This AI meetup is designed to enhance collaboration and networking among HDR students, academic staff, and industry professionals. It offers a unique platform for participants to engage in meaningful discussions, foster partnerships, and explore opportunities for external collaboration, joint research projects, and industry internships. By facilitating these interactions, the event aims to drive innovation and promote knowledge exchange within the AI research community.
Join the LinkedIn Group Sydney AI Meetup Community for the latest event update, discussion, and networking.
Title | Generative Modeling for Clinically Meaningful and Controllable Medical Image Synthesis |
Speaker | Dr. Mingjie Li, Stanford University |
Guest | Dr. Suneeta Mall, Head of AI Engineering at Harrison AI |
Date | May 21, 2025 |
Time | 2:00PM-3:30PM Canberra, Melbourne, Sydney |
Register | Link |
Join the LinkedIn Group Sydney AI Meetup Community for the latest event update, discussion, and networking. | |
Delivery | Online |
Intro | Synthesizing medical images that are both clinically interpretable and controllable is essential for advancing diagnostic support, disease monitoring, and automated clinical workflows. In this talk, Dr. Li will present two recent advances that address distinct yet complementary challenges in medical image synthesis. The first introduces Interpretable Counterfactual Generation (ICG)—a novel framework that jointly generates counterfactual chest X-rays and corresponding textual interpretations. Leveraging a multimodal autoregressive model, the framework enables traceable and hypothesis-driven image synthesis aligned with clinical reasoning. The second work focuses on a text-conditioned latent diffusion model that translates non-contrast CT scans into contrast-enhanced counterparts. Guided by explicit text prompts indicating desired contrast phases, the model achieves high-fidelity vascular enhancement across multiple anatomical regions and imaging conditions. Together, these approaches demonstrate how generative models can move beyond visual realism to deliver clinically meaningful, interpretable, and controllable outputs, paving the way for more trustworthy and flexible AI tools in medical imaging. |
Title | Boosting Large Language Model Reasoning with Knowledge Graphs |
Speaker | Prof. Shirui Pan, Griffith University |
Date | April 30, 2025 |
Time | 08:00 PM Canberra, Melbourne, Sydney |
Register | Link |
Join the LinkedIn Group Sydney AI Meetup Community for the latest event update, discussion, and networking. | |
Delivery | Online |
Intro | Large language models (LLMs) such as ChatGPT and Gemini have gained significant attention due to their emergent abilities and generalizability. However, as black-box models, they face limitations in capturing and accessing factual knowledge. In contrast, knowledge graphs (KGs) provide rich factual information in a structured format, enhancing LLMs' inference and interpretability. In this talk, I will present some recent research on integrating KGs and LLMs for faithful reasoning. Specifically, I will introduce a KG-enhanced LLM approach, Reasoning on Graphs (ROG), which leverages knowledge graphs to enable faithful and interpretable LLM reasoning. ROG follows a planning-retrieval-reasoning paradigm: first, it enables LLMs to generate a plan to retrieve the most relevant knowledge from knowledge graphs; based on the retrieved information, LLMs can then perform faithful reasoning. To further enhance performance, we also develop a graph foundation model that can be applied to new domains, enabling zero-shot reasoning. I will conclude with a brief discussion of future directions in this exciting field. |
Title | 3D Generative AI Compression with Context Models |
Speaker | Prof. Jianfei Cai, Monash University |
Date | Feb 14, 2025 |
Time | 12:30 PM Canberra, Melbourne, Sydney |
Register | Link |
Join the LinkedIn Group Sydney AI Meetup Community for the latest event update, discussion, and networking. | |
Delivery | Online and In Person |
Location | Lecture Theatre 123, Level 1 School of Computer Science (J12) 1 Cleveland St, Darlington NSW 2008 |
Catering | Free light lunch, 12:30 pm to 1:00 pm |
Intro | While 3D vision is not a new field, it has recently undergone a transformation driven by significant advancements in generative models. 3D Generative AI or Spatial AI has emerged as a major focus within the 3D vision community. At its core, the field has experienced a paradigm shift with the introduction of Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), which have redefined 3D representation. Leveraging deep learning techniques and 2D image supervision, these methods have achieved remarkable results in view synthesis. However, their reliance on extensive feature sets and large network parameters poses significant storage challenges. To address this, we have developed a series of innovative approaches—CNC, HAC, and FCGS—focused on efficient and effective compression of these advanced 3D representations. Central to our work is the use of context models, which play a pivotal role in optimizing 3D compression while preserving visual quality. This talk will delve into the design principles and impact of these techniques, paving the way for more efficient 3D vision applications. |
Dr. Mingjie Li is a postdoctoral scholar at the Laboratory of Artificial Intelligence in Medicine and Biomedical Physics at Stanford University. His research focuses on medical generative modeling, with the goal of developing clinically meaningful and controllable image synthesis methods to support diagnosis and treatment planning. He received his Ph.D. from the University of Technology Sydney. His work has been published in top-tier venues including T-PAMI, CVPR, NeurIPS, and ECCV. He also serves as a regular reviewer for leading journals and conferences such as IEEE TNNLS, IEEE ToMM, CVPR, and NeurIPS.
Suneeta is passionate about solving real-world problems with engineering, data, science, and machine learning. She's a PhD in applied science with a computer science and engineering background. She has extensive distributed, scalable computing and machine learning experience from IBM Software Labs, Expedita, USyd, Nearmap and more recently harrison.ai. She currently leads the AI Engineering division of harrison.ai, a clinician-led artificial intelligence medical technology company tackling some of the biggest issues in healthcare causing inequitable diagnosis today. She believes in lifelong learning and is passionate about knowledge sharing. She is also an author for O'Reilly and writes technical blogs in her spare time.
Shirui Pan received his Ph.D. in Computer Science from the University of Technology Sydney (UTS) and is a Professor in the School of Information and Communication Technology at Griffith University, Australia. His research focuses on data mining and machine learning and has been published in top venues, including Nature Machine Intelligence, KDD, and ICLR, among others. He has received several prestigious awards, including the 2024 IEEE CIS TNNLS Outstanding Paper Award, the 2020 IEEE ICDM Best Student Paper Award, the 2024 AI’s 10 to Watch recognition, and the 2024 IEEE ICDM Tao Li Award. He is also an ARC Future Fellow.
Jianfei Cai is a Professor at Faculty of IT, Monash University, where he had served as the inaugural Head for the Data Science & AI Department. Before that, he was Head of Visual and Interactive Computing Division and Head of Computer Communications Division in Nanyang Technological University (NTU). His major research interests include computer vision, deep learning and multimedia. He has successfully trained 40+ PhD students with three getting NTU SCSE Outstanding PhD thesis award and one getting Monash FIT Graduate Research Student Excellence Award. Many of his PhD students joined leading IT companies such as Meta, Apple, Amazon, Adobe and TikTok or become faculty members in reputable universities. He is a co-recipient of paper awards in ACCV, ICCM, IEEE ICIP and MMSP, and a winner of Monash FIT’s Dean's Researcher of the Year Award. He serves or has served as an Associate Editor for TPAMI, IJCV, IEEE T-IP, T-MM, and T-CSVT as well as serving as Area Chair for CVPR, ICCV, ECCV, IJCAI, ACM Multimedia, ICME, ICIP and ISCAS. He was the Chair of IEEE CAS VSPC-TC during 2016-2018. He had served as the leading TPC Chair for IEEE ICME 2012 and the best paper award committee chair & co-chair for IEEE T-MM 2020 & 2019. He is the leading General Chair for ACM Multimedia 2024, and a Fellow of IEEE.
Gold Sponsor
Silver Sponsor
Bronze Sponsors
Sponsors
Chiarman: Lei Wang (UoW)
Treasurer: Qiang Wu (UTS)
Publicity Chair: Yuankai Qi (MQ)
Industry Chair: Susan Zhang (UoW)
Seminar Chair: Dong Gong (UNSW),
Chang Xu (USyd)
Committee member:
Ling Chen (UTS),
Yi Guo (WSU),
Markus Hagenbuchner (UoW),
Son Lam Phung (UoW),
Zhenghao Chen (UoN),
Rosalind Wang (WSU),
Yanjun Zhang (UTS),
For enquiries, please contact the organizing committee via sydneyaimeetup@mq.edu.au