KAUST researchers collaborated with the Paris Observatory and the National Astronomical Observatory of Japan (NAOJ) to develop advanced Extreme-AO algorithms for habitable exoplanet imaging. The new algorithms, powered by KAUST's linear algebra code running on NVIDIA GPUs, optimize and anticipate atmospheric disturbances. The implemented Singular Value Decomposition (SVD) algorithm won an award at the PASC Conference 2018 and is used at the Subaru Telescope in Hawaii. Why it matters: This advancement enhances the ability to image exoplanets, potentially leading to breakthroughs in the search for habitable planets using ground-based telescopes.
KAUST researchers developed a machine learning algorithm to control a deformable mirror within the Subaru Telescope's exoplanet imaging camera, compensating for atmospheric turbulence. The algorithm, which computes a partial singular value decomposition (SVD), outperforms a standard SVD by a factor of four. The KAUST team received a best paper award at the PASC Conference for this work, which has already been deployed at the Subaru Telescope. Why it matters: This advancement enables sharper images of exoplanets, facilitating their identification and study, and showcases the impact of optimizing core linear algebra algorithms.
A novel wind speed forecasting (WSF) framework is proposed combining Wavelet Packet Decomposition (WPD), Seasonal Adjustment Method (SAM), and Bidirectional Long Short-term Memory (BiLSTM). The SAM method eliminates the seasonal component of the decomposed subseries generated by WPD to reduce forecasting complexity. The model was tested on five years of hourly wind speed observations acquired from the Dumat Al-Jandal wind farm in Al-Jouf, Saudi Arabia, achieving high forecasting accuracy.
KAUST researchers have developed a method using high-intensity pulses of light to remove carbon-based organic micropollutants from wastewater. By using a pulsed light system previously used for semiconductor materials, the team dramatically accelerated the photodegradation treatment. The high-intensity pulsed light (HIPL) triggers decomposition of organic micropollutants (OMPs) with extraordinary degradation rates within milliseconds. Why it matters: This treatment offers a potentially scalable solution to the increasing environmental problem of OMPs in waterways, addressing a critical need in water treatment technologies for the region.
A KAUST-led team in collaboration with Japan's National Institute of Informatics and Cray Inc. has implemented a new algorithm to harness the power of supercomputers. The algorithm integrates new singular value decomposition (SVD) codes into Cray LibSci scientific libraries, supporting machine learning and data de-noising applications. This was achieved through the Cray Center of Excellence (CCOE) at KAUST, established in 2015. Why it matters: The new algorithm helps to optimize the use of advanced supercomputing infrastructure in the region, specifically KAUST's Shaheen II, for computationally intensive AI applications.
KAUST Ph.D. student Lukas Larisch won the Parameterized Algorithms and Computational Experiments (PACE) 2017 Challenge in the Optimal Tree Decomposition Challenge, solving more instances than competitors. He received the award at the International Symposium on Parameterized and Exact Computation (IPEC 2017) in Vienna, Austria. Larisch is pursuing his Ph.D. at KAUST and working in the University's Extreme Computing Research Center, focusing on acoustics and graph structure theory. Why it matters: This recognition highlights KAUST's contribution to advanced computer science research and its ability to attract and foster talented researchers in niche areas like parameterized complexity.
MBZUAI researchers presented new resources at EMNLP for improving the factuality of LLMs, including a web application for fact-checking LLM-generated text and benchmarks for evaluating automated fact-checkers. They found that current automated fact-checkers miss nearly 40% of false claims generated by LLMs. The study breaks down the fact-checking process into eight tasks, including decomposition and decontextualization, to identify where systems fail. Why it matters: This work addresses a critical challenge in the deployment of LLMs by providing tools and methods for improving their reliability and trustworthiness, which is essential for widespread adoption in sensitive applications.
MBZUAI's Samuel Horváth presented a new framework called Maestro at ICML 2024 for efficiently training machine learning models in federated settings. Maestro identifies and removes redundant components of a model through trainable decomposition to increase efficiency on edge devices. The approach decomposes layers into low-dimensional approximations, discarding unused aspects to reduce model size. Why it matters: This research addresses the challenge of running complex models on resource-constrained devices, crucial for expanding AI applications while preserving data privacy.