To achieve the potential performance gain of massive multiple-input multiple-output (MIMO) systems, base stations (BS) require downlink channel state information (CSI) fed back by users to execute beamforming design, especially in the frequency division duplex (FDD) systems. However, due to the enormous number of antennas in massive MIMO systems, the feedback overhead of downlink CSI acquisition is extremely large. To address this issue, deep learning (DL) techniques have been introduced to develop high-accuracy feedback strategies under limited backhaul constraints. In this paper, we provide an overview of DL-based CSI compression and feedback approaches in massive MIMO systems. Specifically, we introduce the conventional CSI compression and feedback schemes and the existing problems. Besides, we elaborate on various DL techniques employed in CSI compression from the perspective of network architecture and analyze the advantages of different techniques. We also enumerate the applications of DL-based methods for solving practical challenges in CSI compression and feedback. In addition, we brief the remaining issues in deep CSI compression and indicate potential directions in future wireless networks.

Cell-free (CF) multiple-input multiple-output (MIMO) is a promising technique to enable the vision of ubiquitous wireless connectivity for next-generation network communications. Compared to traditional co-located massive MIMO, CF MIMO allows geographically distributed access points (APs) to serve all users on the same time-frequency resource with spatial multiplexing techniques, resulting in better performance in terms of both spectral efficiency and coverage enhancement. However, the performance gain is achieved at the expense of deploying more APs with high cost and power consumption. To address this issue, the recently proposed reconfigurable intelligent surface (RIS) technique stands out with its unique advantages of low cost, low energy consumption and programmability. In this paper, we provide an overview of RIS-assisted CF MIMO and its interaction with advanced optimization designs and novel applications. Particularly, recent studies on typical performance metrics such as energy efficiency (EE) and spectral efficiency (SE) are surveyed. Besides, the application of RIS-assisted CF MIMO techniques in various future communication systems is also envisioned. Additionally, we briefly discuss the technical challenges and open problems for this area to inspire research direction and fully exploit its potential in meeting the demands of future wireless communication systems.