitations. CMDL supports the data discovery process over both structured and unstructured data while retaining the structural properties of tables.

cs.AI↗

arXiv2018

Unsupervised String Transformation Learning for Entity Consolidation

Data integration has been a long-standing challenge in data management with many applications. A key step in data integration is entity consolidation. It takes a collection of clusters of duplicate records as input and produces a single "golden record" for each cluster, which contains the canonical value for each attribute. Truth discovery and data fusion methods, as well as Master Data Management (MDM) systems, can be used for entity consolidation. However, to achieve better results, the variant values (i.e., values that are logically the same with different formats) in the clusters need to be consolidated before applying these methods. For this purpose, we propose a data-driven method to standardize the variant values based on two observations: (1) the variant values usually can be transformed to the same representation (e.g., "Mary Lee" and "Lee, Mary") and (2) the same transformation often appears repeatedly across different clusters (e.g., transpose the first and last name). Our approach first uses an unsupervised method to generate groups of value pairs that can be transformed in the same way (i.e., they share a transformation). Then the groups are presented to a human for verification and the approved ones are used to standardize the data. In a real-world dataset with 17,497 records, our method achieved 75% recall and 99.5% precision in standardizing variant values by asking a human 100 yes/no questions, which completely outperformed a state of the art data wrangling tool.

cs.DB↗

arXiv2016

Impact of Physical Activity on Sleep:A Deep Learning Based Exploration

The importance of sleep is paramount for maintaining physical, emotional and mental wellbeing. Though the relationship between sleep and physical activity is known to be important, it is not yet fully understood. The explosion in popularity of actigraphy and wearable devices, provides a unique opportunity to understand this relationship. Leveraging this information source requires new tools to be developed to facilitate data-driven research for sleep and activity patient-recommendations. In this paper we explore the use of deep learning to build sleep quality prediction models based on actigraphy data. We first use deep learning as a pure model building device by performing human activity recognition (HAR) on raw sensor data, and using deep learning to build sleep prediction models. We compare the deep learning models with those build using classical approaches, i.e. logistic regression, support vector machines, random forest and adaboost. Secondly, we employ the advantage of deep learning with its ability to handle high dimensional datasets. We explore several deep learning models on the raw wearable sensor output without performing HAR or any other feature extraction. Our results show that using a convolutional neural network on the raw wearables output improves the predictive value of sleep quality from physical activity, by an additional 8% compared to state-of-the-art non-deep learning approaches, which itself shows a 15% improvement over current practice. Moreover, utilizing deep learning on raw data eliminates the need for data pre-processing and simplifies the overall workflow to analyze actigraphy data for sleep and physical activity research.

cs.LG↗

arXiv2016

Robust Automated Human Activity Recognition and its Application to Sleep Research

Human Activity Recognition (HAR) is a powerful tool for understanding human behaviour. Applying HAR to wearable sensors can provide new insights by enriching the feature set in health studies, and enhance the personalisation and effectiveness of health, wellness, and fitness applications. Wearable devices provide an unobtrusive platform for user monitoring, and due to their increasing market penetration, feel intrinsic to the wearer. The integration of these devices in daily life provide a unique opportunity for understanding human health and wellbeing. This is referred to as the "quantified self" movement. The analyses of complex health behaviours such as sleep, traditionally require a time-consuming manual interpretation by experts. This manual work is necessary due to the erratic periodicity and persistent noisiness of human behaviour. In this paper, we present a robust automated human activity recognition algorithm, which we call RAHAR. We test our algorithm in the application area of sleep research by providing a novel framework for evaluating sleep quality and examining the correlation between the aforementioned and an individual's physical activity. Our results improve the state-of-the-art procedure in sleep research by 15 percent for area under ROC and by 30 percent for F1 score on average. However, application of RAHAR is not limited to sleep analysis and can be used for understanding other health problems such as obesity, diabetes, and cardiac diseases.

cs.LG↗

arXiv2015

Parameter Database : Data-centric Synchronization for Scalable Machine Learning

We propose a new data-centric synchronization framework for carrying out of machine learning (ML) tasks in a distributed environment. Our framework exploits the iterative nature of ML algorithms and relaxes the application agnostic bulk synchronization parallel (BSP) paradigm that has previously been used for distributed machine learning. Data-centric synchronization complements function-centric synchronization based on using stale updates to increase the throughput of distributed ML computations. Experiments to validate our framework suggest that we can attain substantial improvement over BSP while guaranteeing sequential correctness of ML tasks.

cs.DB↗