Wenyue Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Wenyue Zhou has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Chuan Zhang
LEADS, the National Mobile Communications Research Laboratory, and the Frontiers Science Center for Mobile Information Communication and Security, Southeast University, Nanjing, China
25 shared publications - Yongming Huang
National Mobile Communications Research Laboratory, Southeast University, Nanjing, China
20 shared publications - Xiaohu You
Southeast University
17 shared publications - Xiaosi Tan
LEADS, the National Mobile Communications Research Laboratory, and the Frontiers Science Center for Mobile Information Communication and Security, Southeast University, Nanjing, China
8 shared publications - Jian Zheng
LEADS, the National Mobile Communications Research Laboratory, and the Frontiers Science Center for Mobile Information Communication and Security, Southeast University, Nanjing, China
5 shared publications - Zeqiong Tan
LEADS the National Mobile Communications Research Laboratory, and the Frontiers Science Center for Mobile Information Communication and Security, Southeast University, Nanjing, China
5 shared publications
Latest Publications
- 13 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 1861-1865
AttnMPNet: An Attention-Based Message Passing Network for MIMO Detection
In this letter, we propose AttnMPNet, an attention-based message passing neural network for massive multiple-input multiple-output (MIMO) detection. AttnMPNet integrates Gaussian approximated message passing with self-attention to iteratively refine soft posterior estimates for each transmitted symbol. Within each iteration, approximate likelihood messages are first constructed and then processed through attention blocks to capture inter-symbol dependencies, followed by symbol-wise posterior probability estimation. To support this inference pipeline, we further design a compact and expressive feature representation that enables both efficient computation and high detection accuracy in massive MIMO scenarios. Simulation results show that AttnMPNet achieves near-maximum-likelihood performance across diverse MIMO configurations while significantly reducing inference latency compared to neural baselines.
- 13 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 1861-1865
AttnMPNet: An Attention-Based Message Passing Network for MIMO Detection
In this letter, we propose AttnMPNet, an attention-based message passing neural network for massive multiple-input multiple-output (MIMO) detection. AttnMPNet integrates Gaussian approximated message passing with self-attention to iteratively refine soft posterior estimates for each transmitted symbol. Within each iteration, approximate likelihood messages are first constructed and then processed through attention blocks to capture inter-symbol dependencies, followed by symbol-wise posterior probability estimation. To support this inference pipeline, we further design a compact and expressive feature representation that enables both efficient computation and high detection accuracy in massive MIMO scenarios. Simulation results show that AttnMPNet achieves near-maximum-likelihood performance across diverse MIMO configurations while significantly reducing inference latency compared to neural baselines.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 25 (15361276) , 12309-12324
FCBsP: Fixed-Constellation Belief-Selective Propagation Detection for MIMO Turbo Receivers
The belief-selective propagation (BsP) algorithm has recently emerged as a promising approach for massive MIMO detection. However, when applied in MIMO turbo receivers, known for their superior performance compared to separated detection and decoding (SDD) receivers, the BsP-based receiver suffers from significant performance degradation and high processing latency. To overcome these limitations, this paper proposes a fixed-constellation BsP (FCBsP) detector tailored for MIMO turbo receivers. By building fixed configuration sets and utilizing the approximate multi-user interference for message updates, the proposed FCBsP detector achieves a better trade-off between error performance and computational complexity compared to the BsP. Furthermore, two unexplored features: information compensation and decoding-first mechanism are proposed to fine-tune the exchanged information and lower the processing latency of the FCBsP-based turbo receiver. Numerical results demonstrate that the proposed FCBsP-based turbo receiver earns about 0.7 and 1.8 dB performance gains over the BsP-based turbo receiver at BLER=10−3 in an LDPC-coded 32 × 12 64-QAM MIMO system under Rayleigh and practical channels, respectively.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 25 (15361276) , 12309-12324
FCBsP: Fixed-Constellation Belief-Selective Propagation Detection for MIMO Turbo Receivers
The belief-selective propagation (BsP) algorithm has recently emerged as a promising approach for massive MIMO detection. However, when applied in MIMO turbo receivers, known for their superior performance compared to separated detection and decoding (SDD) receivers, the BsP-based receiver suffers from significant performance degradation and high processing latency. To overcome these limitations, this paper proposes a fixed-constellation BsP (FCBsP) detector tailored for MIMO turbo receivers. By building fixed configuration sets and utilizing the approximate multi-user interference for message updates, the proposed FCBsP detector achieves a better trade-off between error performance and computational complexity compared to the BsP. Furthermore, two unexplored features: information compensation and decoding-first mechanism are proposed to fine-tune the exchanged information and lower the processing latency of the FCBsP-based turbo receiver. Numerical results demonstrate that the proposed FCBsP-based turbo receiver earns about 0.7 and 1.8 dB performance gains over the BsP-based turbo receiver at BLER=10−3 in an LDPC-coded 32 × 12 64-QAM MIMO system under Rayleigh and practical channels, respectively.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 1489-1493
ATLBO-Q: Adaptive TLBO-Based Quantization for MMSE MIMO Detection
Quantization is of significance for multiple-input multiple-output (MIMO) detector design in wireless communication systems. Existing uniform quantization methods suffer from high bitwidth redundancy and inefficient hardware resource utilization, while machine-learning-based automatic quantization frameworks introduce considerable computational burden. In this letter, an adaptive teaching-learning-based-optimization (TLBO)-based quantization (ATLBO-Q) framework is proposed for minimum mean square error MIMO detectors, where Cholesky decomposition is utilized to eliminate floating-point matrix inversion operations. The bitwidth assignments are optimized iteratively through an adaptive teacher-learner phase, avoiding the complex training procedures. Simulation results demonstrate that the proposed ATLBO-Q achieves significant reduction in average bitwidth and computational complexity while maintaining near-floating-point bit error rate performance, thereby attaining a desirable trade-off between the detection precision and hardware efficiency.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 1489-1493
ATLBO-Q: Adaptive TLBO-Based Quantization for MMSE MIMO Detection
Quantization is of significance for multiple-input multiple-output (MIMO) detector design in wireless communication systems. Existing uniform quantization methods suffer from high bitwidth redundancy and inefficient hardware resource utilization, while machine-learning-based automatic quantization frameworks introduce considerable computational burden. In this letter, an adaptive teaching-learning-based-optimization (TLBO)-based quantization (ATLBO-Q) framework is proposed for minimum mean square error MIMO detectors, where Cholesky decomposition is utilized to eliminate floating-point matrix inversion operations. The bitwidth assignments are optimized iteratively through an adaptive teacher-learner phase, avoiding the complex training procedures. Simulation results demonstrate that the proposed ATLBO-Q achieves significant reduction in average bitwidth and computational complexity while maintaining near-floating-point bit error rate performance, thereby attaining a desirable trade-off between the detection precision and hardware efficiency.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74, 13672-13686
WeFTNet: DNN-Aided Weighted Fourier Transform Approximate MMSE Detection for Massive MIMO
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74, 13672-13686
WeFTNet: DNN-Aided Weighted Fourier Transform Approximate MMSE Detection for Massive MIMO
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 4981-4985
Robust Beamforming Design for Cell-Free MIMO ISAC Systems With Imperfect CSI
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 4981-4985
Robust Beamforming Design for Cell-Free MIMO ISAC Systems With Imperfect CSI
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 4996-5000
LR-BsP: Lattice Reduction-Aided Belief-Selective Propagation for Correlated MIMO Detection
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 4996-5000
LR-BsP: Lattice Reduction-Aided Belief-Selective Propagation for Correlated MIMO Detection
- 2 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 750-754
DeepSAQ: Deep Learning-Driven Sensitivity-Aware Quantization for MMSE MIMO Detection
Hardware-efficient quantization strategies are imperative for massive MIMO detectors. However, conventional methods such as unified quantization and manual tuning respectively suffer from bitwidth redundancy and prohibitive exploration overhead. To address these challenges, this letter proposes a deep learning-driven sensitivity-aware quantization (DeepSAQ) framework, which includes: 1) A gradient-driven framework with a Bayesian optimized loss function to minimize fractional bitwidths; 2) Sensitivity-aware tuning to compress the fractional bitwidth redundancy; 3) Range-extended integral bitwidths to further improve the quantization efficiency. Applying to the unfolded MMSE-wNSA detection, the proposed framework delivers floating-point comparable performance but reduces 50.04% average bitwidths and 50.47% computational complexity compared to the unified quantization. Benchmarking with the recent art, the proposed framework succeeds in squeezing up to 18.32% bitwidths and 21.23% computational complexity in 8 $\times $ 128 64-QAM MIMO systems.
- 2 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 750-754
DeepSAQ: Deep Learning-Driven Sensitivity-Aware Quantization for MMSE MIMO Detection
Hardware-efficient quantization strategies are imperative for massive MIMO detectors. However, conventional methods such as unified quantization and manual tuning respectively suffer from bitwidth redundancy and prohibitive exploration overhead. To address these challenges, this letter proposes a deep learning-driven sensitivity-aware quantization (DeepSAQ) framework, which includes: 1) A gradient-driven framework with a Bayesian optimized loss function to minimize fractional bitwidths; 2) Sensitivity-aware tuning to compress the fractional bitwidth redundancy; 3) Range-extended integral bitwidths to further improve the quantization efficiency. Applying to the unfolded MMSE-wNSA detection, the proposed framework delivers floating-point comparable performance but reduces 50.04% average bitwidths and 50.47% computational complexity compared to the unified quantization. Benchmarking with the recent art, the proposed framework succeeds in squeezing up to 18.32% bitwidths and 21.23% computational complexity in 8 $\times $ 128 64-QAM MIMO systems.
- 11 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 495-499
EP-based Distributed Message Passing Detection for Cell-Free Massive MIMO
Expectation propagation (EP) has been applied to signal detection in Cell-Free massive MIMO (CF-mMIMO) systems to achieve high performance. However, its computational complexity becomes prohibitive as the number of users and antennas increases. In this letter, we apply the EP-based approximate message passing framework to CF-mMIMO and propose a distributed detector, called EP-dAMP, which efficiently distributes computational tasks between the access points (APs) and the central processing unit (CPU) by offloading part of the computations from the APs to the CPU. Building on this foundation, we further propose a low-complexity variant, LC-dAMP, designed to reduce the computational demands on APs and achieve lower fronthaul overhead. Simulation results demonstrate that both algorithms can achieve a complexity reduction of 85%-94% compared to existing non-linear detectors for CF-mMIMO while achieving better bit error rate (BER) performance.
- 11 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 495-499
EP-based Distributed Message Passing Detection for Cell-Free Massive MIMO
Expectation propagation (EP) has been applied to signal detection in Cell-Free massive MIMO (CF-mMIMO) systems to achieve high performance. However, its computational complexity becomes prohibitive as the number of users and antennas increases. In this letter, we apply the EP-based approximate message passing framework to CF-mMIMO and propose a distributed detector, called EP-dAMP, which efficiently distributes computational tasks between the access points (APs) and the central processing unit (CPU) by offloading part of the computations from the APs to the CPU. Building on this foundation, we further propose a low-complexity variant, LC-dAMP, designed to reduce the computational demands on APs and achieve lower fronthaul overhead. Simulation results demonstrate that both algorithms can achieve a complexity reduction of 85%-94% compared to existing non-linear detectors for CF-mMIMO while achieving better bit error rate (BER) performance.
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (12) , 19282-19293
OptiMISD: Optimized MCTS Integrated Sphere Decoder for Challenging MIMO Detection
With rapid advancements in wireless communications, MIMO systems are evolving to include a greater number of antennas and higher modulation orders. In these challenging environments, traditional linear detectors such as the MMSE often fall short in delivering satisfactory performance. While tree-search based detectors like the sphere decoder (SD) and K-Best detector can improve outcomes, they suffer from prohibitive complexity due to the vast search space. This article introduces OptiMISD—an optimized Monte Carlo tree search (MCTS) integrated sphere decoder, designed specifically for challenging MIMO detection scenarios. We propose three innovative techniques to enhance its efficacy: 1) a partial K-Best approach, 2) a fast upper confidence for trees (UCT) policy, and 3) a radius restriction method. Our numerical results demonstrate that OptiMISD not only achieves a performance gain of over 3 dB compared to the K-Best detector (with K = 64) @ BER = 10−4 but also reduces complexity by up to 84.9%. Additionally, the principles of OptiMISD can be adapted to address other tree-search based challenges.
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (12) , 19282-19293
OptiMISD: Optimized MCTS Integrated Sphere Decoder for Challenging MIMO Detection
With rapid advancements in wireless communications, MIMO systems are evolving to include a greater number of antennas and higher modulation orders. In these challenging environments, traditional linear detectors such as the MMSE often fall short in delivering satisfactory performance. While tree-search based detectors like the sphere decoder (SD) and K-Best detector can improve outcomes, they suffer from prohibitive complexity due to the vast search space. This article introduces OptiMISD—an optimized Monte Carlo tree search (MCTS) integrated sphere decoder, designed specifically for challenging MIMO detection scenarios. We propose three innovative techniques to enhance its efficacy: 1) a partial K-Best approach, 2) a fast upper confidence for trees (UCT) policy, and 3) a radius restriction method. Our numerical results demonstrate that OptiMISD not only achieves a performance gain of over 3 dB compared to the K-Best detector (with K = 64) @ BER = 10−4 but also reduces complexity by up to 84.9%. Additionally, the principles of OptiMISD can be adapted to address other tree-search based challenges.