This paper introduces MOTOR, a multimodal retrieval and re-ranking approach for medical visual question answering (MedVQA) that uses grounded captions and optimal transport to capture relationships between queries and retrieved context, leveraging both textual and visual information. MOTOR identifies clinically relevant contexts to augment VLM input, achieving higher accuracy on MedVQA datasets. Empirical analysis shows MOTOR outperforms state-of-the-art methods by an average of 6.45%.
McLaren Racing and KAUST are collaborating to advance research, innovation, and education in high-performance motorsport, supporting Saudi Vision 2030. McLaren driver Oscar Piastri visited KAUST for a research tour showcasing collaborative projects in aerodynamics, advanced lubricants, and biosensors. KAUST researchers are applying aerodynamics work with McLaren to support Saudi industry, and designing improved lubricant formulations to reduce friction. Why it matters: The partnership exemplifies cross-sector collaboration and KAUST's role in driving high-impact science and technology in the region, with applications extending beyond Formula 1.
KAUST, Abdul Latif Jameel Motors, and Toyota have formed a partnership to advance hydrogen fuel cell research in Saudi Arabia, supporting the Kingdom's decarbonization goals. KAUST has acquired proton electrolyte membrane (PEM) fuel cell modules from Toyota to establish a dedicated laboratory under its Clean Energy and Research Platform (CERP). Researchers at KAUST are conducting studies to optimize PEM fuel cells for Saudi Arabia's environmental conditions, aiming to maximize efficiency and reliability. Why it matters: This collaboration supports Saudi Arabia's Vision 2030 and net-zero goals, fostering innovation in hydrogen technology and sustainable energy solutions within the region.
The study introduces the Qatar University Dual-Machine Bearing Fault Benchmark dataset (QU-DMBF) containing sound and vibration data from two motors across 1080 conditions. It proposes a deep learning approach for sound-based fault detection, addressing limitations of vibration-based methods. Experiments on QU-DMBF show sound-based detection is more robust, independent of sensor location, and cost-effective while matching vibration-based performance. Why it matters: The new dataset and findings could shift the focus toward sound-based methods for more reliable and accessible predictive maintenance in industrial settings.
KAUST has launched self-driving shuttles on its campus, making it the first adopter of autonomous vehicles in Saudi Arabia. The pilot project utilizes vehicle technology from Local Motors and EasyMile. SAPTCO will operate the autonomous shuttles and manage operations with Saudi staff. Why it matters: This initiative advances Saudi Arabia's 2030 Vision and positions KAUST as a regional leader in smart city development and AI research.
MBZUAI researchers developed a new approach called Multimodal Optimal Transport via Grounded Retrieval (MOTOR) to improve the accuracy of vision-language models for medical image analysis. MOTOR combines retrieval-augmented generation (RAG) with an optimal transport algorithm to retrieve and rank relevant image and textual data. Testing on two medical datasets showed that MOTOR improved average performance by 6.45%. Why it matters: This technique addresses the challenges of limited specialized medical datasets and computational costs associated with training AI models for medical image interpretation, offering a more efficient and accurate solution.
Technology Innovation Institute (TII) and the University of Modena and Reggio Emilia are participating as Team TII-EuroRacing in the Autonomous Challenge at CES 2022 in Las Vegas. TII is also a premier sponsor of the event, which features head-to-head autonomous racecar competition at the Las Vegas Motor Speedway. Team TII-EuroRacing will compete with its DO12 racecar, a Dallara AV-21 retrofitted for automation, after making it to the finals at the Indy Autonomous Challenge in October 2021. Why it matters: This event highlights the UAE's commitment to advancing autonomous robotics and positions TII as a leader in the development of autonomous racing systems.
The TUM Autonomous Motorsport team developed algorithms and deployment strategies for the Abu Dhabi Autonomous Racing League (A2RL). Their software emulates human driving behavior, pushing vehicle handling and multi-vehicle interactions. The team's approach led to a victory in the A2RL challenge. Why it matters: Autonomous racing serves as a valuable research environment for advancing autonomous driving tech and improving road safety in the region and globally.