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.
This paper introduces Adaptive Entropy-aware Optimization (AEO), a new framework to tackle Multimodal Open-set Test-time Adaptation (MM-OSTTA). AEO uses Unknown-aware Adaptive Entropy Optimization (UAE) and Adaptive Modality Prediction Discrepancy Optimization (AMP) to distinguish unknown class samples during online adaptation by amplifying the entropy difference between known and unknown samples. The study establishes a new benchmark derived from existing datasets with five modalities and evaluates AEO's performance across various domain shift scenarios, demonstrating its effectiveness in long-term and continual MM-OSTTA settings.
A delegation from the Abu Dhabi Executive Office (ADEO) Education Affairs Department visited MBZUAI on December 15, 2021. Ian Mathews, VP of Corporate Services, presented MBZUAI's progress and 2022 initiatives. Discussions covered the importance of collaboration and recruitment enhancements with ADEO's support. Why it matters: This visit highlights the ongoing relationship between MBZUAI and key Abu Dhabi government entities, signaling continued support for the university's AI initiatives.
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.
Mo Li, an assistant professor of bioscience, is featured in a faculty focus article by KAUST. The article appears on the university's Biological and Environmental Science and Engineering Division page. Why it matters: This highlights KAUST's ongoing efforts to showcase faculty expertise and research areas within the university.
The paper introduces Yet another Policy Optimization (YaPO), a reference-free method for learning sparse steering vectors in the latent space of a Sparse Autoencoder (SAE) to steer LLMs. By optimizing sparse codes, YaPO produces disentangled, interpretable, and efficient steering directions. Experiments show YaPO converges faster, achieves stronger performance, exhibits improved training stability and preserves general knowledge compared to dense steering baselines.
Researchers from MBZUAI have introduced VideoMolmo, a large multimodal model for spatio-temporal pointing conditioned on textual descriptions. The model incorporates a temporal module with an attention mechanism and a temporal mask fusion pipeline using SAM2 for improved coherence across video sequences. They also curated a dataset of 72k video-caption pairs and introduced VPoS-Bench, a benchmark for evaluating generalization across real-world scenarios, with code and models publicly available.