ISTD PhD Oral Defence Seminar by Hee Ming Shan – The proliferation of hateful multimodal content, particularly in the form of hateful memes, poses significant threats to online safety and social cohesion. Although deep learning systems, especially vision-language models, are essential to automated multimodal content moderation, they operate as black boxes, offering limited explainability into their decision-making processes.

ISTD PhD Oral Defence Seminar by Chia Yew Ken – This thesis investigates the crucial role of structured information in natural language processing and artificial intelligence, with a focus on its extraction, utilisation, and extension to multimodal reasoning.

ISTD PhD Oral Defence Seminar by Bhardwaj Rishabh – This thesis investigates critical non-idealities in AI systems, focusing on safety behaviour post-training and alignment.

ISTD PhD Oral Defence Seminar by Wei Han – This thesis, aims to provide practical solutions towards basic issues such as high computational costs of multimodal learning, and giving practical solutions to each of them.

ISTD PhD Oral Defence Seminar by Perry Lam – Neural networks are known to be over-parametrised and sparse models have been shown to perform as well as dense models over a range of image and language processing tasks. However, while compact representations and model compression methods have been applied to speech tasks, sparsification techniques have rarely been used on text-to-speech (TTS) models. We seek to characterise the impact of selected sparse techniques on the performance and model complexity.

Congratulations to PhD student Hee Ming Shan for obtaining SDSC Dissertion Research Fellowship 2023

ISTD PhD Oral Defence Seminar by Teo Tzu Hsuan Christopher – In this dissertation, we make important contributions in improving fairness in generative models by identifying and addressing constraints which may limit their broader adoption.

ISTD PhD Oral Defence Seminar by Dai Siyang – Urbanisation has given rise to increasingly complex systems that sustain and manage the lives of urban residents. As populations grow, the challenges of managing traffic, overcrowding, and environmental challenges escalate. These complexities place stress on urban ecosystems, demanding innovative solutions to ensure smooth and sustainable operations.

ISTD PhD Oral Defence Seminar by Yao Xiao – Adapting large language models to downstream tasks and to human preferences has become the dominant cost in the model development pipeline. This thesis argues that the binding constraint in adaptation is not the volume of parameters, data, or computation available, but the fraction of that budget which carries usable learning signal – and that this holds in both parameterisation and post-training data.

ISTD PhD Oral Defence Seminar by Ng Xun Long – The thesis presents Chaotic World, a large-scale multi-modal dataset with fine-grained annotations of human actions, interactions, and sounds in chaotic situations.