A groundbreaking non-hand-worn VR hand rehabilitation system has been developed, utilizing ionic hydrogel electrodes and deep learning for electromyography (EMG) gesture recognition. The system offers load-free rehabilitation without bulky mechanical components, providing a more accessible and flexible alternative to traditional rehabilitation methods. This VR-based solution enables immersive training and precise hand rehabilitation for stroke and joint disease patients in the comfort of their homes, without the constraints of time or location.

A self-supervised deep learning model has been developed to improve the quality of dynamic fluorescence images by leveraging temporal gradients. The method enables accurate denoising without ground truth data and facilitates clearer visualization of spatially and temporally dynamic biological signals in vivo.

Researchers from University of South China, Tsinghua University and Technical University of Munich have developed a whole system uncertainty model and an Intelligent optimized power control system of the space nuclear reactor with faster response, higher control accuracy and stronger adaptability under uncertainty conditions. These research results provide new ideas and solutions for improving the intelligence level and autonomous control capability of advanced nuclear energy systems in complex environments.

Understanding how cities grow is vital for shaping sustainable urban futures—but mapping the true extent of urban expansion remains a formidable technical hurdle. 

A research paper by scientists at Chinese Academy of Sciences proposed a dual-task learning framework, the “Twin Brother” model, which fuses convolutional neural network (CNN), long short-term memory (LSTM), neural networks (NNs), and the squeezing-elicited attention mechanism to classify the lateral gait stage and estimate the hip angle from electromyography (EMG) signals.

The new research paper, published on May. 1 in the journal Cyborg and Bionic Systems, provide a “Twin Brother” model. The model is a dual-task learning framework designed for simultaneous gait phases recognition for lateral walking and continuous hip angle prediction.

Addressing the urgent need for sustainable CO₂ conversion, researchers at Tongji University developed a novel copper-based metal-organic framework (MOF) catalyst, TJE-ttfp, which achieves 99.2% Faradaic efficiency for C1 liquid fuels (formic acid and methanol) at a remarkably reduction potential of −0.1 V. By leveraging dynamic Cu(I)/Cu(II) interconversion and electron-rich ligands, the material suppresses competing hydrogen evolution while enhancing CO₂ activation, offering a breakthrough for energy-efficient carbon utilization.

Teaching STEM in Hong Kong’s preschools presents cultural, personal, and organizational challenges for female, ethnically diverse teachers. A recent study from The Education University of Hong Kong explores these barriers through the Concerns-Based Adoption Model, identifying five key concerns affecting STEM adoption. By examining confidence issues, traditional teaching philosophies, and limited resources, this study provides insights into the complex factors shaping early STEM education and calls for tailored support to enhance inclusivity.

Gliomas are among the deadliest brain tumors, with limited treatment options and poor survival rates. Scientists from China identified FAM111B, a DNA-repair-associated protein, as a key driver of glioma progression. The study shows that FAM111B overexpression enhances tumor growth and aggressiveness by activating the PI3K/AKT pathway. This is the first research to link FAM111B to gliomas, offering a promising new biomarker and therapeutic target for this intractable disease.

In this Science Bulletin review, the scientists from City University of Hong Kong summarized the recently developed metal-based Janus nanomaterials, including their synthesis methods and application in electrochemical carbon dioxide reduction.