Category: Announcement

Welcome to The University of Queensland, Lufan Zhang!

We are delighted to announce the appointment of Lufan Zhang as our new Postdoctoral Research Fellow. Lufan is one of our very own, having recently submitted her PhD thesis for examination at Swinburne University of Technology, supervised by CIRES Chief Investigator Associate Professor Paul Scifleet.

Her doctoral research was conducted in collaboration with partner organisation Astral, reflecting her strong engagement with industry-relevant, applied research.

“Undertaking my PhD with the support of CIRES at Swinburne, in collaboration with Astral Consulting, has been an incredibly rewarding and enriching journey. The industry-focused partnership offered invaluable real-world insights and created a dynamic environment that fostered both my academic development and professional growth. I am deeply grateful to everyone who supported and guided me along the way, and I am excited for the opportunity to continue exploring, innovating, and contributing to the field,” said Lufan.

At UQ, Lufan will join the CIRES team to contribute to innovative research on AI preparedness and the evaluation of AI deployments across public and private sector organisations. She will work closely with CIRES Director Professor Shazia Sadiq FTSE and Research Director Professor Marta Indulska on advancing impactful, responsible AI research.

“Lufan brings extensive experience in empirical research methods and working with industry. She is well positioned to direct her future research efforts towards AI readiness and I look forward to working with her on the important and interesting research questions in that area,” said Professor Sadiq.

We’re thrilled to have Lufan continue her journey with CIRES and look forward to the insights and impact she will bring.

Welcome Lufan!

EMIT: A New Approach for Irregular Time Series in Healthcare AI

Excited to share our paper “EMIT: Event-Based Masked Auto Encoding for Irregular Time Series” published at ICDM 2024. Together with A/Prof. Sen WANG, Dr Ruihong Qiu, A/Prof. Adam Irwin and Prof. Shazia Sadiq, we explore how irregular time series (like vital signs and lab results recorded at uneven intervals) challenge existing AI models and how our proposed framework, EMIT, improves clinical decision support through better representation learning. Special thanks to CIRES, Queensland Health and The University of Queensland for supporting this research.

Read full paper at https://arxiv.org/pdf/2409.16554

Our Approach
We introduce EMIT, a pretraining framework based on transformer architecture, tailored for irregular clinical time series data. EMIT learns by:

• Finding important points in irregular time series
• Pretraining by masking and predicting those points
• Use the pretrained model for any downstream task (e.g., outcome prediction)

Key Findings

Improved Representation Learning: EMIT captures important variations without losing timing information, outperforming generic pretext approaches for irregular time series.

Data Efficiency: On benchmark healthcare datasets (MIMIC-III & PhysioNet Challenge 2012), EMIT achieved strong results using only 50% of labeled data, reducing reliance on costly annotations.

Task Relevance: By designing pretext tasks specific to irregular time series, EMIT delivers more reliable clinical predictions compared to standard forecasting approaches.

How can we design AI that adapts to the messy, irregular reality of clinical data while still delivering trustworthy predictions?

On 20 August 2025 we celebrated our Centre’s 4th birthday with UQ and Swinburne colleagues, and four years of research collaboration, impactful partnerships, and a growing a community dedicated to building a more resilient, inclusive, and ethical digital future. Since our launch in 2021, CIRES has:

• Delivered cutting-edge research in human-centred AI and information resilience
• Fostered strong collaborations across academia, industry, and government
• Supported the next generation of researchers and innovators
• Helped shape national conversations on responsible technology

We reviewed our 2021-2025 YTD performance stats (see pics), and after that effort, we thought we definitely deserved two cakes to celebrate.

From our Director, Professor Shazia Sadiq FTSE: “CIRES was founded with a bold vision — to reduce socio-technical barriers to data driven transformation. Four years on, I’m proud of how far we’ve come and grateful to our team and collaborators who continue to pursue our mission of Information Resilience.”

We’re proud of what we’ve achieved — and even more excited about what’s ahead, including our first PhD graduates. Thank you to our researchers, partners, and supporters who have been part of this journey.

Congratulations to our PhD researcher Mehrnoush Mohammadi who recently presented at the 26th International Conference on Artificial Intelligence in Education (AIED2025) 22-26 July 2025 in Palermo, Italy. This year’s conference theme was AI as a catalyst for inclusive, personalised, & ethical education, to empower teachers & students for an equitable future. Full details and link to paper below.

“I had the opportunity to present a poster our accepted paper: “Knowledge Tracing with A Temporal Hypergraph Memory Network“.

Research Spotlight: This work presents THMN, a Temporal Hypergraph Memory Network, a hybrid Knowledge Tracing model that combines memory-augmented networks with temporal hypergraph reasoning to capture dynamic, high-order concept interactions over time. By modeling how a student’s understanding of concepts shifts across diverse question contexts and scaling updates based on practice diversity, THMN delivers composition-aware, interpretable predictions and consistently outperforms state-of-the-art KT models across four benchmark datasets.

It was an incredible experience connecting with researchers, exchanging ideas, and sharing our work with the global AI in Education community.

Special thanks to my amazing co-authors Dr.Kamal Berahmand, CIRES Centre Director Prof. Shazia Sadiq, and CIRES Chief Investigator, Dr. Hassan Khosravi, for their incredible collaboration, and to the AIED community for the warm welcome and insightful feedback.”

New publication from the CIRES team at The University of Queensland. Congratulations to PhD researcher Mehrnoush Mohammadi, Chief Investigators Assoc. Prof. Hassan Khosravi, Prof. Wojtek Tomaszewski, Centre Director Prof. Shazia Sadiq, and colleagues & co-authors Elham Tajik and Roberto Martinez-Maldonado. Full details & insights below.

“Delighted to share our newly published work, “Artificial Intelligence in Multimodal Learning Analytics: A Systematic Review,” in Computers & Education: Artificial Intelligence. We chart the evolving intersection of AI and Multimodal Learning Analytics (MMLA), providing the first comprehensive systematic review in this space. Huge Thanks to the ARC Training Centre for Information Resilience (CIRES) for supporting this work!

What We Did: We reviewed 686 records (2019–2024), synthesising 43 peer-reviewed studies to develop a structured framework for integrating AI in the MMLA pipeline—from data collection and pre-processing to modelling and feedback.

Key Insights:
► AI is transforming MMLA’s modelling and analysis layers, but links to pedagogy and impact on learning remain underdeveloped.
► Research is concentrated in higher education and lab settings, with limited focus on early learning, diverse stakeholders, or ecological validity.
► While AI enhances real-time feedback and insight generation, challenges like small sample sizes, generalisability, and transparency persist.

Forward: With the rapid rise of generative AI, new opportunities are emerging to advance MMLA, enabling richer feedback, adaptive interventions, context-aware support, and deeper insights into human learning.

What opportunities or risks do you see in embedding AI across multimodal learning environments?

We are delighted to announce that CIRES Centre Director, Professor Shazia Sadiq, has become the latest member of the Kingston AI Group, Australia’s most highly regarded professors of artificial intelligence (AI).

“We are absolutely thrilled that Shazia has joined the Kingston AI Group,” said Kingston AI Group Convenor, University of Adelaide Professor Anton van den Hengel. “Shazia’s experience and contribution to the field makes her one of the foremost experts of AI in Australia.”

Congratulations Shazia!

Welcome to Timo Spinde who joined us this week from Germany! Timo is a visiting PhD researcher from the The University of Göttingen. His research is primarily focused on automatically identifying media bias, and he coordinates the Media Bias Group a research network dedicated to studying media bias. During his PhD, Timo also founded a local German-based fashion company, Bodenseeliebe. He will be based with the CIRES Team at The University of Queensland.

“I am excited to join CIRES for the next few months. Together with Associate Professor Gianluca Demartini, we will work on a project comparing processes that increase media literacy based on both human-generated and computer-generated bias explanations. I am very much looking forward to getting to know Australia, Brisbane, UQ, and ideally finding partners for future projects”.

It is amazing to see that work redesign approaches proposed in our AI thought leadership report – Redesigning Work with Artificial Intelligence: Accelerating the Adoption of Artificial Intelligence in Government Organizations – have been adopted by NSW Department of Planning, Housing and Infrastructure for their Invoice Processing. The research takes a risk perspective to classify tasks and proposes four work redesign approaches based on risk levels and domain expertise/specialisation required. The approaches proposed are backed by case studies from the public sector.

For the full report refer to this link.

The research is jointly published by The University of Queensland and the SAP Institute for Digital Government.

Collaborators: CIRES CI Dr Ida Asadi Someh and CIRES Research Director, Professor Marta Indulska, Dr Reihaneh Bidar, Dr Tapani Rinta-Kahila, Dr Katie Williams,  Ian Ryan, Ryan van Leent [UQ Business School, SAP Australian User Group & CIRES]

CIRES celebrated 2024 International Women’s Day with the launch of the UQ Association for Computing Machinery – Women (ACM-W) Chapter, a new initiative to support and encourage women in computing at UQ and beyond. As the first university in Australia to establish a Student Chapter, UQ is excited to be welcomed into a global network of professional women in computing.

The UQ ACM-W Student Chapter will provide an environment for students to make professional and social connections, learn about technology, get career advice, participate in mentoring, organise events, and provide community service. The chapter is led by CIRES Centre Director, Professor Shazia Sadiq and supported by ten Student Leaders who promote and celebrate the achievements of UQ’s women in computing community.

The Association for Computing Machinery – Women (ACM-W) celebrates, and advocates for Women in Computing with more than 70,000+ members world-wide.

As the use of AI in education rapidly evolves and generates increasing interest, how can we obtain a comprehensive view of its current state-of-the-art developments in research and practical applications?

CIRES CI, A/Prof Hassan Khosravi’s recent paper “A meta systematic review of artificial intelligence in higher education: a call for increased ethics, collaboration and rigour “ published by the International Journal of Educational Technology in Higher Education investigates this question.

Read the paper open access at https://lnkd.in/gaR4826x

The January 2024 issue of the Communications of the ACM, Association for Computing Machinery is out and its cover features CIRES CI, A/Prof Gianluca Demartini’s work on Data Bias Management: Envisioning a unique approach toward bias and fairness research.

Here is Gianluca being interviewed about data bias management for CACM.

Full article.

A number of CIRES students and staff participated in the 34th Australasian Conference on Information Systems [ACIS 2023] 5-8 December 2023, Wellington New Zealand.

CIRES posdoctoral researcher, Dr Javad Pool, shared his PhD journey as part of the ACIS Doctoral Consortium program, as well as presenting his research paper at the main conference.

CIRES students, Daisy Xu presented her current research into “Transforming Data to Value: a Multi-Case Study” at the ACIS 2023 Doctoral Consortium, while Jorge Retamales,  presented his research paper “Becoming data-driven: Integrating inertia and dynamic capabilities perspectives” at the main conference.