The University of Auckland

research

∙ 09/14/2022

Prompt-based Conservation Learning for Multi-hop Question Answering

Multi-hop question answering (QA) requires reasoning over multiple docum...

Zhenyun Deng, et al. ∙

research

∙ 06/09/2019

Four Things Everyone Should Know to Improve Batch Normalization

A key component of most neural network architectures is the use of norma...

Cecilia Summers, et al. ∙

research

∙ 06/03/2022

Falconn++: A Locality-sensitive Filtering Approach for Approximate Nearest Neighbor Search

We present Falconn++, a novel locality-sensitive filtering (LSF) approac...

Ninh Pham, et al. ∙

research

∙ 11/23/2021

Non-invasive hemodynamic analysis for aortic regurgitation using computational fluid dynamics and deep learning

Changes in cardiovascular hemodynamics are closely related to the develo...

Derek Long, et al. ∙

research

∙ 09/24/2022

Closing the Loop: Graph Networks to Unify Semantic Objects and Visual Features for Multi-object Scenes

In Simultaneous Localization and Mapping (SLAM), Loop Closure Detection ...

Jonathan J. Y. Kim, et al. ∙

research

∙ 07/28/2022

Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation

Combining deep learning with symbolic logic reasoning aims to capitalize...

Qiming Bao, et al. ∙

research

∙ 08/21/2022

The Development of a Labelled te reo Māori-English Bilingual Database for Language Technology

Te reo Māori (referred to as Māori), New Zealand's indigenous language, ...

Jesin James, et al. ∙

research

∙ 06/10/2019

Improved Adversarial Robustness via Logit Regularization Methods

While great progress has been made at making neural networks effective a...

Cecilia Summers, et al. ∙

research

∙ 06/16/2022

Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering

Effective multi-hop question answering (QA) requires reasoning over mult...

Zhenyun Deng, et al. ∙

research

∙ 02/08/2020

HHH: An Online Medical Chatbot System based on Knowledge Graph and Hierarchical Bi-Directional Attention

This paper proposes a chatbot framework that adopts a hybrid model which...

Qiming Bao, et al. ∙

research

∙ 10/07/2021

Hitting the Target: Stopping Active Learning at the Cost-Based Optimum

Active learning allows machine learning models to be trained using fewer...

Zac Pullar-Strecker, et al. ∙

research

∙ 03/02/2022

EnclaveTree: Privacy-preserving Data Stream Training and Inference Using TEE

The classification service over a stream of data is becoming an importan...

Qifan Wang, et al. ∙

research

∙ 01/07/2021

On the Interaction of Functional and Inclusion Dependencies with Independence Atoms

Infamously, the finite and unrestricted implication problems for the cla...

Miika Hannula, et al. ∙

research

∙ 01/07/2021

An Algorithm for the Discovery of Independence from Data

For years, independence has been considered as an important concept in m...

Miika Hannula, et al. ∙

research

∙ 07/08/2021

An Embedded Iris Recognition System Optimization using Dynamically ReconfigurableDecoder with LDPC Codes

Extracting and analyzing iris textures for biometric recognition has bee...

Longyu Ma, et al. ∙

research

∙ 08/06/2021

An Empirical Study on End-to-End Singing Voice Synthesis with Encoder-Decoder Architectures

With the rapid development of neural network architectures and speech pr...

Dengfeng Ke, et al. ∙

research

∙ 08/11/2021

What Drives and Sustains Self-Assignment in Agile Teams

Self-assignment, where software developers choose their own tasks, is a ...

Zainab Masood, et al. ∙

research

∙ 08/16/2021

Security Smells Pervade Mobile App Servers

[Background] Web communication is universal in cyberspace, and security ...

Pascal Gadient, et al. ∙

research

∙ 09/11/2021

Space Meets Time: Local Spacetime Neural Network For Traffic Flow Forecasting

Traffic flow forecasting is a crucial task in urban computing. The chall...

Song Yang, et al. ∙

research

∙ 09/13/2021

Source Inference Attacks in Federated Learning

Federated learning (FL) has emerged as a promising privacy-aware paradig...

Hongsheng Hu, et al. ∙

research

∙ 09/20/2021

Modeling Annotation Uncertainty with Gaussian Heatmaps in Landmark Localization

In landmark localization, due to ambiguities in defining their exact pos...

Franz Thaler, et al. ∙

research

∙ 09/27/2021

N-shot Palm Vein Verification Using Siamese Networks

The use of deep learning methods to extract vascular biometric patterns ...

Felix Marattukalam, et al. ∙

research

∙ 09/29/2021

Worrisome Patterns in Developers: A Survey in Cryptography

We surveyed 97 developers who had used cryptography in open-source proje...

Mohammadreza Hazhirpasand, et al. ∙

research

∙ 09/29/2021

Spatially Coupled PLDPC-Hadamard Convolutional Codes

In this paper, we propose a new type of ultimate-Shannon-limit-approachi...

Peng W. Zhang, et al. ∙

research

∙ 09/30/2021

Crypto Experts Advise What They Adopt

Previous studies have shown that developers regularly seek advice on onl...

Mohammadreza Hazhirpasand, et al. ∙

research

∙ 10/15/2021

Hardware Architecture of Layered Decoders for PLDPC-Hadamard Codes

Protograph-based low-density parity-check Hadamard codes (PLDPC-HCs) are...

Peng W. Zhang, et al. ∙

research

∙ 10/21/2021

SymbioLCD: Ensemble-Based Loop Closure Detection using CNN-Extracted Objects and Visual Bag-of-Words

Loop closure detection is an essential tool of Simultaneous Localization...

Jonathan J. Y. Kim, et al. ∙

research

∙ 10/26/2021

Two Decades of Game Jams

In less than a year's time, March 2022 will mark the twentieth anniversa...

Gorm Lai, et al. ∙

research

∙ 10/27/2021

GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series

Traffic forecasting is an integral part of intelligent transportation sy...

Sikai Zhang, et al. ∙

research

∙ 11/05/2021

Phish What You Wish

IT professionals have no simple tool to create phishing websites and rai...

Pascal Gadient, et al. ∙

research

∙ 11/25/2021

Quasi-Isometric Graph-Simplifications

We propose a general framework based on quasi-isometries to study graph ...

Bakhadyr Khoussainov, et al. ∙

research

∙ 12/10/2021

The Industry Relevance of an IT Transition Programme

There is a shortage of qualified people in the IT industry in the world....

Yu-Cheng Tu, et al. ∙

research

∙ 12/27/2021

Evaluating Software User Feedback Classifiers on Unseen Apps, Datasets, and Metadata

Listening to user's requirements is crucial to building and maintaining ...

Peter Devine, et al. ∙

research

∙ 01/18/2022

An Efficient Hashing-based Ensemble Method for Collaborative Outlier Detection

In collaborative outlier detection, multiple participants exchange their...

Kitty Li, et al. ∙

research

∙ 08/21/2022

Visualising Model Training via Vowel Space for Text-To-Speech Systems

With the recent developments in speech synthesis via machine learning, t...

Binu Abeysinghe, et al. ∙

research

∙ 02/01/2023

A Survey of Methods, Challenges and Perspectives in Causality

The Causality field aims to find systematic methods for uncovering cause...

Gaël Gendron, et al. ∙

research

∙ 01/23/2023

Wish You Were Here: Mental and Physiological Effects of Remote Music Collaboration in Mixed Reality

With face-to-face music collaboration being severely limited during the ...

Ruben Schlagowski, et al. ∙

research

∙ 01/05/2023

Instance-based Explanations for Gradient Boosting Machine Predictions with AXIL Weights

We show that regression predictions from linear and tree-based models ca...

Paul Geertsema, et al. ∙

research

∙ 12/09/2022

Automatically Generating CS Learning Materials with Large Language Models

Recent breakthroughs in Large Language Models (LLMs), such as GPT-3 and ...

Stephen MacNeil, et al. ∙

research

∙ 12/02/2022

Programming Is Hard – Or at Least It Used to Be: Educational Opportunities And Challenges of AI Code Generation

The introductory programming sequence has been the focus of much researc...

Brett A. Becker, et al. ∙

research

∙ 11/12/2022

Hypercubes and Hamiltonian Cycles of Display Sets of Rooted Phylogenetic Networks

In the context of reconstructing phylogenetic networks from a collection...

Janosch Döcker, et al. ∙

research

∙ 11/08/2022

OutlierDetection.jl: A modular outlier detection ecosystem for the Julia programming language

OutlierDetection.jl is an open-source ecosystem for outlier detection in...

David Muhr, et al. ∙

research

∙ 11/09/2022

Robosourcing Educational Resources – Leveraging Large Language Models for Learnersourcing

In this article, we introduce and evaluate the concept of robosourcing f...

Paul Denny, et al. ∙

research

∙ 11/04/2022

Experiences from Using Code Explanations Generated by Large Language Models in a Web Software Development E-Book

Advances in natural language processing have resulted in large language ...

Stephen MacNeil, et al. ∙

research

∙ 10/27/2022

Conversing with Copilot: Exploring Prompt Engineering for Solving CS1 Problems Using Natural Language

GitHub Copilot is an artificial intelligence model for automatically gen...

Paul Denny, et al. ∙

research

∙ 10/20/2022

Using Large Language Models to Enhance Programming Error Messages

A key part of learning to program is learning to understand programming ...

Juho Leinonen, et al. ∙

research

∙ 10/06/2022

PrivacyCube: A Tangible Device for Improving Privacy Awareness in IoT

Consumers increasingly bring IoT devices into their living spaces withou...

Bayan Al Muhander, et al. ∙

research

∙ 08/27/2022

Generally-Altered, -Inflated, -Truncated and -Deflated Regression, With Application to Heaped and Seeped Data

Models such as the zero-inflated and zero-altered Poisson and zero-trunc...

Thomas W. Yee, et al. ∙

research

∙ 05/03/2022

Scalable Private Decision Tree Evaluation with Sublinear Communication

Private decision tree evaluation (PDTE) allows a decision tree holder to...

Jianli Bai, et al. ∙

research

∙ 03/21/2022

Choosing good subsamples for regression modelling

A common problem in health research is that we have a large database wit...

Thomas Lumley, et al. ∙

The University of Auckland

Featured Researchers