Vacation Research Experience Scheme student topics

It has hypothesised that one of the barriers to Artificial General Intelligence is the lack of the ability to abstract concepts in AI systems. For example, a robot could learn to move a 'red block behind a blue sphere' but would struggle to then "move a blue block in front of a red sphere" as its AI has no abstract concepts of behind/in front or that objects have properties independent of their colour. Recently, the Abstraction Reasoning Corpus has been …

Faculty

Faculty of Engineering

School

School of Electrical Engineering and Robotics

Research centre

Centre for Robotics

Monte Carlo integration is a cornerstone of modern Bayesian computation. However, standard estimators suffer from a slow root-N convergence rate, making variance reduction essential. Various so-called variance reduction methods have been proposed in the literature, notably Stein control variates, which leverage gradient information of the log target density function to construct variance-reduced estimators of integrands. However, a common feature of many practical Monte Carlo problems (e.g., computing posterior means or specific marginal expectations) is that the integrand intrinsically lies in …

Faculty

Faculty of Science

School

School of Mathematical Sciences

Research centre

Centre for Data Science

Modern travel apps can automatically detect whether you are travelling by bus, train, or ferry. However, doing this often requires sending your location to external transport services, potentially revealing where you are, where you are going, and your daily travel habits.This project aims to develop privacy-preserving techniques that allow Travelly, a smart mobility app, to identify nearby public transport without unnecessarily exposing users' locations.You will investigate whether it is possible to accurately determine if someone is travelling on public transport …

Faculty

Faculty of Science

School

School of Information Systems

Research centre

Centre for Data Science

As AI-based systems increasingly rely on large-scale, sensitive data, ensuring data privacy while maintaining high model performance has become a critical challenge. This project addresses the fundamental tension between privacy protection and machine learning utility by developing methods that enable accurate AI models to be trained and deployed on protected data.The central research question is how to effectively integrate advanced privacy-preserving techniques, particularly differential privacy (DP), into modern machine learning pipelines. While DP provides strong, quantifiable privacy guarantees, it often …

Faculty

Faculty of Science

School

School of Computer Science

Research centre

Centre for Data Science

Bayesian statistics provide a framework for a statistical inference for quantifying the uncertainty of unknowns based on information pre and post data collection.This information is captured in the posterior distribution, which is a probability distribution over the space of unknowns given the observed data.The ability to make inferences based on the posterior essentially amounts to efficiently simulating from the posterior distribution, which can generally not be done perfectly in practice.This task of sampling may be challenging for various reasons:The posterior …

Faculty

Faculty of Science

School

School of Mathematical Sciences

Research centre

Centre for Data Science

Acid mine drainage contains elevated levels of heavy metals which are important for Australia’s energy transition. Ion exchange is a potential technology that can selectively recover heavy metals and ease downstream treatment requirements for these matrices. This project looks to better understand the performance of selective copper loading on ion exchange resins in real-world matrices. This topic will explore the selective copper recovery from acid mine drainage to produce copper sulfate electrolyte.

Faculty

Faculty of Engineering

School

School of Mechanical, Medical and Process Engineering

Research centre

Energy Transition Centre

Computer vision systems are increasingly used in real-world applications such as robotics, infrastructure inspection, environmental monitoring, healthcare, transport, and agriculture. However, these systems can make errors when conditions change, for example due to unusual lighting, weather, camera viewpoint, object appearance, image quality, or unfamiliar environments.This project will investigate how to identify when a computer vision model is likely to be wrong, without relying on strong assumptions about the data or requiring very large labelled datasets to set decision thresholds. The …

Faculty

Faculty of Engineering

School

School of Electrical Engineering and Robotics

Research centre

Centre for Robotics

Generative AI tools can be useful for writing and learning, but they can also produce convincing-looking academic references that do not actually exist. These hallucinated references create challenges for academic integrity, assessment, and feedback to students.This project will explore whether we can build and evaluate a tool that automatically checks reference lists and identifies potentially non-existent or suspicious references. The project is connected to the broader goal of supporting responsible GenAI use in education and improving academic integrity processes.You will …

Faculty

Faculty of Engineering

School

School of Electrical Engineering and Robotics

This VRES project involves an international comparative analysis of the laws relating to transfers which take effect during a person’s lifetime (transfers inter vivos) and transfers taking effect on death (transfers mortis causa). It will inform a contribution to a new Elgar Encyclopedia of Private Law: Law of Succession (editors:Juan Pablo Murga Fernandez, Gregor Christandl, Ronald J Scalise and Prue Vines) which Professor Tina Cockburn and Professor Kelly Purser have been invited to contribute to. The authors of all entries …

Faculty

Faculty of Business and Law

School

School of Law

Efflux pump inhibitors (EPIs) are compounds that inhibit efflux pump activity. Current research indicates that combination therapy of EPIs with standard TB therapy can enhance the efficacy of treatment, so known EPIs such as verapamil and reserpine are currently being studied for their ability to enhance tuberculosis treatment.

Faculty

Faculty of Science

School

School of Chemistry and Physics

Research centre

Centre for Materials Science

This project contributes to a scoping review on how heat-related health risks are studied across scales of the built environment, from building, street and neighbourhood conditions to urban systems and population-level exposure. The review will examine how different studies conceptualise heat risk, measure exposure and vulnerability, and connect environmental conditions with health, comfort, behaviour and design responses.The main review will begin in August, with an initial conference paper planned for November. The VRES student will join from November to support …

Faculty

Faculty of Engineering

School

School of Architecture and Built Environment

This project supports the development of a wearable environmental sensing system for monitoring personal heat exposure in outdoor and semi-outdoor built environments. As heatwaves and urban overheating intensify, there is growing need for mobile sensing methods that can capture the microclimatic conditions experienced by pedestrians, outdoor workers, students and other urban users. However, wearable and portable devices vary substantially in what they measure, how they respond to sun, shade, wind and body movement, and how suitable they are for longitudinal …

Faculty

Faculty of Engineering

School

School of Architecture and Built Environment