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 the concept of Arabic Level of Dialectness (ALDi), a continuous variable representing the degree of dialectal Arabic in a sentence, arguing that Arabic exists on a spectrum between MSA and DA. They present the AOC-ALDi dataset, comprising 127,835 sentences manually labeled for dialectness level, derived from news articles and user comments. Experiments show a model trained on AOC-ALDi can identify dialectness levels across various corpora and genres. Why it matters: ALDi provides a more nuanced approach to analyzing Arabic text than binary dialect identification, enabling sociolinguistic analysis of stylistic choices.
Dr. Hao Dong from Peking University presented research on addressing the challenge of limited large-scale training data in embodied AI, particularly for manipulation, task planning, and navigation. The presentation covered simulation learning and large models. Dr. Dong is a chief scientist of China's National Key Research and Development Program and an area chair/associate editor for NeurIPS, CVPR, AAAI, and ICRA. Why it matters: Overcoming data scarcity is crucial for advancing embodied AI research and enabling more sophisticated robotic applications in the region.
Oman Data Park (ODP) has deployed groundbreaking NVIDIA H200 GPUs to revolutionize its AI infrastructure. This upgrade is set to significantly enhance the processing capabilities available for artificial intelligence workloads within Oman. The move positions ODP to offer more advanced and powerful computing resources to its clients and partners. Why it matters: This deployment could substantially boost Oman's AI ecosystem, attracting advanced AI projects and fostering innovation in the region.
Dr. Abdelrahman AlMahmoud from TII's Secure Systems Research Center (SSRC) will participate in a WGISTA webinar on adopting a digital mindset in auditing and fighting corruption. The webinar, organized by the International Organization of Supreme Audit Institutions (INTOSAI), will discuss the impact of emerging technologies on public sector auditing. Dr. AlMahmoud will share insights on how AI and Big Data can enable auditors to process data at a new scale. Why it matters: This highlights the UAE's growing role in applying advanced technologies like AI and big data to improve governance and accountability in the public sector.
KAUST startup uODS signed an MoU with Saudi Aramco Base Oil Company (Luberef) to develop and deploy technology removing sulfur from hydrocarbons. The uODS process, based on KAUST's sonochemistry research, reduces sulfur in marine fuels to meet IMO 2020 regulations. Luberef aims to reduce its environmental footprint by piloting the uODS technology at its Jeddah refineries, with uODS set to produce 10 tons per day of desulfurized fuel for testing. Why it matters: The partnership demonstrates KAUST's role in addressing Saudi Arabia's environmental goals and showcases the potential of university spin-offs to contribute to a more sustainable oil industry in the region.