AIDRC researchers co-authored an accepted IEEE Vehicular Technology Magazine article on time reversal for 6G wireless communications. The article presents experimental results on the spatiotemporal focusing capability of time reversal across carrier frequencies. It examines requirements for efficient time reversal operation and synergies with technologies like reconfigurable intelligent surfaces. Why it matters: The research explores advancements in 6G wireless communication, with potential implications for coverage extension, sensing, and localization capabilities in the region.
MBZUAI researchers identified 'self-referencing causal cycles' in LLM training data that can mitigate the 'reversal curse,' where LLMs struggle with information presented in reverse order. The study, to be presented at ACL, explains that the transformer architecture's unidirectional token generation causes this issue. By leveraging the repetitive nature of information in training texts, the team developed an efficient solution to improve LLM performance. Why it matters: Overcoming the reversal curse can significantly enhance LLM accuracy and reliability, especially in tasks requiring bidirectional reasoning and understanding of context.
This paper introduces rational counterfactuals, a method for identifying counterfactuals that maximize the attainment of a desired consequent. The approach aims to identify the antecedent that leads to a specific outcome for rational decision-making. The theory is applied to identify variable values that contribute to peace, such as Allies, Contingency, Distance, Major Power, Capability, Democracy, and Economic Interdependency. Why it matters: The research provides a framework for analyzing and promoting conditions conducive to peace using counterfactual reasoning.
MBZUAI Professor Kun Zhang received a Test of Time Award Honorable Mention at ICML 2022 for his 2012 paper “On causal and anticausal learning." The paper, co-authored with researchers from the Max-Planck Institute, is considered foundational for causal learning in machine learning. Zhang's work demonstrated the importance of causality for machine learning tasks, helping to shift views in the field. Why it matters: This award highlights the growing recognition of causal AI research and MBZUAI's role in advancing the field.
J. Carlos Santamarina, a Professor of Earth Science and Engineering at KAUST, is researching geomaterial behavior and subsurface processes. His work focuses on energy geo-engineering, resource recovery, and geological storage of energy waste. He uses particle-level experiments, numerical methods, and monitoring systems to understand coupled thermo-hydro-bio-chemo-mechanically processes. Why it matters: This research contributes to energy sustainability and addresses global energy challenges through advanced geotechnology.
KAUST's Extreme Computing Research Center (ECRC) developed Multiple Object Adaptive Optics (MOAO) software. The software will contribute to the activities of the world's largest future optical telescope to be deployed in Chile in 2024. MOAO will eliminate atmospheric noise and enable simultaneous observation of multiple objects at different distances. Why it matters: This contribution highlights KAUST's role in cutting-edge astronomical research and positions the Middle East as a key player in advancing observational astronomy.
KAUST researchers are studying ancient supervolcanoes, like the Toba eruption 75,000 years ago, to understand current and future climate conditions. Volcanic eruptions serve as natural experiments that push the climate system to its limits, helping scientists understand climate's physical mechanisms. Research shows that volcanic eruptions delayed global warming by about 30% starting from 1850. Why it matters: Understanding the impact of volcanic activity on climate change can improve predictions of future global warming, particularly in regions like the Middle East which are strongly affected by volcanic events.
This paper introduces Diffusion-BBO, a new online black-box optimization (BBO) framework that uses a conditional diffusion model as an inverse surrogate model. The framework employs an Uncertainty-aware Exploration (UaE) acquisition function to propose scores in the objective space for conditional sampling. The approach is shown theoretically to achieve a near-optimal solution and empirically outperforms existing online BBO baselines across 6 scientific discovery tasks.