The paper introduces TimeHUT, a new method for learning time-series representations using hierarchical uniformity-tolerance balancing of contrastive representations. TimeHUT employs a hierarchical setup to learn both instance-wise and temporal information, along with a temperature scheduler to balance uniformity and tolerance. The method was evaluated on UCR, UAE, Yahoo, and KPI datasets, demonstrating superior performance in classification tasks and competitive results in anomaly detection.
MBZUAI introduces Agent-X, a benchmark for evaluating multi-step reasoning in vision-centric agents across real-world, multimodal settings. Agent-X includes 828 tasks with diverse visual contexts and spans six environments, requiring tool use and stepwise decision-making. Experiments show that current LLMs struggle with multi-step vision tasks, achieving less than 50% success, highlighting areas for improvement in LMM reasoning and tool use.
This paper introduces a method for quantifying the transferability of architectural components in Single Image Super-Resolution (SISR) models, termed "Universality," and proposes a Universality Assessment Equation (UAE). Guided by the UAE, the authors design optimized modules, Cycle Residual Block (CRB) and Depth-Wise Cycle Residual Block (DCRB), and demonstrate their effectiveness across various datasets and low-level tasks. Results show that networks using these modules outperform state-of-the-art methods, achieving improved PSNR or parameter reduction.
This paper introduces a new Single Domain Generalization (SDG) method called ConDiSR for medical image classification, using channel-wise contrastive disentanglement and reconstruction-based style regularization. The method is evaluated on multicenter histopathology image classification, achieving a 1% improvement in average accuracy compared to state-of-the-art SDG baselines. Code is available at https://github.com/BioMedIA-MBZUAI/ConDiSR.
A KAUST-led international study published in Nature outlines a roadmap for marine life to recover to full abundance by 2050. The study identifies "recovery wedges" consisting of six complementary interventions: protecting species, harvesting wisely, protecting spaces, restoring habitats, reducing pollution, and mitigating climate change. Researchers found evidence of marine life's resilience and a shift from losses to recovery in some areas. Why it matters: The study provides actionable recommendations for large-scale interventions to achieve a sustainable future for marine ecosystems in the Red Sea and globally.
MBZUAI researchers developed Data Wise, an AI platform that provides instant data analytics for businesses. The platform uses AI agents and LLMs to analyze raw customer data and generate actionable recommendations. Data Wise aims to address the shortage of data scientists, particularly in the UAE and GCC. Why it matters: This platform democratizes access to advanced analytics, empowering businesses in the region to make data-driven decisions without relying on scarce technical expertise.
WISE (World Innovation Summit for Education) hosted a Research and Policy dialogue in Qatar focused on assessing the readiness of classrooms for AI integration. The discussion explored the opportunities and challenges educators face in adopting artificial intelligence tools and methodologies. Participants shared insights on necessary policy frameworks, curriculum adjustments, and teacher training to effectively incorporate AI into educational settings. Why it matters: This dialogue highlights the proactive efforts within the GCC region to prepare its education sector for the transformative impact of artificial intelligence.
WISE (World Innovation Summit for Education) recently hosted a policy dialogue in Qatar, focusing on assessing AI readiness within classrooms. The discussions leveraged insights from global research to explore the integration of artificial intelligence in educational settings. The dialogue aimed to inform future strategies for incorporating AI technologies effectively into school curricula and teaching practices. Why it matters: This initiative highlights Qatar's commitment to shaping education policy around emerging technologies and addressing the practical challenges of AI adoption in schools across the region and globally.