arXiv ·
MBZUAI researchers have introduced MIRA, a novel framework for improving the factual accuracy of multimodal large language models in medical applications. MIRA uses calibrated retrieval to manage factual risk and integrates image embeddings with a medical knowledge base for efficient reasoning. Evaluated on medical VQA and report generation benchmarks, MIRA achieves state-of-the-art results, with code available on GitHub.
KAUST ·
The Red Sea Development Company (TRSDC) and KAUST have signed a Master Research Agreement (MRA) to collaborate on sustainability research. Prior collaborations included flora and fauna assessments and the Brains-for-Brine Challenge. The MRA focuses on marine environments, waste management, food production, energy conservation, and carbon sequestration. Why it matters: This partnership aims to develop regenerative tourism practices, preserve the Red Sea's biodiversity, and establish a model for sustainable tourism in the region.
KAUST ·
KAUST and Boeing renewed their Master Research Agreement (MRA) on September 1. The agreement aims to boost collaborative research on next-generation aerospace technologies. The renewed MRA signifies a continued partnership between the Saudi university and the American aerospace company. Why it matters: This agreement can foster innovation in aerospace within Saudi Arabia and aligns with the Kingdom's broader technology development goals.
arXiv ·
Researchers from MBZUAI have developed MMRINet, a Mamba-based neural network for efficient brain tumor segmentation in MRI scans. The model uses Dual-Path Feature Refinement and Progressive Feature Aggregation to achieve high accuracy with only 2.5M parameters, making it suitable for low-resource clinical environments. MMRINet achieves a Dice score of 0.752 and HD95 of 12.23 on the BraTS-Lighthouse SSA 2025 benchmark.