Related papers: Naeural AI OS -- Decentralized ubiquitous computin…

Large Language Models (LLMs) have demonstrated remarkable language understanding and generation capabilities. However, training, deploying, and accessing these models pose notable challenges, including resource-intensive demands, extended…

Compound AI Systems, integrating multiple interacting components like models, retrievers, and external tools, have emerged as essential for addressing complex AI tasks. However, current implementations suffer from inefficient resource…

Multimodal artificial intelligence (AI) integrates diverse types of data via machine learning to improve understanding, prediction, and decision-making across disciplines such as healthcare, science, and engineering. However, most…

As artificial intelligence, machine learning, and data science continue to drive the data-centric economy, the challenges of implementing machine learning on a single machine due to extensive data and computational needs have led to the…

Edge computing is a promising solution to enable low-latency IoT applications, by shifting computation from remote data centers to local devices, less powerful but closer to the end user devices. However, this creates the challenge on how…

Future AI applications require performance, reliability and privacy that the existing, cloud-dependant system architectures cannot provide. In this article, we study orchestration in the device-edge-cloud continuum, and focus on edge AI for…

The cloud-based solutions are becoming inefficient due to considerably large time delays, high power consumption, security and privacy concerns caused by billions of connected wireless devices and typically zillions bytes of data they…

The rapid advancement of ML models in critical sectors such as healthcare, finance, and security has intensified the need for robust data security, model integrity, and reliable outputs. Large multimodal foundational models, while crucial…

Significant investments to upgrade and construct large-scale scientific facilities demand commensurate investments in R&D to design algorithms and computing approaches to enable scientific and engineering breakthroughs in the big data era.…

The disruptive potential of AI systems roots in the emergence of big data. Yet, a significant portion is scattered and locked in data silos, leaving its potential untapped. Federated Machine Learning is a novel AI paradigm enabling the…

The emerging trend of ubiquitous and pervasive computing aims at embedding everyday devices such as wristwatches, smart phones, home video systems, autofocus cameras, intelligent vehicles, musical instruments, kitchen appliances etc. with…

Machine Learning (ML) DevOps, also known as MLOps, has emerged as a critical framework for efficiently operationalizing ML models in various industries. This study investigates the adoption trends, implementation efforts, and benefits of ML…

The Universal Basic Computing Power (UBCP) initiative ensures global, free access to a set amount of computing power specifically for AI research and development (R&D). This initiative comprises three key elements. First, UBCP must be cost…

Collective animal behaviors are paradigmatic examples of fully decentralized operations involving complex collective computations such as collective turns in flocks of birds or collective harvesting by ants. These systems offer a unique…

Resource-constrained IoT devices, such as sensors and actuators, have become ubiquitous in recent years. This has led to the generation of large quantities of data in real-time, which is an appealing target for AI systems. However,…

Credible commitment devices have been a popular approach for robust multi-agent coordination. However, existing commitment mechanisms face limitations like privacy, integrity, and susceptibility to mediator or user strategic behavior. It is…

The rapid evolution of embedded systems, along with the growing variety and complexity of AI algorithms, necessitates a powerful hardware/software co-design methodology based on virtual prototyping technologies. The market offers a diverse…

This article introduces our vision for a new interaction paradigm: Heads-Up Computing, a concept involving the provision of seamless computing support for daily activities. Its synergistic and user-centric approach frees humans from common…

In our everyday life, we intuitively use space to regulate our social interactions. When we want to talk to someone, we approach them; if someone joins the conversation, we adjust our bodies to make space for them. In contrast, devices are…

Emerging AI applications such as ChatGPT, graph convolutional networks, and other deep neural networks require massive computational resources for training and inference. Contemporary computing platforms such as CPUs, GPUs, and TPUs are…