Related papers: Dragoman: Efficiently Evaluating Declarative Mappi…

Large language models ($\textbf{LLMs}$) have emerged as a powerful method for discovery. Instead of utilizing numerical data, LLMs utilize associated variable $\textit{semantic metadata}$ to predict variable relationships. Simultaneously,…

Many heritage institutions hold extensive collections of theatre programmes, which remain largely underused due to their complex layouts and lack of structured metadata. In this paper, we present a workflow for transforming such documents…

Large language models (LLMs) have significantly advanced autonomous agents, particularly in zero-shot tool usage, also known as function calling. This research delves into enhancing the function-calling capabilities of LLMs by exploring…

The ``black-box'' nature of deep learning models presents a significant barrier to their adoption for scientific discovery, where interpretability is paramount. This challenge is especially pronounced in discovering the governing equations…

Dataflow analysis is a fundamental code analysis technique that identifies dependencies between program values. Traditional approaches typically necessitate successful compilation and expert customization, hindering their applicability and…

The growing adoption of Graph Neural Networks (GNNs) in high-stakes domains like healthcare and finance demands reliable explanations of their decision-making processes. While inherently interpretable GNN architectures like Graph…

In recent years, several efforts have been made to enhance conceptual data modelling with automated reasoning to improve the model's quality and derive implicit information. One approach to achieve this in implementations, is to constrain…

The Multi-Agent Path Finding (MAPF) problem aims to find collision-free paths for multiple agents while optimizing objectives such as the sum of costs or makespan. MAPF has wide applications in domains like automated warehouses,…

Graph Chain-of-Thought (Graph-CoT) enables large language models (LLMs) to perform step-by-step reasoning over graph-structured knowledge, but existing pipelines suffer from low accuracy, excessive token usage, high latency, and low…

Parallel dataflow systems are a central part of most analytic pipelines for big data. The iterative nature of many analysis and machine learning algorithms, however, is still a challenge for current systems. While certain types of bulk…

Reparameterization Policy Gradient (RPG) has emerged as a powerful paradigm for model-based reinforcement learning, enabling high sample efficiency by backpropagating gradients through differentiable dynamics. However, prior RPG approaches…

Data mining techniques can transform massive amounts of unstructured data into quantitative data that quickly reveal insights, trends, and patterns behind the original data. In this paper, a data mining model is applied to analyse the 2019…

This work addresses flexibility in deep learning by means of transductive reasoning. For adaptation to new data and tasks, e.g., in continual learning, existing methods typically involve tuning learnable parameters or complete re-training…

Retrieval-Augmented Generation (RAG) systems are increasingly deployed on large-scale document collections, often comprising millions of documents and tens of millions of text chunks. In industrial-scale retrieval platforms, scalability is…

Parallel dataflow systems have become a standard technology for large-scale data analytics. Complex data analysis programs in areas such as machine learning and graph analytics often involve control flow, i.e., iterations and branching.…

We introduce a mapping framework for deep learning inference that takes advantage of predictable neural network behavior to plan both computation and communication ahead of time. The framework generates a unified stream of instructions and…

Autoformalization aims to translate natural-language mathematical statements into a formal language. While LLMs have accelerated progress in this area, existing methods still suffer from low accuracy. We identify two key abilities for…

The rapid evolution of malware has necessitated the development of sophisticated detection methods that go beyond traditional signature-based approaches. Graph learning techniques have emerged as powerful tools for modeling and analyzing…

Recent advances in large language models (LLMs) have intensified efforts to fuse heterogeneous open-source models into a unified system that inherits their complementary strengths. Existing logit-based fusion methods maintain inference…

The growing need to integrate information from a large number of diverse sources poses significant scalability challenges for data integration systems. These systems often rely on manually written schema mappings, which are complex,…