Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from crit...
In this paper, we propose a Differentially Private Stochastic Gradient Push with Compressed communication (termed DP-CSGP) for decentralized learning over direc...
Denoising language models (DLMs) have been proposed as a powerful alternative to traditional language models (LMs) for automatic speech recognition (ASR), motiv...
Large Mixture-of-Experts (MoE) model inference is challenging due to high resource demands and dynamic workloads. Existing solutions often deploy the entire mod...
Much of software engineering (SE) research assumes that progress depends on massive datasets and CPU-intensive optimizers. Yet has this assumption been rigorous...
The study presents the outcomes of research and experimental validation in the domain of automated codebase migration, with a focus on addressing challenges in ...
An increasing variety of AI accelerators is being considered for large-scale training. However, enabling large-scale training on early-life AI accelerators face...
The global climate is experiencing a rapid and unprecedented warming trend. The ICT sector is a notable contributor to global greenhouse gas emissions, with its...
With the rise of AI-enabled cyber-physical systems, data annotation has become a critical yet often overlooked process in the development of these intelligent i...
While Large Language Model (LLM) agents show great potential for automated UI navigation such as automated UI testing and AI assistants, their efficiency has be...
Unlike classical software, where logging and runtime tracing can effectively reveal internal execution status, quantum circuits possess unique properties, such ...
Metamorphic testing (MT) alleviates the oracle problem by checking metamorphic relations (MRs) across multiple test executions. The fault detection effectivenes...
Use cases are widely employed to specify functional requirements, yet existing benchmarks are scarce and face the risk of being misaligned with actual system be...
This paper proposes a parallel-in-time method for computing continuous-time maximum-a-posteriori (MAP) trajectory estimates of the states of partially observed ...
High-performance computing (HPC) clusters consume enormous amounts of energy, with idle nodes as a major source of waste. Powering down unused nodes can mitigat...
Blockchain technology is gaining momentum across many sectors. Whereas blockchain solutions have important positive effects on the business domain, they also in...
With the rise of cryptocurrencies, many new applications built on decentralized blockchains have emerged. Blockchains are full-stack distributed systems where m...
We investigate adaptive minimal routing in 2D torus networks on chip NoCs under node fault conditions comparing a reinforcement learning RL based strategy to an...
The scaling of computation throughput continues to outpace improvements in memory bandwidth, making many deep learning workloads memory-bound. Kernel fusion is ...
Article URL: https://cordis.europa.eu/article/id/462587-from-sci-fi-to-reality-researchers-realise-quantum-teleportation-using-today-s-internet-tech Comments UR...
Black-box optimization often relies on evolutionary and swarm algorithms whose performance is highly problem dependent. We view an optimizer as a short program ...
Control policies in deep reinforcement learning are often implemented with fixed-capacity multilayer perceptrons trained by backpropagation, which lack structur...
Efforts to improve Kolmogorov-Arnold networks (KANs) with architectural enhancements have been stymied by the complexity those enhancements bring, undermining t...
Memristor-based in-memory computing has emerged as a promising paradigm to overcome the constraints of the von Neumann bottleneck and the memory wall by enablin...
