Zhao Jiuzhang (1907–1968) was one of the 23 recipients of the Two Bombs and One Satellite Merit Medal. Devoting his whole life to serving the nation through science and technology, and guided by an exceptionally far−sighted strategic vision, he established and advanced China's basic research in geophysics, space physics, atmospheric science, ocean wave research, and seismology, and was one of the initiators and founders of China's artificial satellite program. Taking into full account the actual conditions of New China, Zhao Jiuzhang emphasized that "missions drive the development of disciplines, while disciplines in turn support the fulfillment of missions". Learning from his scientist spirit and carrying forward his devotion to China, his visionary foresight, his pioneering and innovative drive, and his distinctive philosophy of education are of far−reaching practical significance for further strengthening basic research and accelerating China's endeavor to build herself into a leading country in science and technology in the new era.

Grain boundaries are one of the common defects in metallic materials and strongly affect the mechanical properties of metals. In response to the urgent demand for high strength and damage resistance of metallic materials in engineering applications, this paper takes the properties of grain boundaries and corresponding mechanical properties as examples to systematically review the digital and intelligent research progress of the microstructure and mechanical properties of metallic materials. This review elaborates on the closed−loop research paradigm of "high−throughput computing − theoretical model − machine learning and large language model". In detail, the high−throughput computing platform generates material data in batches through multi−scale computing, forming the large database. Based on the large database, combined with the classical thermodynamic/dynamic models of materials science and the bonding theories of metal physics, descriptors and theoretical models are constructed to establish the quantitative structure−activity relationship between microstructure and macroscopic mechanical properties. Machine learning can be used for rapid prediction of material properties. They can also integrate descriptors with theoretical models to solve the "black box" problem, thereby guiding theoretical calculations and experimental studies. Large−language models can be trained on massive materials science texts, demonstrating powerful cross−disciplinary knowledge integration and generation capabilities, and can serve as efficient intelligent research assistants to assist in material discovery and design. Finally, we also look forward to the development of this field towards the deep integration of physical constraint embedding and autonomous scientific discovery. We also propose the key challenges, such as data quality, theoretical universality, model transferability, and "Hallucination" of the large−language models. All these reviews provide a systematic theoretical reference for the digital and intelligent research on the grain boundary properties and corresponding mechanical properties of metallic materials, as well as for the design of high−performance metallic materials.

Brain−computer interface (BCI), as a cutting−edge field integrating brain science, artificial intelligence, and engineering technology, are becoming an important vehicle for cultivating new types of productivity. This study focuses on the crucial stage of BCI's transition from scientific research to industrial application, systematically reviewing our country's latest progress in policy layout, basic components, encoding and decoding methods, and typical application systems. It proposes that BCIs not only provide a path for the accumulation of new production factors through the efficient collection and processing of brain data, but also promote the formation of emerging industrial chains represented by personalized diagnosis and treatment of brain diseases, and demonstrate forward−looking potential in the field of human−machine collaborative brain−computer intelligence. Furthermore, this study proposes development suggestions from the dimensions of technological autonomy, industry−academia−research integration, and ethical standards, aiming to provide theoretical reference and analytical framework for our country to seize the strategic high ground in BCIs and shape its future industrial competitiveness.

Chinese Meridian Project is dedicated to monitoring the chain of changes in the Sun–Earth space environment, enhancing the capability of autonomous space weather forecasting, and meeting the national demand for space security assurance. As the world's most extensive ground−based comprehensive monitoring network for the space environment in terms of coverage, parameter diversity, and overall capability, the Meridian Project has driven leapfrog advancements in China's ground−based space environment monitoring capabilities, indigenous innovation in monitoring technologies, and data service capacities. This paper reviews these transformative developments, elucidates the project's significant contributions to institutionalized fundamental research in space weather in China, and outlines three future development directions—— "consolidating the foundation, empowering applications, and expanding the network".

The rapid development of large language models has made the question of whether AI can be conscious no longer merely a philosophical issue, but also a practical concern in technology ethics and governance. Alexander Lerchner's concept of the "abstraction fallacy" attempts to fundamentally challenge the possibility that current large language models could lead to genuine consciousness. At its core, AI computation is a symbolic processing of the world: it can simulate human language, emotions, and behavior, but this does not mean that it truly generates subjective experience. This article argues that AI consciousness will not naturally emerge simply from larger models, greater computational power, or more complex algorithms. AI may increasingly resemble human beings; it may say "I am in pain", "I am afraid", or "I hope", and it may display complex communication and planning abilities. Yet these remain forms of behavioral imitation and functional simulation, and they do not demonstrate that AI truly has feelings. Current and foreseeable artificial intelligence systems should therefore be regarded as powerful non−conscious tools rather than subjects with subjective experience. The focus of future AI governance should not be a premature discussion of machine rights, but the prevention of excessive anthropomorphism, responsibility displacement, and the underestimation of real risks posed by highly capable AI tools.