Computational Neuroscience, Graph Neural Networks, Computer Vision
I am currently a PhD candidate in the Faculty of Engineering and IT at the University of Melbourne under Prof. Andrew Zalesky, Dr. Sidhant Chopra, A/Prof. Maria Di Biase, Dr. Wei Tong,and Dr. Lukas Roell, specializing in mathematical modelling, computational methods, and artificial intelligence, particularly computer vision, with applications to multiscale network modelling in neuroscience.
I have experience working in AI research at the Walter and Eliza Hall Institute of Medical Research as a Data Research Engineer, and at Sindy Lab as a Software Engineer focused on AI detection for academic integrity. I am also a teaching associate for Algorithms and Analysis at RMIT University and Algorithms for Bioinformatics at The University of Melbourne.
Updates
Our paper Pathology-Aware Brain Graph Learning is out for review under IEEE Transactions on Pattern Analysis and Machine Intelligence.
Our paper TRACE-Seg3D: Counterfactual Context Auditing For Robust 3D Glioma Segmentation Under Institutional Shift is out for review under ACCV 2026.
Our paper Bayesian Networks with Latent Time Embedding for Stage-Aware Causal Modelling of Alzheimer's Disease Progression is out for review under IEEE BHI 2026.
Our paper HiBrain: Hierarchical Prototype Learning on Multimodal Brain Graphs for Stage-Aware Biomarker Discovery is accepted under ACM KDD 2026.
Our paper HiBrain: Hierarchical Prototype Learning on Multimodal Brain Graphs for Stage-Aware Biomarker Discovery is out for review under ACM KDD 2026.
Our paper Causal Prompting for Implicit Sentiment Analysis with Large Language Models is accepted under IEEE Transactions on Computational Social Systems.
Our paper Neuromorphic Dual-Pathway Prompt Learning for Unsupervised Continual Anomaly Detection is out for review under IEEE Transactions on Cognitive and Developmental Systems.
Our paper Explainable Graph Neural Networks: Understanding Brain Connectivity and Biomarkers in Dementia is out for review under ACM Transactions on Computing for Healthcare.
Our paper Structure Matters: Brain Graph Augmentation via Learnable Edge Masking for Data-efficient Psychiatric Diagnosis is accepted under AJCAI 2025 in Canberra, Australia.
Our paper BrainMAP: Multimodal Graph Learning For Efficient Brain Disease Localization is accepted under IEEE NER 2025 in San Diego, USA.
Our paper Structure Matters: Brain Graph Augmentation via Learnable Edge Masking for Data-efficient Psychiatric Diagnosis is out for review under AJCAI 2025.
Our paper Causal Prompting for Implicit Sentiment Analysis with Large Language Models is out for review under IEEE Transactions on Computational Social Systems.
Our paper BrainMAP: Multimodal Graph Learning For Efficient Brain Disease Localization is out for review under IEEE NER 2025.
Selected work
IEEE International Conference on Neural Engineering (A), 2025
A multimodal graph learning framework for efficient brain disease localization, integrating MRI and DTI data to enhance diagnostic accuracy and reduce computational costs.
IEEE Transactions on Computational Social Systems (Q1), 2025
CAPITAL is a causal prompting framework that incorporates front-door adjustment into chain-of-thought reasoning.
Australasian Joint Conference on Artificial Intelligence (B), 2025
SAM-BG uses structure-aware augmentation via edge masking to learn robust, biologically meaningful brain graph representations from large-scale unlabeled fMRI data.
ACM Transactions on Computing for Healthcare (Q1), 2025
This paper presents a comprehensive review of XGNNs in dementia research, with a taxonomy of methods, clinical comparisons, and open challenges for early detection.
IEEE Transactions on Pattern Analysis and Machine Intelligence (Q1), 2026
BrainPoG is a lightweight graph learning model that reduces disease-irrelevant nodes and noisy features to improve model efficiency and predictive accuracy.
ACM KDD (A*), 2026
HiBrain is a hierarchical prototype-based framework for multimodal brain network analysis and stage-aware biomarker discovery.
Community
Teaching