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.
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.
Pascal Fua from EPFL presented an approach to implementing convolutional neural nets that output complex 3D surface meshes. The method overcomes limitations in converting implicit representations to explicit surface representations. Applications include single view reconstruction, physically-driven shape optimization, and bio-medical image segmentation. Why it matters: This research advances geometric deep learning by enabling end-to-end trainable models for 3D surface mesh generation, with potential impact on various applications in computer vision and biomedical imaging in the region.
Nobuyuki Umetani from the University of Tokyo presented a talk on using AI to accelerate simulations and optimization for 3D shape designs. The talk covered interactive approaches integrating physical simulation into geometric modeling. Specific applications discussed included musical instruments, garment design, aerodynamic design, and floor plan design. Why it matters: This highlights growing interest in AI techniques at MBZUAI and across the GCC for streamlining engineering design and simulation processes.
Artists from Switzerland collaborated with researchers at KAUST's Red Sea Research Center to photograph autonomous reef monitoring structures (ARMS). ARMS are artificial towers that capture small critters colonizing coral reefs, developed to measure marine biodiversity. KAUST has deployed and retrieved over 180 ARMS units since 2013 to study cryptobenthic biodiversity, which represents up to 70% of a reef's biodiversity. Why it matters: This collaboration highlights the innovative approaches being used to study marine ecosystems in the Red Sea and underscores the importance of interdisciplinary collaborations in advancing scientific understanding.
This article discusses KAUST's presence at the 252nd American Chemical Society Meeting & Exposition in Philadelphia, PA. A KAUST team consisting of staff, students, and faculty attended the event. The article includes a photo from the event and standard KAUST copyright information. Why it matters: This highlights KAUST's efforts to engage with the international scientific community and showcase its research and educational programs.