A DeepMind researcher presented work on incorporating symmetries into machine learning models, with applications to lattice-QCD and molecular dynamics. The work includes permutation and translation-invariant normalizing flows for free-energy estimation in molecular dynamics. They also presented U(N) and SU(N) Gauge-equivariant normalizing flows for pure Gauge simulations and its extensions to incorporate fermions in lattice-QCD. Why it matters: Applying symmetry principles to generative models could improve AI's ability to model complex physical systems relevant to materials science and other fields in the region.
Bruno Ribeiro from Purdue University presented a talk on Asymmetry Learning and Out-of-Distribution (OOD) Robustness. The talk introduced Asymmetry Learning, a new paradigm that focuses on finding evidence of asymmetries in data to improve classifier performance in both in-distribution and out-of-distribution scenarios. Asymmetry Learning performs a causal structure search to find classifiers that perform well across different environments. Why it matters: This research addresses a key challenge in AI by proposing a novel approach to improve the reliability and generalization of classifiers in unseen environments, potentially leading to more robust AI systems.
KAUST research engineer Samy Ould-Chikh is collaborating with the Néel Institute-CNRS at the European Synchrotron Radiation Facility (ESRF) in France. They are using the ESRF's high-energy synchrotron light source to study the inner structure of matter at the atomic and molecular levels. Ould-Chikh's research focuses on catalysis and functional materials, with an emphasis on renewable energy and photocatalysis. Why it matters: This collaboration highlights KAUST's engagement with leading international research institutions to advance materials science and energy research.
Ahmed Elhag, a PhD student at the University of Oxford, presented a new training procedure that approximates equivariance in unconstrained machine learning models via a multitask objective. The approach adds an equivariance loss to unconstrained models, allowing them to learn approximate symmetries without the computational cost of fully equivariant methods. Formulating equivariance as a flexible learning objective allows control over the extent of symmetry enforced, matching the performance of strictly equivariant baselines at a lower cost. Why it matters: This research from a speaker at MBZUAI balances rigorous theory and practical scalability in geometric deep learning, potentially accelerating drug discovery and design.
KAUST and the Saudi Food and Drug Authority (SFDA) have partnered to develop a new method using nuclear magnetic resonance (NMR) to detect adulterants in olive oil. The method aims to identify and quantify vegetable oils mixed with olive oil, addressing concerns about the mislabeling of olive oil in the Saudi market. KAUST's comprehensive suite of NMR machines was critical for the project. Why it matters: This collaboration enhances food safety and quality control in Saudi Arabia, a major olive oil importer, and helps to ensure consumers receive authentic, high-quality products.
KAUST alumnus Dr. Muhammed Sameed works at CERN on the ALPHA project, studying antimatter. The project aims to understand why there is so little antimatter in the universe, given that physics equations predict equal amounts of matter and antimatter. Sameed's work involves creating, trapping, and studying antimatter particles in a controlled lab environment. Why it matters: This research advances our understanding of fundamental physics and the composition of the universe, with a KAUST alumnus playing a key role.
KAUST alumnus Muhammed Sameed, who completed his master's degree in material science and engineering in 2012, works at CERN on the ALPHA experiment, which uses lasers to measure the properties of anti-hydrogen. Researchers at CERN are investigating the fundamental structure of the universe, including the absence of anti-matter. Current research indicates that every process that creates matter also creates anti-matter in the same amount, which does not align with the observable universe. Why it matters: This highlights KAUST's role in training scientists who contribute to cutting-edge research in fundamental physics, even at international facilities like CERN.
The 34th General Assembly and Scientific Symposium (GASS) of the International Union of Radio Science (URSI) will be held in Rome from August 28 to September 4. The Technology Innovation Institute’s Directed Energy Research Center (DERC), led by Dr Chaouki Kasmi, will present a tutorial and five scientific papers. DERC's presentations will focus on advances in electromagnetics and optoelectronics. Why it matters: DERC's participation highlights the UAE's growing role in international radio science research and development.