From wind farms and ports to electric buses and charging hubs, Professor Dipti Srinivasan is designing optimisation frameworks that make renewable energy systems smarter, fairer and more efficient.

A fully integrated compute-in-memory system pairs 2D memristors with silicon selectors to offer a practical, energy-efficient route for powering next-gen AI applications.

The University of Hong Kong (HKU) has spearheaded an international research collaboration to develop a pioneering theoretical framework that deciphers the predictability of complex networks. A research team including Professor Qingpeng ZHANG’s group at the HKU Musketeers Foundation Institute of Data Science (HKU IDS) and the HKU Li Ka Shing Faculty of Medicine, together with researchers from Zhejiang University and Sapienza University of Rome, has developed a new theoretical framework to understand the predictability of complex networks.

A research team from the LKS Faculty of Medicine at the University of Hong Kong (HKUMed) has developed a machine-learning classifier capable of analysing the genomes of influenza A viruses (IAVs) to accurately predict their potential risk of transmission among mammals. The team has successfully identified the key clues that may explain cross-species transmission of influenza A viruses from birds to mammals, and even to humans. The study found that when guanine (G) or cytosine (C) associated in the IVA genome decreased, the virus demonstrated a higher risk for sustained transmission in mammals, including humans. The research team recommends incorporating this genome signature into future influenza pandemic risk assessment frameworks to facilitate the early identification of high-risk viral strains. This groundbreaking study was published in Nature Microbiology.

Assessing and undertaking building maintenance in densely populated cities like Hong Kong faces growing challenges as ageing buildings become more common. Manual inspections are often time-consuming and costly, leading to delays in identifying structural defects that can compromise public safety. To address these issues, a team in iLab, The University of Hong Kong (HKU), led by Professor Junjie Chen and Professor Wilson Lu from the Department of Real Estate and Construction, Faculty of Architecture, has developed eCheckGo, an innovative artificial intelligence (AI) system powered by a proprietary Large Defect Model (LdM) combined with traditional AI algorithms.

The Faculty of Education at The University of Hong Kong (HKU) and the London Ball Foundation co-hosted the Education Summit 2026, themed “Artificial Intelligence & Cross-Cultural Intelligence”, on April 19 at Loke Yew Hall, HKU. The Summit brought together distinguished speakers and more than 400 participants, including academics, policymakers, educators, and students, for in-depth discussions on the implications of artificial intelligence (AI) for education and the importance of cross-cultural understanding.

Artificial intelligence (AI) is transforming biomolecular and material sciences, enabling rapid predictions and generative design of proteins, drugs, and materials. However, current AI models often fail to adhere to fundamental physical laws, scientific objectives, and safety principles, leading to impractical or unsafe outcomes. A research team led by Qiang Zhang at Zhejiang University and collaborators from Tongji University, Shanghai AI Laboratory, Duke University, the National University of Singapore, The Chinese University of Hong Kong, Mingdu Tech, and University College London, has proposed a comprehensive alignment framework. Their perspective argues that AI systems for biomolecular and materials design should be aligned not only with data distributions or benchmark performance, but also with natural laws, scientific goals, and responsible research principles. By analyzing examples across protein engineering, drug discovery, and materials science, the authors show that many AI-generated candidates fail not because models are useless, but because the objectives being optimized are often disconnected from the physical, functional, and regulatory realities of the laboratory and the real world. This approach aims to make AI a trustworthy and effective partner in scientific discovery.