Seán Moran
YOU?
Author Swipe
View article: On Iterative Evaluation and Enhancement of Code Quality Using GPT-4o
On Iterative Evaluation and Enhancement of Code Quality Using GPT-4o Open
This paper introduces CodeQUEST, a novel framework leveraging Large Language Models (LLMs) to iteratively evaluate and enhance code quality across multiple dimensions, including readability, maintainability, efficiency, and security. The f…
View article: Using AI/ML to Find and Remediate Enterprise Secrets in Code & Document Sharing Platforms
Using AI/ML to Find and Remediate Enterprise Secrets in Code & Document Sharing Platforms Open
We introduce a new challenge to the software development community: 1) leveraging AI to accurately detect and flag up secrets in code and on popular document sharing platforms that frequently used by developers, such as Confluence and 2) a…
View article: Police Interaction with Victims of Domestic Violence
Police Interaction with Victims of Domestic Violence Open
This research project focused on the differing interactions between police officers and victims of domestic violence. The objective of the study was twofold. The first objective was to determine which interactions breed the most positive s…
View article: A Generative AI Assistant to Accelerate Cloud Migration
A Generative AI Assistant to Accelerate Cloud Migration Open
We present a tool that leverages generative AI to accelerate the migration of on-premises applications to the cloud. The Cloud Migration LLM accepts input from the user specifying the parameters of their migration, and outputs a migration …
View article: DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal
DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal Open
Machine learning models trained on sensitive or private data can inadvertently memorize and leak that information. Machine unlearning seeks to retroactively remove such details from model weights to protect privacy. We contribute a lightwe…
View article: Estimating class separability of text embeddings with persistent homology
Estimating class separability of text embeddings with persistent homology Open
This paper introduces an unsupervised method to estimate the class separability of text datasets from a topological point of view. Using persistent homology, we demonstrate how tracking the evolution of embedding manifolds during training …
View article: Spam-T5: Benchmarking Large Language Models for Few-Shot Email Spam Detection
Spam-T5: Benchmarking Large Language Models for Few-Shot Email Spam Detection Open
This paper investigates the effectiveness of large language models (LLMs) in email spam detection by comparing prominent models from three distinct families: BERT-like, Sentence Transformers, and Seq2Seq. Additionally, we examine well-esta…
View article: Learning a Consensus Sub-Network with Polarization Regularization and One Pass Training
Learning a Consensus Sub-Network with Polarization Regularization and One Pass Training Open
The subject of green AI has been gaining attention within the deep learning community given the recent trend of ever larger and more complex neural network models. Existing solutions for reducing the computational load of training at infer…
View article: API-Miner: an API-to-API Specification Recommendation Engine
API-Miner: an API-to-API Specification Recommendation Engine Open
When designing a new API for a large project, developers need to make smart design choices so that their code base can grow sustainably. To ensure that new API components are well designed, developers can learn from existing API components…
View article: Code Librarian: A Software Package Recommendation System
Code Librarian: A Software Package Recommendation System Open
The use of packaged libraries can significantly shorten the software development cycle by improving the quality and readability of code. In this paper, we present a recommendation engine called Librarian for open source libraries. A candid…
View article: Topical: Learning Repository Embeddings from Source Code using Attention
Topical: Learning Repository Embeddings from Source Code using Attention Open
This paper presents Topical, a novel deep neural network for repository level embeddings. Existing methods, reliant on natural language documentation or naive aggregation techniques, are outperformed by Topical's utilization of an attentio…
View article: Low Light Video Enhancement using Synthetic Data Produced with an\n Intermediate Domain Mapping
Low Light Video Enhancement using Synthetic Data Produced with an\n Intermediate Domain Mapping Open
Advances in low-light video RAW-to-RGB translation are opening up the\npossibility of fast low-light imaging on commodity devices (e.g. smartphone\ncameras) without the need for a tripod. However, it is challenging to collect\nthe required…
View article: Vengeance deferred: Children in selected short stories of Saki.
Vengeance deferred: Children in selected short stories of Saki. Open
This article examines the position of privilege allotted to children in selected short stories by ‘Saki' (H.H. Munro 1870-1916) and the possible autobiographical justification behind it. While other writers, then and now, have favoured the…
View article: Vengeance deferred: Children in selected short stories of Saki.
Vengeance deferred: Children in selected short stories of Saki. Open
This article examines the position of privilege allotted to children in selected short stories by ‘Saki' (H.H. Munro 1870-1916) and the possible autobiographical justification behind it. While other writers, then and now, have favoured the…