Related papers: Reproducibility, energy efficiency and performance…
AI-Hybrid TRNG is a deep-learning framework that extracts near-uniform entropy directly from physical noise, eliminating the need for bulky quantum devices or expensive laboratory-grade RF receivers. Instead, it relies on a low-cost,…
$\textit{RigL}$, a sparse training algorithm, claims to directly train sparse networks that match or exceed the performance of existing dense-to-sparse training techniques (such as pruning) for a fixed parameter count and compute budget. We…
In recent years, numerous incidents involving the leakage of website accounts and text passwords (referred to as passwords) have raised significant concerns regarding the potential exposure of personal information. These events underscore…
Machine learning (ML) has been widely used in the literature to automate software engineering tasks. However, ML outcomes may be sensitive to randomization in data sampling mechanisms and learning procedures. To understand whether and how…
The advent of Large Language Models (LLMs) has significantly advanced the field of automated code generation. LLMs rely on large and diverse datasets to learn syntax, semantics, and usage patterns of programming languages. For low-resource…
In this paper, a new chaotic pseudo-random number generator (PRNG) is proposed. It combines the well-known ISAAC and XORshift generators with chaotic iterations. This PRNG possesses important properties of topological chaos and can…
Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored. Previous approaches, such as generative classifiers, have…
Recent advancements in improving the reasoning capabilities of Large Language Models have underscored the efficacy of Process Reward Models (PRMs) in addressing intermediate errors through structured feedback mechanisms. This study analyzes…
Throughout the last years, machine learning techniques have been broadly encouraged in the context of deep learning architectures. An exciting algorithm denoted as Restricted Boltzmann Machine relies on energy- and probabilistic-based…
Pre-trained language models (PLMs) have become a prevalent technique in deep learning for code, utilizing a two-stage pre-training and fine-tuning procedure to acquire general knowledge about code and specialize in a variety of downstream…
Hardware generation languages (HGLs) increase hardware design productivity by creating parameterized modules and test benches. Unfortunately, existing tools are not widely adopted due to several demerits, including limited support for…
As large language models (LLMs) scale in size and adoption, their computational and environmental costs continue to rise. Prior benchmarking efforts have primarily focused on latency reduction in idealized settings, often overlooking the…
The security of many cryptographic constructions depends on random number generators for providing unpredictable keys, nonces, initialization vectors and other parameters. Modern operating systems implement cryptographic pseudo-random…
This study aims to enhance the maintainability of code generated by Large Language Models (LLMs), with a focus on the Python programming language. As the use of LLMs for coding assistance grows, so do concerns about the maintainability of…
Reproduction studies reported in NLP provide individual data points which in combination indicate worryingly low levels of reproducibility in the field. Because each reproduction study reports quantitative conclusions based on its own,…
Parallel stochastic simulations tend to exploit more and more computing power and they are now also developed for General Purpose Graphics Process Units (GP-GPUs). Conse-quently, they need reliable random sources to feed their applications.…
There are various notions of quantum pseudorandomness, such as pseudorandom unitaries (PRUs), pseudorandom state generators (PRSGs) and pseudorandom function-like state generators (PRFSGs). Unlike classical pseudorandomness, where different…
Random number generation (RNG) is a crucial element in security protocols, and its performance and reliability are critical for the safety and integrity of digital systems. This is especially true in 5G networks with many devices with low…
The replicability crisis in the social, behavioral, and data sciences has led to the formulation of algorithm frameworks for replicability -- i.e., a requirement that an algorithm produce identical outputs (with high probability) when run…
Large Language Models (LLMs) continue to demonstrate superior performance with increasing scale, yet training models with billions to trillions of parameters requires staggering computational resources, e.g. a one-trillion-parameter…