Ultra-massive multiple-input multiple-output (UM-MIMO) is a cutting-edge technology that promises to revolutionize wireless networks by providing an unprecedentedly high spectral and energy efficiency. The enlarged array aperture of UM-MIMO facilitates the accessibility of the near-field region, thereby offering a novel degree of freedom for communications and sensing. Nevertheless, the transceiver design for such systems is challenging because of the enormous system scale, the complicated channel characteristics, and the uncertainties in propagation environments. Therefore, it is critical to study scalable, low-complexity, and robust algorithms that can efficiently characterize and leverage the properties of the near-field channel. In this article, we will advocate two general frameworks from an artificial intelligence (AI)-native perspective, which are tailored for the algorithmic design of near-field UM-MIMO transceivers. Specifically, the frameworks for both iterative and non-iterative algorithms are discussed. Near-field beam focusing and channel estimation are presented as two tutorial-style examples to demonstrate the significant advantages of the proposed AI-native frameworks in terms of various key performance indicators.

翻译：超大规模多输入多输出（UM-MIMO）是一项前沿技术，通过提供前所未有的高频谱效率和能量效率，有望彻底革新无线网络。UM-MIMO增大的阵列孔径促进了近场区域的通达性，从而为通信与感知提供了全新的自由度。然而，由于系统规模庞大、信道特性复杂以及传播环境的不确定性，此类系统的收发机设计面临巨大挑战。因此，研究能够高效表征并利用近场信道特性的可扩展、低复杂度且鲁棒的算法至关重要。本文从人工智能（AI）原生视角提出两种通用框架，专为近场UM-MIMO收发机的算法设计量身定制。具体而言，讨论了迭代算法与非迭代算法两种框架。通过近场波束聚焦与信道估计两个教程式示例，阐明了所提AI原生框架在多个关键性能指标上的显著优势。