9 citations · 14 across the 10 of their papers we have counts for
10 papers
Self Knowledge Re-expression: A Fully Local Method for Adapting LLMs to Tasks Using Intrinsic Knowledge
Mengyu Wang, Xiaoying Zhi, Zhiyi Li +4
While the next-token prediction (NTP) paradigm enables large language models (LLMs) to express their intrinsic knowledge, its sequential nature constrains performance on specialize…
Automatic Labelling with Open-source LLMs using Dynamic Label Schema Integration
Thomas Walshe, Sae Young Moon, Chunyang Xiao +2
Acquiring labelled training data remains a costly task in real world machine learning projects to meet quantity and quality requirements. Recently Large Language Models (LLMs), not…
A Benchmark Generative Probabilistic Model for Weak Supervised Learning
Georgios Papadopoulos, Fran Silavong, Sean Moran
Finding relevant and high-quality datasets to train machine learning models is a major bottleneck for practitioners. Furthermore, to address ambitious real-world use-cases there is…
Learning a Consensus Sub-Network with Polarization Regularization and One Pass Training
Xiaoying Zhi, Varun Babbar, Rundong Liu +4
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 solutio…
API-Miner: an API-to-API Specification Recommendation Engine
Sae Young Moon, Gregor Kerr, Fran Silavong +1
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…
Topical: Learning Repository Embeddings from Source Code using Attention
Agathe Lherondelle, Varun Babbar, Yash Satsangi +3
This paper presents Topical, a novel deep neural network for repository level embeddings. Existing methods, reliant on natural language documentation or naive aggregation technique…
CV4Code: Sourcecode Understanding via Visual Code Representations
Ruibo Shi, Lili Tao, Rohan Saphal +2
We present CV4Code, a compact and effective computer vision method for sourcecode understanding. Our method leverages the contextual and the structural information available from t…
Enhancing Privacy against Inversion Attacks in Federated Learning by using Mixing Gradients Strategies
Shaltiel Eloul, Fran Silavong, Sanket Kamthe +2
Federated learning reduces the risk of information leakage, but remains vulnerable to attacks. We investigate how several neural network design decisions can defend against gradien…
ST-FL: Style Transfer Preprocessing in Federated Learning for COVID-19 Segmentation
Antonios Georgiadis, Varun Babbar, Fran Silavong +2
Chest Computational Tomography (CT) scans present low cost, speed and objectivity for COVID-19 diagnosis and deep learning methods have shown great promise in assisting the analysi…
Senatus -- A Fast and Accurate Code-to-Code Recommendation Engine
Fran Silavong, Sean Moran, Antonios Georgiadis +2
Machine learning on source code (MLOnCode) is a popular research field that has been driven by the availability of large-scale code repositories and the development of powerful pro…