TII's Secure Systems Research Center (SSRC) has become a strategic member of RISC-V International to advance the development of open-source Instruction Set Architecture (ISA) for computer chips. SSRC aims to contribute to the RISC-V community by developing security and resilience features in processors and platforms, fostering innovation in end-to-end security. SSRC will conduct open source research to secure communications between edge devices and cloud infrastructure, and harden device hardware and software to prevent malware. Why it matters: This move enables the UAE to have greater control and independence in computing platform design, reducing reliance on proprietary architectures and enhancing security and resilience in critical infrastructure.
MBZUAI researchers developed Mobile-VideoGPT, a compact and efficient multimodal model for real-time video understanding on edge devices. The system uses keyframe selection, efficient token projection, and a Qwen-2.5-0.5B language model. Testing showed that Mobile-VideoGPT is faster and performs better than other models while being significantly smaller, and the model and code are publicly available. Why it matters: This research enables on-device AI processing for video, reducing reliance on remote servers and addressing privacy concerns, which can accelerate the adoption of AI in mobile and embedded applications.
The Secure Systems Research Center (SSRC) has partnered with the University of New South Wales (UNSW Sydney) to research enhancements and scaling of the seL4 microkernel on edge devices. The collaboration aims to extend the seL4 microkernel to support dynamic virtualization, combining minimal trusted computing base with strong isolation. This will address challenges related to heterogeneous hardware, software, and environmental factors in edge computing. Why it matters: This partnership aims to improve the security of edge devices in critical sectors, addressing vulnerabilities in cyber-physical and autonomous systems.
The Secure Systems Research Center (SSRC) has obtained membership in the seL4 Foundation. This membership allows SSRC to participate in and contribute to the open-source development of seL4, a formally verified microkernel OS. SSRC aims to research, contribute to, and advance next-generation high-end edge device environments using seL4's capabilities. Why it matters: This move enhances the UAE's capabilities in developing secure and resilient edge computing solutions, fostering innovation in critical sectors like secure communications and drone technology.
MBZUAI graduate Daniel Gebre from Eritrea has developed iShrink, a compression pipeline that reduces the size of LLMs to run offline on mobile phones and edge devices. Gebre's master's thesis focused on enabling access to cutting-edge AI without requiring internet access, motivated by his experience in under-resourced regions. His journey to MBZUAI began with a Merit Scholarship awarded by the UAE Ministry of Education, leading him to pursue a Master of Science in Machine Learning. Why it matters: This research has the potential to democratize access to AI in areas with limited internet connectivity, particularly in regions like Gebre's homeland, Eritrea.
Muhammad Shafique from NYU Abu Dhabi discusses building energy-efficient and robust EdgeAI systems. The talk covers trends, challenges, and techniques for optimizing software and hardware stacks. These optimizations aim to enable embodied AI in autonomous systems, IoT-Healthcare, Industrial-IoT, and smart environments. Why it matters: The research addresses key challenges in deploying AI on resource-constrained edge devices in the GCC region, particularly regarding energy efficiency and security.
Researchers at National Taiwan University are developing low-complexity neural network technologies using quantization to reduce model size while maintaining accuracy. Their work includes binary-weighted CNNs and transformers, along with a neural architecture search scheme (TPC-NAS) applied to image recognition, object detection, and NLP tasks. They have also built a PE-based CNN/transformer hardware accelerator in Xilinx FPGA SoC with a PyTorch-based software framework. Why it matters: This research provides practical methods for deploying efficient deep learning models on resource-constrained hardware, potentially enabling broader adoption of AI in embedded systems and edge devices.
MBZUAI's Samuel Horváth presented a new framework called Maestro at ICML 2024 for efficiently training machine learning models in federated settings. Maestro identifies and removes redundant components of a model through trainable decomposition to increase efficiency on edge devices. The approach decomposes layers into low-dimensional approximations, discarding unused aspects to reduce model size. Why it matters: This research addresses the challenge of running complex models on resource-constrained devices, crucial for expanding AI applications while preserving data privacy.