Related papers: The Stellar Transformation: From Interconnection N…
Recent studies have drawn attention to the untapped potential of the "star operation" (element-wise multiplication) in network design. While intuitive explanations abound, the foundational rationale behind its application remains largely…
A new network named the "Digital Twin Network" (DTN) uses the "Digital Twin" (DT) technology to produce virtual twins of real things. The network load and size continue to grow as a result of the development of 5G, the Internet of Things,…
We explore a new class of diffusion models based on the transformer architecture. We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the…
Classical Internet evolved exceptionally during the last five decades, from a network comprising a few static nodes in the early days to a leviathan interconnecting billions of devices. This has been possible by the separation of concern…
Deep learning methods have demonstrated outstanding performances on classification and regression tasks on homogeneous data types (e.g., image, audio, and text data). However, tabular data still pose a challenge, with classic machine…
Conditional computation is a popular strategy to make Transformers more efficient. Existing methods often target individual modules (e.g., mixture-of-experts layers) or skip layers independently of one another. However, interpretability…
Convolutional neural networks (CNNs) have achieved great successes in many computer vision problems. Unlike existing works that designed CNN architectures to improve performance on a single task of a single domain and not generalizable, we…
In this paper, we present STAR, a new distributed in-memory database with asymmetric replication. By employing a single-node non-partitioned architecture for some replicas and a partitioned architecture for other replicas, STAR is able to…
Transformer architectures, particularly Diffusion Transformers (DiTs), have become widely used in diffusion and flow-matching models due to their strong performance compared to convolutional UNets. However, the isotropic design of DiTs…
We consider a distributed antenna system where $L$ antenna terminals (ATs) are connected to a Central Processor (CP) via digital error-free links of finite capacity $R_0$, and serve $L$ user terminals (UTs). This system model has been…
Interconnecting well-functioning, scalable stationary qubits and photonic qubits could substantially advance quantum communication applications and serve to link future quantum processors. Here, we present two protocols for transferring the…
This document is a result of the COOCK project "Smart Port 2025: improving and accelerating the operational efficiency of a harbour eco-system through the application of intelligent technologies". It reports on the needs of companies for…
The development of a future, global quantum communication network (or quantum internet) will enable high rate private communication and entanglement distribution over very long distances. However, the large-scale performance of ground-based…
Top-tier parallel computing clusters continue to accumulate more and more computational power with more and better CPUs and Networks. This allows, especially for environmental simulations, computations with larger domain sizes and better…
Multi-core quantum computing architectures offer a promising and scalable solution to the challenges of integrating large number of qubits into existing monolithic chip design. However, the issue of transferring quantum information across…
The advance of direct satellite-to-device communication has positioned mega-satellite constellations as a cornerstone of 6G wireless communication, enabling seamless global connectivity even in remote and underserved areas. However,…
We use Deep Operator Networks (DeepONets) to perform super-resolution reconstruction of the solutions of two types of partial differential equations and compare the model predictions with the results obtained using conventional…
Building large models with parameter sharing accounts for most of the success of deep convolutional neural networks (CNNs). In this paper, we propose doubly convolutional neural networks (DCNNs), which significantly improve the performance…
Targeted attacks against network infrastructure are notoriously difficult to guard against. In the case of communication networks, such attacks can leave users vulnerable to censorship and surveillance, even when cryptography is used. Much…
Graph Convolutional Networks (GCNs) have shown to be effective in handling unordered data like point clouds and meshes. In this work we propose novel approaches for graph convolution, pooling and unpooling, inspired from finite differences…