 |
Yang Song
ARC Future Fellow, Scientia Associate Professor
Associate Head of School (Research)
Co-Director, iCinema, UNSW
Neuro-Reasoning Research Lab
School of Computer Science and Engineering
University of New South Wales
Office: Room 401E, Building K17
Email: yang.song1 AT unsw.edu.au
Google Scholar
UNSW Researcher
LinkedIn
|
 |
About Me
I am an ARC Future Fellow and Scientia Associate Professor in the
School of Computer Science and Engineering (CSE),
Faculty of Engineering, UNSW Sydney.
I graduated with a BEng in Computer Engineering from
Nanyang Technological University, Singapore,
and obtained a PhD degree in Computer Science from the
University of Sydney in 2013.
I was an ARC DECRA Fellow at the University of Sydney before joining UNSW as a Lecturer in 2018.
I was awarded the prestigious ARC Future Fellowship in 2019 and have been a Scientia Fellow at UNSW since 2020.
I currently lead the Neuro-Reasoning Research Lab
and serve as Associate Head of School (Research) at CSE and Co-Director of iCinema Research Centre.
Research Interests
My research focuses on developing Computer Vision, Deep Learning and, more generally,
Human-centred and Multimodal AI methodologies for biomedical image analysis, robotics and other applications for social good.
Some of the specific research problems include:
Segmentation in radiological images
Cancer analysis in histopathology images
Image enhancement and generation
Vision-language models
Human-robot interaction
Action planning and decision making
Neuro-symbolic learning
Truthfulness and explainability in LLMs
Explainable AI, fairness, debiasing
I have produced over 280 peer-reviewed publications including papers in TMI, MedIA, TIP, TMM, TBME, Neural Networks, NeuroImage, Bioinformatics, Neurocomputing,
CVPR, ICCV, AAAI, IJCAI, ACMMM, BMVC, ICLR, NeurIPS, ICRA, IROS, Interspeech, MICCAI and ISBI.
I have been listed among the World's Top 2% Scientists by Stanford University and Elsevier since 2022.
A full list of my publications can be seen from my Google Scholar.
I am an Associated Editor for IEEE Transactions on Medical Imaging and IEEE Transactions on Multimedia.
I am also an Area Chair for IJCAI, MICCAI and ISBI and was a Senior Program Committee member for AAAI and IJCAI. I hosted multiple tutorials and workshops at MICCAI and ISBI.
I am a regular reviewer for IEEE TPAMI, TMI and TIP, Nature Communications,
CVPR, ICCV, ECCV, AAAI, IJCAI, MICCAI, WACV, BMVC, etc.
Looking for highly self-motivated PhD students with good communication skills and strong research experience in deep learning, computer vision, generative AI or robotics.
If you are interested, please email me your CV and transcripts.
Research Grants and Awards
In 2015, I received an ARC Discovery Early Career Researcher Award (DECRA).
In 2017, I received a Dean's Research Award from the Faculty of Engineering, University of Sydney.
In 2019, I receive an ARC Future Fellowship for deep weak learning in micro and nanoscale images.
In 2020, I was awarded a UNSW Scientia Fellowship, which supports career development of outstanding researchers.
In 2021, I received two grant awards from Google and the Faculty of Engineering Research Excellence Award.
In 2022, I received an NHMRC Ideas Grant on computational brain imaging led by
my collaborator at Macquarie University.
In 2023, I received a Women in AI award for AI in Innovation in the Asia-pacific region. I also received an ARC Linkage Project Grant on rip current detection in collaboration with Surf Life Saving Australia, and an Award for Inclusion Research from Google.
In 2024, I was one of the chief investigators receiving a large ARC grant to establish the ARC Industrial Transformation Research Hub
for Human-Robot Teaming for Sustainable and Resilient Construction.
In 2025, I received an ARC Discovery Project grant on contextualised commonsense reasoning with neuro-symbolic AI.
In 2026, I received an NVIDIA Academic Grant Program award for addressing hallucinations in AI models.
Research Themes
Computational histopathology:
Computational histopathology aims to discover phenotypic information for cancer diagnosis and prognosis from histopathology images,
such as cell nuclei segmentation, tumour detection, biomarker analysis and survival prediction.
Our research mainly develops advanced deep learning models to address challenges caused by limitations in the data, such as small sizes of training datasets,
noisy and coarse ground truth annotations, and high heterogeneity in data.
Computational neuroscience:
Computational neuroscience helps provide a mechanism to understand human brain's functionalities and
gain insights into the cause and progression of neurological diseases.
Our research is focused on single neuron reconstruction from light microscopy images,
brain tumour and lesion segmentation in MRI and tractography analysis in DTI, which are about designing
domain-inspired deep learning models to identify representative patterns for the specific problems.
Vision, Language and Robotics:
Driven by interests in solving underlying challenges in perception and reasoning,
we also work on general computer vision, multimodal data analysis and robotics applications,
such as scene analysis, action recognition, image enhancement, question answering, action planning and simulation.
Our research focuses on developing novel deep learning methods that are robust and generalisable across domains and tasks,
and such methods have wide applications such as robotics, autonomous driving and smart cities.
Deep learning paradigms:
To develop deep learning models that are data-efficient and generalisable, we focus on several deep learning paradigms
such as self/semi/weakly-supervised learning, zero/few-shot learning, federated learning, and test-time adaptation and intervention.
We also investigate mechanisms that
integrate deep learning with symbolic knowledge, such as knowledge graphs, languages and logic rules, to both reduce
the requirement of training data and enhance the reasoning capability of deep learning.
AI trustworthiness:
To reduce potential bias in deep learning models, we develop methods that can enhance fairness and transparency,
with various representation learning and interpretability/explainability techniques. We develop efficient mechanisms to address
hallucinations in LLMs and vision-language models with higher robustness against data heterogeneity and adversarial attacks.
Machine ethics is another important topic, about how to develop AI approaches
that can reason about moral choices and perform action planning accordingly.
Research Group
Current PhD Students (as primary or co-supervisor)
Tammy Zhong (2022.02 - )
Shenghui Yan (2022.02 - )
Marium Malik (2022.05 - )
Yongze Wang (2022.05 - )
Peibo Li (2023.02 - )
Lihuan Li (2023.05 - )
Frank Wu (2023.05 - )
Yiwen Xu (2023.09 - )
Mitchell Torok (2023.09 - )
Jiaqi Guo (2024.02 - )
Shenyang Qian (2024.02 - )
Haonan Zhong (2024.05 - )
Anmol Goyal (2025.02 - )
Laurence Xian (2025.05 - )
Jinwen Lei (2025.09 - )
Haoran Fan (2025.09 - )
Current MPhil Students (as primary or co-supervisor)
Bethia Sun (2023.09 - )
Sanjay Govindan (2024.02 - )
Yunchuan Li (2024.09 - )
Qingchen Tang (2025.02 - )
Graduated PhD and MPhil Students (as primary or co-supervisor)
Fan Zhang (PhD, first job at Harvard University)
Afaf Tareef (PhD, first job at Mutah University)
Siqi Liu (PhD, first job at Siemens Healthineers, US)
Donghao Zhang (PhD, first job at Monash University)
Dongnan Liu (PhD, first job at University of Sydney)
Priyanka Rana (PhD, first job at Macquarie University)
Yuqian Chen (PhD, first job at Harvard University)
Chaoyi Zhang (PhD)
Ari Tchetchenian (PhD)
Cong Cong (PhD, first job at Macquarie University)
Jiayi Zhu (PhD)
Lei Fan (PhD, first job at UNSW)
Raynaldio Limarga (PhD, first job at University of Manchester)
Kunzi Xie (PhD, first job at UNSW)
Junyan Wang (PhD, first job at University of Adelaide)
Yan Hu (PhD)
Piumi Don Simonge (PhD, first job at A*STAR Singapore)
Peibo Li (MPhil)
Yiwen Xu (MPhil)
Yu Liu (MPhil)
Renhao Huang (PhD, first job at UNSW)
Yi Fu (MPhil)
Zhijie Zhu (MPhil)
Ali Ghadiri Modarres (MPhil, first job at KPMG)
Zhan Heng (PhD, first job at UNSW)
Wenbin Wang (PhD, first job at Canva)
Ruoyu Guo (PhD, first job at UNSW)
Mark Amos (MPhil)
Yafei Luo (MPhil)
Sicong Gao (MPhil)
Alumni
Anthony Tompkins (Post-doc, 2022 - 2025)
Yixing Yang (Post-doc, 2021.06 - 2022.05)
Henry Liang (Software engineer, 2021.09 - 2021.12)
Haozhe Jia (Visiting student, from Northwestern Polytechnical University)
Yicheng Wu (Visiting student, from Northwestern Polytechnical University)
Teaching and Projects
COMP9517: Computer Vision
COMP9491: Applied Artificial Intelligence
Honours thesis and MIT research projects supervision - interested students please email for topic discussion
Vertically Integrated Project (VIP): AI-4-Everyone
|