Related papers: Reliable Access to Massive Restricted Texts: Exper…
It is imperative to safeguard computer applications and information systems against the growing number of cyber-attacks. Automated software testing tools can be developed to quickly analyze many lines of code and detect vulnerabilities by…
Searching large digital repositories can be extremely frustrating, as common list-based formats encourage users to adopt a convenience-sampling approach that favours chance discovery and random search, over meaningful exploration. We have…
Substantial amounts of work are required to clean large collections of digitized books for NLP analysis, both because of the presence of errors in the scanned text and the presence of duplicate volumes in the corpora. In this paper, we…
We present MixtureVitae, an open-access pretraining corpus built to minimize legal risk while providing strong downstream performance. MixtureVitae follows a permissive-first, risk-mitigated sourcing strategy that combines public-domain and…
Introduction. The purpose of this work is the evaluation of responsiveness when remote users communicate with a human-readable knowledge base (KB). Responsiveness [R(s)] is considered here as a measure of service quality. Method. The…
Data repositories have accumulated a large number of tabular datasets from various domains. Machine Learning researchers are actively using these datasets to evaluate novel approaches. Consequently, data repositories have an important…
Large pages are commonly deployed to reduce address translation overheads for big-memory workloads. Modern x86-64 processors from Intel and AMD support two large page sizes -- 1GB and 2MB. However, previous works on large pages have…
Containers are an emerging technology that hold promise for improving productivity and code portability in scientific computing. We examine Linux container technology for the distribution of a non-trivial scientific computing software stack…
Although different architectures of quantum perceptrons have been recently put forward, the capabilities of such quantum devices versus their classical counterparts remain debated. Here, we consider random patterns and targets independently…
Generative retrieval (GR) has emerged as a promising paradigm in information retrieval (IR). However, most existing GR models are developed and evaluated using a static document collection, and their performance in dynamic corpora where…
We introduce Magistral, Mistral's first reasoning model and our own scalable reinforcement learning (RL) pipeline. Instead of relying on existing implementations and RL traces distilled from prior models, we follow a ground up approach,…
Retrieval-Augmented Generation (RAG) systems extend large language models (LLMs) with external knowledge sources but introduce new attack surfaces through the retrieval pipeline. In particular, adversaries can poison retrieval corpora so…
Most STM systems are poorly equipped to support libraries of concurrent data structures. One reason is that they typically detect conflicts by tracking transactions' read sets and write sets, an approach that often leads to false conflicts.…
We are presenting a set of multilingual text analysis tools that can help analysts in any field to explore large document collections quickly in order to determine whether the documents contain information of interest, and to find the…
How much large language models (LLMs) can aid scientific discovery, notably in assisting academic peer review, is in heated debate. Between a literature digest and a human-comparable research assistant lies their practical application…
Information overload is a major obstacle to scientific progress. The explosive growth in scientific literature and data has made it ever harder to discover useful insights in a large mass of information. Today scientific knowledge is…
Building storage systems has remained the domain of systems experts for many years. They are complex and difficult to implement. Extreme care is needed to ensure necessary guarantees of performance and operational correctness. Furthermore,…
High performance computing data is surging fast into the exabyte-scale world, where tape libraries are the main platform for long-term durable data storage besides high-cost DNA. Tape libraries are extremely hard to model, but accurate…
Data selection can reduce the amount of training data needed to finetune LLMs; however, the efficacy of data selection scales directly with its compute. Motivated by the practical challenge of compute-constrained finetuning, we consider the…
Physics-informed learning has shown to have a better generalization than learning without physical priors. However, training physics-informed deep neural networks requires some aspect of physical simulations to be written in a…