Computer Science

A new computational method aligns spatial transcriptomics data while retaining cell-level measurements.

Lingnan University held a flag-raising ceremony to celebrate the 77th anniversary of the founding of the People’s Republic of China on the University campus today, 1 October, starting at 10:30 am. Honoured guests included the Hon Andrew Yao Cho-fai, Council Chairman of Lingnan University; Dr Patrick Wong Chi-kwong, Chairman of the Court; Ms Carrie Leung Ka-lai, Treasurer of the Council; Mr Sammy Leung Chung-sing, Council Member; Prof William Shum Wai-lam, Council Member; Mr David Kwok Sek-chi, Member of the Court; Prof S. Joe Qin, President and Wai Kee Kau Chair Professor of Data Science; Prof Raymond Chan Hon-fu, Vice-President (Academics) cum Provost and Lam Man Tsan Chair Professor of Scientific Computing; Prof Xin Yao, Vice-President (Research and Innovation) and Tong Tin Sun Chair Professor of Machine Learning; and Mr Ernest Chan Chi-man, Vice-President (Administration), and Lingnan senior management, staff, and students.

Researchers from the University of Osaka and collaborating institutions accelerated protons to nearly half the speed of light using a long-pulse laser and ultrathin graphene. A moving electric field carried the protons to high energies, and artificial intelligence helped detect rare high-energy particles among millions of detector images. This technique could pave the way for future AI-driven autonomous laser experiment systems.

A new framework developed by SUTD researchers could improve how robots, autonomous systems and augmented reality tools recognise objects and navigate complex real-world environments.

Correlation does not imply causation. Using AI to discover new materials is becoming more common, but data-driven approaches sometimes rely heavily on correlations and make testing AI-based predictions difficult. A new perspective paper published by Tohoku University researchers developed a framework for incorporating physics-based principles into AI to generate more interpretable, testable, and meaningful predictions.

Lingnan University has achieved outstanding results in the newly released Times Higher Education (THE) World University Rankings 2027. Among 2,297 institutions across 118 countries and regions, Lingnan made a remarkable leap from the 301–350 band to 257th, climbing nearly 100 places to show the highest improvement among the Hong Kong SAR’s eight UGC-funded universities. This demonstrates widespread international recognition of the University’s excellence in quality education, industry-academic-research collaboration, internationalisation, and the nurturing of research-oriented liberal arts talent in the digital era.

The University Grants Committee (UGC) of the Hong Kong Special Administrative Region presented the 2026 UGC Teaching Award to Prof Helen Geng Hongyan, Assistant Professor of Teaching of the Division of Science at Lingnan University. She received the award in the General Faculty Members category. The award recognises her student-centred, innovative teaching approach, which breaks through traditional boundaries between the arts and sciences, incorporates artificial intelligence (AI) and Service-Learning in science education, stimulates students’ interest in interdisciplinary learning, and demonstrates excellence in teaching.

Lingnan University and the Civil Service Bureau of the Hong Kong Special Administrative Region (HKSAR) Government jointly organised the first Government Career Fair on the Lingnan campus today (29 September), with 20 exhibition booths, bringing together over 15 government bureaux and departments — including the Digital Policy Office, the Education Bureau, disciplined services and the Leisure and Cultural Services Department, totalling over 30 civil service grades. Recruitment activities were held alongside career talks, on-site interviews, and written examinations, helping students gain a deeper understanding of the career development opportunities available across different government grades.

AI-assisted TB screening could reduce costs and bring diagnostic support to underserved communities, helping narrow gaps in public healthcare.

The Lingnan University Institute for Advanced Study (LUIAS) held a ceremony on campus yesterday, 23 September, to confer the title of Senior Lingnan Scholar on Prof Meng Bingchun, a renowned scholar in media and communications, and Professor in the Department of Media and Communications at the London School of Economics and Political Science (LSE), in recognition of her important academic contributions in the fields of media studies, communication governance, and digital culture. Her distinguished lecture, titled “The politics and poetics of AI: From great power competition to imaginaries of good life”, offered an in-depth analysis of the divergent artificial intelligence (AI) policies and development models of China and the US, explaining that this competition is not only a rivalry over “hard power” in data and computing capabilities, but also a contest between the two sides’ visions of good life.

Why are individual investors, commonly known as “retail investors”, prone to losing money in the stock market? A Lingnan University joint study of more than 4,600 Chinese and US stocks finds that investors are less likely to buy stocks blindly when they understand the difference between a company’s “reported earnings” and its “actual cash flows”. The research team used social media to explain the difference between the two, and to teach investors how to analyse relevant company data. The results show that for companies whose earnings contain a larger accrual component, the buying behaviour of retail investors who received the relevant education declined significantly. Investment losses arising from stock prices rising and then falling after an earnings announcement were also reduced.

Prof S. Joe Qin, President and Wai Kee Kau Chair Professor of Data Science at Lingnan University, welcomes the release of Hong Kong’s First Five-Year Plan and the 2026 Policy Address delivered by Chief Executive of the Hong Kong SAR Government, Mr John Lee, and responds as follows:

- DGIST Professor Daehee Park’s team identifies “competition for resources (skill conflict)” within AI, paving the way to prevent performance degradation in integrated models - Prediction and planning integrated into a single compact model, improving both tasks while maintaining the same model size - Research accepted at the prestigious ECCV 2026, with results demonstrated with support from NVIDIA

Lingnan University has achieved outstanding results in the newly released 2026 ShanghaiRanking's Global Ranking of Academic Subjects (GRAS), with eight subjects on the list, nearly three times as many as last year. Five subjects, including Computer Science and Engineering, and Electrical and Electronic Engineering, made the list for the first time, and Artificial Intelligence, which made its debut on the list last year, saw a significant leap in its ranking, breaking into the global top 100 for the first time in the 76th to 100th band. This achievement underscores Lingnan’s dedication to advancing interdisciplinary research in artificial intelligence and data science, and demonstrates widespread recognition from the international academic community.

AI-powered cyborg cockroaches, Undiagnosed kidney disease, Plants as genetic engineers, AI and mental workload, Carnivorous plants confirm Darwin prediction, Moisture conveyor belt and Forever chemicals in furry friends. Read all in the latest Editor's Choice.

Lingnan University recently hosted the Research and Knowledge Transfer Excellence Awards Presentation Ceremony 2026. At the “Excellence Beyond Achievement Where Technology Meets Humanity” ceremony, 53 Lingnan scholars were presented with the Outstanding Researcher Award, the Early Career Researcher Award, and the Research & Knowledge Transfer Fund Award for their exceptional contributions to academic research and knowledge transfer that advance societal development. The University’s overall innovation and technology performance reached new heights in the 2025/26 academic year, with the number of granted patents for research projects increasing sixfold year-on-year to set a new record.

Prof Sam Kwong Tak-wu, Associate Vice-President (Strategic Research), Dean of the School of Graduate Studies, and J.K. Lee Chair Professor of Computational Intelligence at Lingnan University, was recently elected to the Class of 2026 Fellows of the Academy of Science of the Royal Society of Canada (RSC) in recognition of his outstanding academic achievements and remarkable contributions in the field of science. Fellowship of the RSC is one of the highest honours Canada bestows upon scholars and scientists. This year, 105 people worldwide were elected as new Fellows, and Prof Kwong is one of the three scholars in Hong Kong SAR to receive this prestigious recognition. He will attend the induction ceremony in Ottawa in November.

Finding better materials to store hydrogen safely and efficiently is key to clean energy, but AI models trained on incomplete data can recommend candidates that don't actually work in practice. An international team led by Tohoku University, drawing on insight from 69 researchers, has proposed a "physics-aware" framework that combines thermodynamic constraints, reproducible data, and real experimental feedback to make AI-guided materials discovery more reliable. The roadmap could help accelerate the search for practical hydrogen storage solutions to support future clean-energy systems.

• Principal Researcher Sang-Chul Lee’s team presents an automatic compensation technique (Ada-Comp) that prevents declines in recommendation performance for specific user groups • Overcomes structural limitations of graph neural network (GNN)-based recommender systems, establishing a standard for trustworthy next-generation AI • Undergraduate researcher Eugene Jeong participates as first author; findings presented at KDD-UC ’26, a world-leading academic conference

Researchers at Tohoku University have combined multiple tools to create an automated, self-improving AI workflow that may improve our search for polymer material candidates so that it is less expensive, less costly, and more environmentally friendly.

Prof Jean-Michel Morel, Chair Professor of the Division of Industrial Data Science at Lingnan University, has been elected a Foreign Member of the Luxembourg Academy of Sciences and Arts (LASA). The honour recognises his pioneering research extending from mathematical foundations to image analysis and industrial data science, and demonstrating the profound contribution of fundamental mathematics to artificial intelligence (AI), computer vision, and image analysis, aligning with LASA's mission to foster interdisciplinary exchange.

Validating artificial intelligence performance in radiology studies with demographic subgroups

A research group in Japan led by Professor YAMAMOTO Takashi, Deputy Director, Center for Quantum Information and Quantum Biology / Graduate School of Engineering Science, the University of Osaka, in collaboration with the National Institute of Information and Communications Technology (NICT) and Hamamatsu Photonics K.K., has successfully demonstrated a world-record 10-channel multiplexed quantum photonic interface based on an integrated waveguide array, a key technology for optically interconnecting multiple quantum computers.

Lingnan University hosted the “Empower Your Future: Lingnan Postgraduate Orientation 2026” on campus today, 27 August, welcoming about 3,200 new taught postgraduate/doctoral degree and MPhil/PhD programme students for the 2026/27 academic year. To meet the growing demand for professionals in artificial intelligence (AI), data analytics, and smart manufacturing in the digital era, Lingnan has introduced three new taught postgraduate programmes, bringing the number of offerings to a record high of 50. In addition, the University held its first-ever “Welcome Gathering for Research Postgraduate Students” to help new students adapt more quickly to Lingnan’s academic research environment.

Researchers from the University of Osaka have developed a fast computational framework that predicts the optical performance of quantum color centers without being restricted to a specific host material. By replacing computationally intensive calculations with simple theoretical formulas and procedures, the method enables rapid screening of promising quantum materials spanning ultraviolet to telecommunication wavelengths.

As solid-state electrolyte research grows, so does the amount of data. The problem is that much of it remains scattered across the literature. That is where researchers at WPI-AIMR, Tohoku University, come in — with DigBat, a new platform designed to bring this information together and help map the growing landscape of solid-state electrolyte research. By connecting data from across the field, DigBat can help researchers see relationships more clearly and point toward promising directions for future battery materials research.

Hematopoietic stem cells can transform into any type of blood cell. However, this ability declines as we age. Recent research at Tohoku University uses AI to guide their deep dive into understanding which genes cause aging in stem cells.

Lingnan University held its 2026/27 academic year New Student Orientation (NSO) and Official Welcome for undergraduate students at its Tuen Mun campus today (24 August).

Lingnan University announced the establishment of the innovation and entrepreneurship platform “LU Xcelerator (LUX)” and held its Opening Ceremony today, 21 August. LUX focuses on “AI + X” and the application of agentic AI in different industries, leveraging the unique strength of Lingnan University in data science and interdisciplinary studies. Benefitting from Lingnan’s location near the Northern Metropolis, LUX will spearhead an innovative mode of collaboration between “Government, Industry, Academia, Research, and Investment” in the Greater Bay Area. This new platform will assist our students and researchers in translating innovative research into market-ready applications with tangible commercial and social value.

Researchers from the University of Osaka and Diponegoro University developed an AI-powered navigation system for cyborg cockroaches. Using onboard sensors and a multilayer perceptron, the system recognizes flat ground, climbs, descents, and holes in real time, then adapts electrical stimulation accordingly. By supporting natural climbing while reducing unnecessary steering, the approach shortened obstacle-crossing and total navigation times, reduced travel distance and stimulation, and significantly improved efficient movement across complex terrain.