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.
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.
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.
Antonio Adamo is an assistant professor of bioscience in the Biological and Environmental Science and Engineering Division at KAUST. He is highlighted in a KAUST faculty focus. Why it matters: Showcases KAUST's faculty expertise in bioscience.
KAUST has announced a collaboration with Ocean Aero and Shelf Subsea to enhance Red Sea research using autonomous underwater and surface vehicles (AUSVs). Ocean Aero's Triton Generation III AUSV, which can sail and submerge for long-range data collection, will be customized with sensors for KAUST's Red Sea Research Center. KAUST's CEMSE division will integrate AI and IoT features into the vehicles. Why it matters: This partnership will advance KAUST's marine research capabilities and contribute to the understanding of the Red Sea's unique environment, aligning with Saudi Arabia's Vision 2030 and the UN's Ocean Science Decade.