MBZUAI researchers developed FarSight, a plugin to reduce hallucinations in Multimodal Large Language Models (MLLMs). FarSight addresses the issue where MLLMs generate inaccurate text by losing focus on relevant image details, leading to snowball hallucinations. Testing on models like LLaVA-1.5-7B showed FarSight's effectiveness in reducing initial mistakes, thereby minimizing overall hallucinations. Why it matters: Improving the reliability of MLLMs is crucial for applications requiring high accuracy, enhancing their utility in various real-world scenarios.
MBZUAI Professor Fahad Khan is working on a unified theory of machine visual intelligence. His goal is to enable AI systems to better understand and function in complex, chaotic visual environments. The aim is to improve real-world applications like smart cities, personalized healthcare, and autonomous vehicles. Why it matters: This research could significantly advance AI's ability to perceive and interact with the real world, especially in challenging environments common in the developing world.
A new benchmark, LongShOTBench, is introduced for evaluating multimodal reasoning and tool use in long videos, featuring open-ended questions and diagnostic rubrics. The benchmark addresses the limitations of existing datasets by combining temporal length and multimodal richness, using human-validated samples. LongShOTAgent, an agentic system, is also presented for analyzing long videos, with both the benchmark and agent demonstrating the challenges faced by state-of-the-art MLLMs.
KAUST Professor Wolfgang Heidrich is researching computational imaging systems that jointly design optics and image reconstruction algorithms. He focuses on hardware-software co-design for imaging systems with applications in HDR, compact cameras, and hyperspectral imaging. Heidrich's work on HDR displays was the basis for Brightside Technologies, acquired by Dolby in 2007. Why it matters: This research aims to advance imaging technology through AI-driven design, potentially impacting various fields from consumer electronics to scientific research within the region and globally.
Yanwei Fu from Fudan University will present research on multimodal models, robotic grasping, and fMRI neural decoding. Topics include few-shot learning, object-centered self-supervised learning, image manipulation, and visual-language alignment. The research also covers Transformer compression and applications of large models with MVS 3D modeling in robotic arm grasping. Why it matters: While the talk is not directly about Middle East AI, the topics covered are core to advancing AI research and applications in the region.
Pong C Yuen from Hong Kong Baptist University will present a talk on remote photoplethysmography (rPPG) detection. The talk will review the development of rPPG detection, share recent research, and discuss future directions. rPPG is a technology for non-contact computer vision and healthcare applications like heart rate estimation. Why it matters: Advancements in rPPG could enable new remote patient monitoring and diagnostic tools in the region, reducing the need for physical contact.