Chao-Kai Wen

Jiajia Guo, Chao-Kai Wen, Shi Jin et al.

Many performance gains achieved by massive multiple-input and multiple-output depend on the accuracy of the downlink channel state information (CSI) at the transmitter (base station), which is usually obtained by estimating at the receiver (user terminal) and feeding back to the transmitter. The overhead of CSI feedback occupies substantial uplink bandwidth resources, especially when the number of the transmit antennas is large. Deep learning (DL)-based CSI feedback refers to CSI compression and reconstruction by a DL-based autoencoder and can greatly reduce feedback overhead. In this paper, a comprehensive overview of state-of-the-art research on this topic is provided, beginning with basic DL concepts widely used in CSI feedback and then categorizing and describing some existing DL-based feedback works. The focus is on novel neural network architectures and utilization of communication expert knowledge to improve CSI feedback accuracy. Works on bit-level CSI feedback and joint design of CSI feedback with other communication modules are also introduced, and some practical issues, including training dataset collection, online training, complexity, generalization, and standardization effect, are discussed. At the end of the paper, some challenges and potential research directions associated with DL-based CSI feedback in future wireless communication systems are identified.

Jiajia Guo, Chao-Kai Wen, Shi Jin et al.

The 3rd Generation Partnership Project started the study of Release 18 in 2021. Artificial intelligence (AI)-native air interface is one of the key features of Release 18, where AI for channel state information (CSI) feedback enhancement is selected as the representative use case. This article provides an overview of AI for CSI feedback enhancement in 5G-Advanced. Several representative non-AI and AI-enabled CSI feedback frameworks are first introduced and compared. Then, the standardization of AI for CSI feedback enhancement in 5G-advanced is presented in detail. First, the scope of the AI for CSI feedback enhancement in 5G-Advanced is presented and discussed. Then, the main challenges and open problems in the standardization of AI for CSI feedback enhancement, especially focusing on performance evaluation and the design of new protocols for AI-enabled CSI feedback, are identified and discussed. This article provides a guideline for the standardization study of AI-based CSI feedback enhancement.

Jung-Chieh Chen, Hwei-Ming Chung, Chao-Kai Wen et al.

Efficient and accurate state estimation is essential for the optimal management of the future smart grid. However, to meet the requirements of deploying the future grid at a large scale, the state estimation algorithm must be able to accomplish two major tasks: (1) combining measurement data with different qualities to attain an optimal state estimate and (2) dealing with the large number of measurement data rendered by meter devices. To address these two tasks, we first propose a practical solution using a very short word length to represent a partial measurement of the system state in the meter device to reduce the amount of data. We then develop a unified probabilistic framework based on a Bayesian belief inference to incorporate measurements of different qualities to obtain an optimal state estimate. Simulation results demonstrate that the proposed scheme significantly outperforms other linear estimators in different test scenarios. These findings indicate that the proposed scheme not only has the ability to integrate data with different qualities but can also decrease the amount of data that needs to be transmitted and processed.

Hwei-Ming Chung, Bahram Alinia, Noel Crespi et al.

This paper studies charging scheduling problem of electric vehicles (EVs) in the scale of a microgrid (e.g., a university or town) where a set of charging stations are controlled by a central aggregator. A bi-objective optimization problem is formulated to jointly optimize total charging cost and user convenience. Then, a close-to-optimal online scheduling algorithm is proposed as solution. The algorithm achieves optimal charging cost and is near optimal in terms of user convenience. Moreover, the proposed method applies an efficient load forecasting technique to obtain future load information. The algorithm is assessed through simulation and compared to the previous studies. The results reveal that our method not only improves previous alternative methods in terms of Pareto-optimal solution of the bi-objective optimization problem, but also provides a close approximation for the load forecasting.

Xiangyi Li, Jiajia Guo, Chao-Kai Wen et al.

Deep learning has revolutionized the design of the channel state information (CSI) feedback module in wireless communications. However, designing the optimal neural network (NN) architecture for CSI feedback can be a laborious and time-consuming process. Manual design can be prohibitively expensive for customizing NNs to different scenarios. This paper proposes using neural architecture search (NAS) to automate the generation of scenario-customized CSI feedback NN architectures, thereby maximizing the potential of deep learning in exclusive environments. By employing automated machine learning and gradient-descent-based NAS, an efficient and cost-effective architecture design process is achieved. The proposed approach leverages implicit scene knowledge, integrating it into the scenario customization process in a data-driven manner, and fully exploits the potential of deep learning for each specific scenario. To address the issue of excessive search, early stopping and elastic selection mechanisms are employed, enhancing the efficiency of the proposed scheme. The experimental results demonstrate that the automatically generated architecture, known as Auto-CsiNet, outperforms manually-designed models in both reconstruction performance (achieving approximately a 14% improvement) and complexity (reducing it by approximately 50%). Furthermore, the paper analyzes the impact of the scenario on the NN architecture and its capacity.

Xinjie Li, Xingyu Zhou, Jing Zhang et al.

Superimposed pilot (SIP) transmission improves spectral efficiency by eliminating the dedicated pilot overhead required in orthogonal pilot (OP)-based schemes. However, SIP suffers from severe pilot-data coupling, which leads to a critical performance-complexity bottleneck at the receiver. To address this issue, this paper proposes a low-overhead transmission framework that revitalizes data-dependent superimposed training (DDST) with enhanced interference mitigation strategies. First, for quasi-static block-fading channels, an enhanced DDST receiver is developed to achieve non-iterative pilot-data decoupling by exploiting data-dependent algebraic structures. Second, to overcome the sensitivity of conventional DDST to channel variations and symbol misidentification in fast time-varying environments, a mix transmission scheme is developed. By strategically applying DDST to a subset of resource elements, the proposed scheme combines the interference-free transmission property of OP with the zero-pilot-overhead advantage of SIP, thereby improving demapping reliability and interference suppression. Furthermore, under the proposed mix scheme, a Vision Transformer-based neural receiver is designed to capture the orthogonal structure between pilots and perturbation-bearing data, as well as the underlying channel correlations, thereby relaxing the stringent quasi-static assumption required for interference disentanglement. Simulation results demonstrate that the proposed framework achieves significant performance gains in the low-to-medium SNR regime under time-varying channels while providing superior computational efficiency compared with state-of-the-art SIP receivers.

Chi-Jui Sung, Fan-Hao Lin, Tzu-Hao Huang et al.

Sixth-generation (6G) networks are envisioned to achieve full-band cognition by jointly utilizing spectrum resources from Frequency Range 1 (FR1) to Frequency Range 3 (FR3, 7-24 GHz). Realizing this vision faces two challenges. First, physicsbased ray tracing (RT), the standard tool for network planning and coverage modeling, becomes computationally prohibitive for multi-band and multi-directional analysis over large areas. Second, current 5G systems rely on inter-frequency measurement gaps for carrier aggregation and beam management, which reduce throughput, increase latency, and scale poorly as bands and beams proliferate. These limitations motivate a datadriven approach to infer high-frequency characteristics from low-frequency observations. This work proposes CommUNext, a unified deep learning framework for cross-band, multi-directional signal strength (SS) prediction. The framework leverages lowfrequency coverage data and crowd-aided partial measurements at the target band to generate high-fidelity FR3 predictions. Two complementary architectures are introduced: Full CommUNext, which substitutes costly RT simulations for large-scale offline modeling, and Partial CommUNext, which reconstructs incomplete low-frequency maps to mitigate measurement gaps in real-time operation. Experimental results show that CommUNext delivers accurate and robust high-frequency SS prediction even with sparse supervision, substantially reducing both simulation and measurement overhead.

Xingyu Zhou, Le Liang, Hao Ye et al.

Accurate channel state information (CSI) acquisition is essential for modern wireless systems, which becomes increasingly difficult under large antenna arrays, strict pilot overhead constraints, and diverse deployment environments. Existing artificial intelligence-based solutions often lack robustness and fail to generalize across scenarios. To address this limitation, this paper introduces a predictive-foundation-model-based channel estimation framework that enables accurate, low-overhead, and generalizable CSI acquisition. The proposed framework employs a predictive foundation model trained on large-scale cross-domain CSI data to extract universal channel representations and provide predictive priors with strong cross-scenario transferability. A pilot processing network based on a vision transformer architecture is further designed to capture spatial, temporal, and frequency correlations from pilot observations. An efficient fusion mechanism integrates predictive priors with real-time measurements, enabling reliable CSI reconstruction even under sparse or noisy conditions. Extensive evaluations across diverse configurations demonstrate that the proposed estimator significantly outperforms both classical and data-driven baselines in accuracy, robustness, and generalization capability.

Mengyuan Li, Qianfan Lu, Jiachen Tian et al.

In near-field extremely large-scale multiple-input multiple-output (XL-MIMO) systems, spherical wavefront propagation expands the traditional beam codebook into the joint angular-distance domain, rendering conventional beam training prohibitively inefficient, especially in complex 3-dimensional (3D) low-altitude environments. Furthermore, since near-field beam variations are deeply coupled not only with user positions but also with the physical surroundings, precise beam alignment demands profound environmental understanding capabilities. To address this, we propose a large language model (LLM)-driven multimodal framework that fuses historical GPS data, RGB image, LiDAR data, and strategically designed task-specific textual prompts. By utilizing the powerful emergent reasoning and generalization capabilities of the LLM, our approach learns complex spatial dynamics to achieve superior environmental comprehension...

Chu-Hsiang Huang, Chao-Kai Wen, Geoffrey Ye Li

Artificial intelligence (AI) and machine learning (ML) models are rapidly permeating the 5G Radio Access Network (RAN), powering beam management, channel state information (CSI) feedback, positioning, and mobility prediction. However, without a standardized life-cycle management (LCM) framework, challenges, such as model drift, vendor lock-in, and limited transparency, hinder large-scale adoption. 3GPP Releases 16-20 progressively evolve AI/ML from experimental features to managed, interoperable network functions. Beginning with the Network Data Analytics Function (NWDAF) in Rel-16, subsequent releases introduced standardized interfaces for model transfer, execution, performance monitoring, and closed-loop control, culminating in Rel-20's two-sided CSI-compression Work Item and vendor-agnostic LCM profile. This article reviews the resulting five-block LCM architecture, KPI-driven monitoring mechanisms, and inter-vendor collaboration schemes, while identifying open challenges in resource-efficient monitoring, environment drift detection, intelligent decision-making, and flexible model training. These developments lay the foundation for AI-native transceivers as a key enabler for 6G.

Jiajia Guo, Peiwen Jiang, Chao-Kai Wen et al.

Accurate channel state information (CSI) is critical to the performance of wireless communication systems, especially with the increasing scale and complexity introduced by 5G and future 6G technologies. While artificial intelligence (AI) offers a promising approach to CSI acquisition and utilization, existing methods largely depend on task-specific neural networks (NNs) that require expert-driven design and large training datasets, limiting their generalizability and practicality. To address these challenges, we propose LVM4CSI, a general and efficient framework that leverages the structural similarity between CSI and computer vision (CV) data to directly apply large vision models (LVMs) pre-trained on extensive CV datasets to wireless tasks without any fine-tuning, in contrast to large language model-based methods that generally necessitate fine-tuning. LVM4CSI maps CSI tasks to analogous CV tasks, transforms complex-valued CSI into visual formats compatible with LVMs, and integrates lightweight trainable layers to adapt extracted features to specific communication objectives. We validate LVM4CSI through three representative case studies, including channel estimation, human activity recognition, and user localization. Results demonstrate that LVM4CSI achieves comparable or superior performance to task-specific NNs, including an improvement exceeding 9.61 dB in channel estimation and approximately 40% reduction in localization error. Furthermore, it significantly reduces the number of trainable parameters and eliminates the need for task-specific NN design.

Xiaojie Li, Yu Han, Zhizheng Lu et al.

The upper 6 GHz (U6G) band with XL-MIMO is a key enabler for sixth-generation wireless systems, yet intelligent radiomap prediction for such systems remains challenging. Existing datasets support only small-scale arrays (up to 8x8) with predominantly isotropic antennas, far from the 1024-element directional arrays envisioned for 6G. Moreover, current methods encode array configurations as scalar parameters, forcing neural networks to extrapolate array-specific radiation patterns, which fails when predicting radiomaps for configurations absent from training data. To jointly address data scarcity and generalization limitations, this paper advances XL-MIMO radiomap prediction from three aspects. To overcome data limitations, we construct the first XL-MIMO radiomap dataset containing 78400 radiomaps across 800 urban scenes, five frequency bands (1.8-6.7 GHz), and nine array configurations up to 32x32 uniform planar arrays with directional elements. To enable systematic evaluation, we establish a comprehensive benchmark framework covering practical scenarios from coverage estimation without field measurements to generalization across unseen configurations and environments. To enable generalization to arbitrary beam configurations without retraining, we propose the beam map, a physics-informed spatial feature that analytically computes array-specific coverage patterns. By decoupling deterministic array radiation from data learned multipath propagation, beam maps shift generalization from neural network extrapolation to physics-based computation. Integrating beam maps into existing architectures reduces mean absolute error by up to 60.0% when generalizing to unseen configurations and up to 50.5% when transferring to unseen environments. The complete dataset and code are publicly available at https://lxj321.github.io/MulticonfigRadiomapDataset/.

Muhan Chen, Jiajia Guo, Chao-Kai Wen et al.

Massive multiple-input multiple-output can obtain more performance gain by exploiting the downlink channel state information (CSI) at the base station (BS). Therefore, studying CSI feedback with limited communication resources in frequency-division duplexing systems is of great importance. Recently, deep learning (DL)-based CSI feedback has shown considerable potential. However, the existing DL-based explicit feedback schemes are difficult to deploy because current fifth-generation mobile communication protocols and systems are designed based on an implicit feedback mechanism. In this paper, we propose a DL-based implicit feedback architecture to inherit the low-overhead characteristic, which uses neural networks (NNs) to replace the precoding matrix indicator (PMI) encoding and decoding modules. By using environment information, the NNs can achieve a more refined mapping between the precoding matrix and the PMI compared with codebooks. The correlation between subbands is also used to further improve the feedback performance. Simulation results show that, for a single resource block (RB), the proposed architecture can save 25.0% and 40.0% of overhead compared with Type I codebook under two antenna configurations, respectively. For a wideband system with 52 RBs, overhead can be saved by 30.7% and 48.0% compared with Type II codebook when ignoring and considering extracting subband correlation, respectively.

Jiajia Guo, Chao-Kai Wen, Shi Jin

In frequency-division duplexing systems, the downlink channel state information (CSI) acquisition scheme leads to high training and feedback overheads. In this paper, we propose an uplink-aided downlink channel acquisition framework using deep learning to reduce these overheads. Unlike most existing works that focus only on channel estimation or feedback modules, to the best of our knowledge, this is the first study that considers the entire downlink CSI acquisition process, including downlink pilot design, channel estimation, and feedback. First, we propose an adaptive pilot design module by exploiting the correlation in magnitude among bidirectional channels in the angular domain to improve channel estimation. Next, to avoid the bit allocation problem during the feedback module, we concatenate the complex channel and embed the uplink channel magnitude to the channel reconstruction at the base station. Lastly, we combine the above two modules and compare two popular downlink channel acquisition frameworks. The former framework estimates and feeds back the channel at the user equipment subsequently. The user equipment in the latter one directly feeds back the received pilot signals to the base station. Our results reveal that, with the help of uplink, directly feeding back the pilot signals can save approximately 20% of feedback bits, which provides a guideline for future research.

Chang-Jen Wang, Chao-Kai Wen, Shang-Ho et al.

Phase retrieval (PR) is an important component in modern computational imaging systems. Many algorithms have been developed over the past half-century. Recent advances in deep learning have introduced new possibilities for a robust and fast PR. An emerging technique called deep unfolding provides a systematic connection between conventional model-based iterative algorithms and modern data-based deep learning. Unfolded algorithms, which are powered by data learning, have shown remarkable performance and convergence speed improvement over original algorithms. Despite their potential, most existing unfolded algorithms are strictly confined to a fixed number of iterations when layer-dependent parameters are used. In this study, we develop a novel framework for deep unfolding to overcome existing limitations. Our development is based on an unfolded generalized expectation consistent signal recovery (GEC-SR) algorithm, wherein damping factors are left for data-driven learning. In particular, we introduce a hypernetwork to generate the damping factors for GEC-SR. Instead of learning a set of optimal damping factors directly, the hypernetwork learns how to generate the optimal damping factors according to the clinical settings, thereby ensuring its adaptivity to different scenarios. To enable the hypernetwork to adapt to varying layer numbers, we use a recurrent architecture to develop a dynamic hypernetwork that generates a damping factor that can vary online across layers. We also exploit a self-attention mechanism to enhance the robustness of the hypernetwork. Extensive experiments show that the proposed algorithm outperforms existing ones in terms of convergence speed and accuracy and still works well under very harsh settings, even under which many classical PR algorithms are unstable.

Hengtao He, Chao-Kai Wen, Shi Jin et al.

In this paper, we investigate the model-driven deep learning (DL) for MIMO detection. In particular, the MIMO detector is specially designed by unfolding an iterative algorithm and adding some trainable parameters. Since the number of trainable parameters is much fewer than the data-driven DL based signal detector, the model-driven DL based MIMO detector can be rapidly trained with a much smaller data set. The proposed MIMO detector can be extended to soft-input soft-output detection easily. Furthermore, we investigate joint MIMO channel estimation and signal detection (JCESD), where the detector takes channel estimation error and channel statistics into consideration while channel estimation is refined by detected data and considers the detection error. Based on numerical results, the model-driven DL based MIMO detector significantly improves the performance of corresponding traditional iterative detector, outperforms other DL-based MIMO detectors and exhibits superior robustness to various mismatches.

Jing Zhang, Hengtao He, Chao-Kai Wen et al.

Channel estimation and signal detection are very challenging for an orthogonal frequency division multiplexing (OFDM) system without cyclic prefix (CP). In this article, deep learning based on orthogonal approximate message passing (DL-OAMP) is used to address these problems. The DL-OAMP receiver includes a channel estimation neural network (CE-Net) and a signal detection neural network based on OAMP, called OAMP-Net. The CE-Net is initialized by the least square channel estimation algorithm and refined by minimum mean-squared error (MMSE) neural network. The OAMP-Net is established by unfolding the iterative OAMP algorithm and adding some trainable parameters to improve the detection performance. The DL-OAMP receiver is with low complexity and can estimate time-varying channels with only a single training. Simulation results demonstrate that the bit-error rate (BER) of the proposed scheme is lower than those of competitive algorithms for high-order modulation.

Peiwen Jiang, Tianqi Wang, Bin Han et al.

Orthogonal frequency division multiplexing (OFDM) has been widely applied in current communication systems. The artificial intelligence (AI)-aided OFDM receivers are currently brought to the forefront to replace and improve the traditional OFDM receivers. In this study, we first compare two AI-aided OFDM receivers, namely, data-driven fully connected deep neural network and model-driven ComNet, through extensive simulation and real-time video transmission using a 5G rapid prototyping system for an over-the-air (OTA) test. We find a performance gap between the simulation and the OTA test caused by the discrepancy between the channel model for offline training and the real environment. We develop a novel online training system, which is called SwitchNet receiver, to address this issue. This receiver has a flexible and extendable architecture and can adapt to real channels by training only several parameters online. From the OTA test, the AI-aided OFDM receivers, especially the SwitchNet receiver, are robust to real environments and promising for future communication systems. We discuss potential challenges and future research inspired by our initial study in this paper.

Hengtao He, Shi Jin, Chao-Kai Wen et al.

Intelligent communication is gradually considered as the mainstream direction in future wireless communications. As a major branch of machine learning, deep learning (DL) has been applied in physical layer communications and has demonstrated an impressive performance improvement in recent years. However, most of the existing works related to DL focus on data-driven approaches, which consider the communication system as a black box and train it by using a huge volume of data. Training a network requires sufficient computing resources and extensive time, both of which are rarely found in communication devices. By contrast, model-driven DL approaches combine communication domain knowledge with DL to reduce the demand for computing resources and training time. This article reviews the recent advancements in the application of model-driven DL approaches in physical layer communications, including transmission scheme, receiver design, and channel information recovery. Several open issues for further research are also highlighted after presenting the comprehensive survey.

Hwei-Ming Chung, Wen-Tai Li, Chau Yuen et al.

A well-designed attack in the power system can cause an initial failure and then results in large-scale cascade failure. Several works have discussed power system attack through false data injection, line-maintaining attack, and line-removing attack. However, the existing methods need to continuously attack the system for a long time, and, unfortunately, the performance cannot be guaranteed if the system states vary. To overcome this issue, we consider a new type of attack strategy called combinational attack which masks a line-outage at one position but misleads the control center on line outage at another position. Therefore, the topology information in the control center is interfered by our attack. We also offer a procedure of selecting the vulnerable lines of its kind. The proposed method can effectively and continuously deceive the control center in identifying the actual position of line-outage. The system under attack will be exposed to increasing risks as the attack continuously. Simulation results validate the efficiency of the proposed attack strategy.