Related papers: Grove: a Separation-Logic Library for Verifying Di…
Users typically interact with and evaluate language models via single outputs, but each output is just one sample from a broad distribution of possible completions. This interaction hides distributional structure such as modes, uncommon…
Despite the recent success associated with Large Language Models (LLMs), they are notably cost-prohibitive to deploy in resource-constrained environments due to their excessive memory and computational demands. In addition to model…
Improving the reliability of power distribution systems is critically important for both utilities and customers. This calls for an efficient service restoration module within a distribution management system to support the implementation…
The Gene-pool Optimal Mixing EA (GOMEA) family of EAs offers a specific means to exploit problem-specific knowledge through linkage learning, i.e., inter-variable dependency detection, expressed using subsets of variables, that should…
Retrieval-Augmented Generation for software engineering often relies on vector similarity search, which captures topical similarity but can fail on multi-hop architectural reasoning such as controller to service to repository chains,…
Digital libraries curate millions of research software artefacts yet lack scalable infrastructure for assessing whether those artefacts remain executable. Existing automated assessment tools treat static repository completeness -- what a…
Retrieval-Augmented Generation (RAG) systems combine vector similarity search with large language models (LLMs) to deliver accurate, context-aware responses. However, co-locating the vector retriever and the LLM on shared GPU infrastructure…
High Energy and Nuclear Physics (HENP) libraries are now required to be more and more multi-thread-safe, if not multi-thread-friendly and multi-threaded. This is usually done using the new constructs and library components offered by the…
With the emerging of huge amount of unlabeled data, unsupervised out-of-distribution (OOD) detection is vital for ensuring the reliability of graph neural networks (GNNs) by identifying OOD samples from in-distribution (ID) ones during…
A novel parallel patterns library, Groovy Parallel Patterns, is presented which, from the outset, has been designed to exploit more general process parallelism than the usual data and task parallel architectures. The library executes on a…
Recent progress in Large Language Model (LLM) reasoning is increasingly driven by the refinement of post-training loss functions and alignment strategies. However, standard Reinforcement Learning (RL) paradigms like Group Relative Policy…
Memory disaggregation is an emerging data center architecture that improves resource utilization and scalability. Replication is key to ensure the fault tolerance of applications, but replicating shared data in disaggregated memory is hard.…
We describe a parallel version of our tree-code for the simulation of self-gravitating systems in Astrophysics. It is based on a dynamic and adaptive method for the domain decomposition, which exploits the hierarchical data arrangement used…
This paper investigates an edge computing system where requests are processed by a set of replicated edge servers. We investigate a class of applications where similar queries produce identical results. To reduce processing overhead on the…
Scheduling is an important task allowing parallel systems to perform efficiently and reliably. For modern computation systems, divisible load is a special type of data which can be divided into arbitrary sizes and independently processed in…
Recent Retrieval Augmented Generation (RAG) aims to enhance Large Language Models (LLMs) by incorporating extensive knowledge retrieved from external sources. However, such approach encounters some challenges: Firstly, the original queries…
Knowledge graphs (KGs) are increasingly integrated with large language models (LLMs) to provide structured, verifiable reasoning. A core operation in this integration is multi-hop retrieval, yet existing systems struggle to balance…
Recent advances in graph learning have paved the way for innovative retrieval-augmented generation (RAG) systems that leverage the inherent relational structures in graph data. However, many existing approaches suffer from rigid, fixed…
Fully decentralized learning algorithms are still in an early stage of development. Creating modular Gossip Learning strategies is not trivial due to convergence challenges and Byzantine faults intrinsic in systems of decentralized nature.…
In recent years, a number of lightweight programs have been deployed in critical domains, such as in smart contracts based on blockchain technology. Therefore, the security and reliability of such programs should be guaranteed by the most…