Over the past three years, the rapid advancement of Large Language Models (LLMs) has had a profound impact on multiple areas of Artificial Intelligence (AI), particularly in Natural Language Processing (NLP) across diverse languages, including Arabic. Although Arabic is considered one of the most widely spoken languages across 27 countries in the Arabic world and used as a second language in some other non-Arabic countries as well, there is still a scarcity of Arabic resources, datasets, and tools. Arabic NLP tasks face various challenges due to the complexities of the Arabic language, including its rich morphology, intricate structure, and diverse writing standards, among other factors. Researchers have been actively addressing these challenges, demonstrating that pre-trained Large Language Models (LLMs) trained on multilingual corpora achieve significant success in various Arabic NLP tasks. This study provides an overview of using large language models (LLMs) for the Arabic language, highlighting early pre-trained Arabic Language models across various NLP applications and their ability to handle diverse Arabic content tasks and dialects. It also provides an overview of how techniques like finetuning and prompt engineering can enhance the performance of these models. Additionally, the study summarizes common Arabic benchmarks and datasets while presenting our observations on the persistent upward trend in the adoption of LLMs.

The rapid development of large language models (LLMs) has transformed the landscape of natural language processing. Evaluating LLMs properly is crucial for understanding their potential and addressing concerns such as safety. However, LLM evaluation is confronted by various factors, among which contamination stands out as a key issue that undermines the reliability of evaluations. In this work, we introduce the concept of contamination resistance to address this challenge. We propose a benchmark based on Caesar ciphers (e.g., "ab" to "bc" when the shift is 1), which, despite its simplicity, is an excellent example of a contamination resistant benchmark. We test this benchmark on widely used LLMs under various settings, and we find that these models struggle with this benchmark when contamination is controlled. Our findings reveal issues in current LLMs and raise important questions regarding their true capabilities. Our work contributes to the development of contamination resistant benchmarks, enabling more rigorous LLM evaluation and offering insights into the true capabilities and limitations of LLMs.

Our planet is facing increasingly frequent extreme events, which pose major risks to human lives and ecosystems. Recent advances in machine learning (ML), especially with foundation models (FMs) trained on extensive datasets, excel in extracting features and show promise in disaster management. Nevertheless, these models often inherit biases from training data, challenging their performance over extreme values. To explore the reliability of FM in the context of extreme events, we introduce \textbf{ExE}Bench (\textbf{Ex}treme \textbf{E}arth Benchmark), a collection of seven extreme event categories across floods, wildfires, storms, tropical cyclones, extreme precipitation, heatwaves, and cold waves. The dataset features global coverage, varying data volumes, and diverse data sources with different spatial, temporal, and spectral characteristics. To broaden the real-world impact of FMs, we include multiple challenging ML tasks that are closely aligned with operational needs in extreme events detection, monitoring, and forecasting. ExEBench aims to (1) assess FM generalizability across diverse, high-impact tasks and domains, (2) promote the development of novel ML methods that benefit disaster management, and (3) offer a platform for analyzing the interactions and cascading effects of extreme events to advance our understanding of Earth system, especially under the climate change expected in the decades to come. The dataset and code are public https://github.com/zhaoshan2/EarthExtreme-Bench.

This paper shows a comprehensive analysis of three algorithms (Time Series, Random Forest (RF) and Deep Reinforcement Learning) into three inventory models (the Lost Sales, Dual-Sourcing and Multi-Echelon Inventory Model). These methodologies are applied in the supermarket context. The main purpose is to analyse efficient methods for the data-driven. Their possibility, potential and current challenges are taken into consideration in this report. By comparing the results in each model, the effectiveness of each algorithm is evaluated based on several key performance indicators, including forecast accuracy, adaptability to market changes, and overall impact on inventory costs and customer satisfaction levels. The data visualization tools and statistical metrics are the indicators for the comparisons and show some obvious trends and patterns that can guide decision-making in inventory management. These tools enable managers to not only track the performance of different algorithms in real-time but also to drill down into specific data points to understand the underlying causes of inventory fluctuations. This level of detail is crucial for pinpointing inefficiencies and areas for improvement within the supply chain.

Building multimodal language models is fundamentally challenging: it requires aligning vision and language modalities, curating high-quality instruction data, and avoiding the degradation of existing text-only capabilities once vision is introduced. These difficulties are further magnified in the multilingual setting, where the need for multimodal data in different languages exacerbates existing data scarcity, machine translation often distorts meaning, and catastrophic forgetting is more pronounced. To address the aforementioned challenges, we introduce novel techniques spanning both data and modeling. First, we develop a synthetic annotation framework that curates high-quality, diverse multilingual multimodal instruction data, enabling Aya Vision models to produce natural, human-preferred responses to multimodal inputs across many languages. Complementing this, we propose a cross-modal model merging technique that mitigates catastrophic forgetting, effectively preserving text-only capabilities while simultaneously enhancing multimodal generative performance. Aya-Vision-8B achieves best-in-class performance compared to strong multimodal models such as Qwen-2.5-VL-7B, Pixtral-12B, and even much larger Llama-3.2-90B-Vision. We further scale this approach with Aya-Vision-32B, which outperforms models more than twice its size, such as Molmo-72B and LLaMA-3.2-90B-Vision. Our work advances multilingual progress on the multi-modal frontier, and provides insights into techniques that effectively bend the need for compute while delivering extremely high performance.

Solving partial or ordinary differential equation models in cardiac electrophysiology is a computationally demanding task, particularly when high-resolution meshes are required to capture the complex dynamics of the heart. Moreover, in clinical applications, it is essential to employ computational tools that provide only relevant information, ensuring clarity and ease of interpretation. In this work, we exploit two recently proposed operator learning approaches, namely Fourier Neural Operators (FNO) and Kernel Operator Learning (KOL), to learn the operator mapping the applied stimulus in the physical domain into the activation and repolarization time distributions. These data-driven methods are evaluated on synthetic 2D and 3D domains, as well as on a physiologically realistic left ventricle geometry. Notably, while the learned map between the applied current and activation time has its modelling counterpart in the Eikonal model, no equivalent partial differential equation (PDE) model is known for the map between the applied current and repolarization time. Our results demonstrate that both FNO and KOL approaches are robust to hyperparameter choices and computationally efficient compared to traditional PDE-based Monodomain models. These findings highlight the potential use of these surrogate operators to accelerate cardiac simulations and facilitate their clinical integration.

Named Entity Recognition NER is very crucial for various natural language processing applications, including information extraction, machine translation, and sentiment analysis. Despite the ever-increasing interest in African languages within computational linguistics, existing NER systems focus mainly on English, European, and a few other global languages, leaving a significant gap for under-resourced languages. This research presents the development of a WAZOBIA-NER system tailored for the three most prominent Nigerian languages: Hausa, Yoruba, and Igbo. This research begins with a comprehensive compilation of annotated datasets for each language, addressing data scarcity and linguistic diversity challenges. Exploring the state-of-the-art machine learning technique, Conditional Random Fields (CRF) and deep learning models such as Bidirectional Long Short-Term Memory (BiLSTM), Bidirectional Encoder Representation from Transformers (Bert) and fine-tune with a Recurrent Neural Network (RNN), the study evaluates the effectiveness of these approaches in recognizing three entities: persons, organizations, and locations. The system utilizes optical character recognition (OCR) technology to convert textual images into machine-readable text, thereby enabling the Wazobia system to accept both input text and textual images for extraction purposes. The system achieved a performance of 0.9511 in precision, 0.9400 in recall, 0.9564 in F1-score, and 0.9301 in accuracy. The model's evaluation was conducted across three languages, with precision, recall, F1-score, and accuracy as key assessment metrics. The Wazobia-NER system demonstrates that it is feasible to build robust NER tools for under-resourced African languages using current NLP frameworks and transfer learning.

HealthBench consists of 5,000 multi-turn conversations between a model and an individual user or healthcare professional. Responses are evaluated using conversation-specific rubrics created by 262 physicians. Unlike previous multiple-choice or short-answer benchmarks, Health-Bench enables realistic, open-ended evaluation through 48,562 unique rubric criteria spanning several health contexts (e.g., emergencies, transforming clinical data, global health) and behavioral dimensions (e.g., accuracy, instruction following, communication). HealthBench performance over the last two years reflects steady initial progress (compare GPT-3.5 Turbo's 16% to GPT-4o's 32%) and more rapid recent improvements (o3 scores 60%). Smaller models have especially improved: GPT-4.1 nano outperforms GPT-4o and is 25 times cheaper. We additionally release two HealthBench variations: HealthBench Consensus, which includes 34 particularly important dimensions of model behavior validated via physician consensus, and HealthBench Hard, where the current top score is 32%. We hope that HealthBench grounds progress towards model development and applications that benefit human health.

A swath of US technology firms announced deals in the Middle East as Donald Trump trumpeted 600bn in commitments from Saudi Arabia to American artificial intelligence companies during a tour of Gulf states. Among the biggest deals was a set signed by Nvidia. The company will sell hundreds of thousands of AI chips in Saudi Arabia, with a first tranche of 18,000 of its newest "Blackwell" chips going to Humain, Saudi Arabia's sovereign-wealth-fund-owned AI startup, Reuters reported. Cisco on Tuesday said it had signed a deal with G42, the AI firm based in the United Arab Emirates, to help the company develop that country's AI sector. Trump plans to visit the UAE on Thursday.

The likes of shepherd's pie and fish & chips soon be off Britain's dinner menu in favour of more eco-friendly options, according to a new report. Scientists have teamed up with HelloFresh to predict what Brits will be eating in just 10 years time as we fight to halt climate change. And the menu of the near future reveals five very bizarre options – with no meat in sight. There's a stir fry with noodles made out of kelp (a type of brown algae) as well as'meatballs' made with mushrooms on a bed of sorghum. There's also teff galette – a French-style tart made out of teff, a highly-nutritious ancient grain – served with dandelion salad.