Kaixuan Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kaixuan Huang has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Shunqing Zhang
Shanghai University
10 shared publications - Guangjin Pan
Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden
4 shared publications - Henk Wymeersch
Chalmers University of Technology
2 shared publications - Jihong Li
School of Communication and Information Engineering, Shanghai University, Shanghai, China
2 shared publications - Lixiang Lian
ShanghaiTech University
2 shared publications - Tao Yu
School of Communication and Information Engineering, Shanghai University, Shanghai, China
2 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (23) , 58411-58425
Decision-Aware Joint Blockage Prediction and Proactive Beamforming for Dynamic mmWave Networks
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (23) , 58411-58425
Decision-Aware Joint Blockage Prediction and Proactive Beamforming for Dynamic mmWave Networks
- 25 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP (15) , 1
Few-Shot Cross-Domain Indoor Localization via Multi-Modal Feature Refinement
Fingerprint-based indoor localization is a critical enabling technology for Internet of Things (IoT) applications, where the primary challenges stem from complex environmental variability and prohibitive costs of data collection and labeling. This paper introduces a cross-domain multi-modal indoor localization framework that effectively combines visual and WiFi signals using few-shot learning techniques, achieving improved localization performance with minimal training data. We derive an upper bound on the generalized transfer localization error. Based on this bound, our learning-based approach applies feature-level knowledge distillation from pre-trained localization models. This process systematically calibrates discrepancies in feature distributions between the source and target environments. As a result, the proposed method significantly reduces the dependence on large labeled datasets. Experimental results demonstrate that our proposed method achieves substantial improvements over state-of-the-art localization models, with a mean localization error of 0.247 meters across diverse indoor environments, while requiring substantially fewer labeled samples in the target domain.
- 25 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP (15) , 1
Few-Shot Cross-Domain Indoor Localization via Multi-Modal Feature Refinement
Fingerprint-based indoor localization is a critical enabling technology for Internet of Things (IoT) applications, where the primary challenges stem from complex environmental variability and prohibitive costs of data collection and labeling. This paper introduces a cross-domain multi-modal indoor localization framework that effectively combines visual and WiFi signals using few-shot learning techniques, achieving improved localization performance with minimal training data. We derive an upper bound on the generalized transfer localization error. Based on this bound, our learning-based approach applies feature-level knowledge distillation from pre-trained localization models. This process systematically calibrates discrepancies in feature distributions between the source and target environments. As a result, the proposed method significantly reduces the dependence on large labeled datasets. Experimental results demonstrate that our proposed method achieves substantial improvements over state-of-the-art localization models, with a mean localization error of 0.247 meters across diverse indoor environments, while requiring substantially fewer labeled samples in the target domain.
- 30 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 2393-2397
A Low-Complexity Joint Antenna Selection and Beamforming Scheme for Single-Anchor Multi-Antenna SPEB-Based Indoor Localization
Single-anchor multi-antenna indoor localization confronts critical challenges, including significant pilot overheads, channel reciprocity impairments, and complicated resource optimization. To address these issues, this paper proposes a low-complexity joint antenna selection and beamforming scheme for squared position error bound (SPEB) minimization. The scheme first performs correlation-guided thresholding to extract an informative subspace, which provides a high-quality warm start. It then applies a closed-form worst-case reformulation of reciprocity mismatch, converting the original minmax SPEB design into a deterministic worst-case surrogate that is efficiently optimized via projected-gradient (PG) beamforming updates. A gating-based sensitivity proxy is further employed to refine the active antenna subset without expensive combinatorial search. Theoretical and numerical results show that our proposed scheme can achieve sub-meter localization accuracy while significantly reducing computational complexity.
- 30 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15 (21622337) , 2393-2397
A Low-Complexity Joint Antenna Selection and Beamforming Scheme for Single-Anchor Multi-Antenna SPEB-Based Indoor Localization
Single-anchor multi-antenna indoor localization confronts critical challenges, including significant pilot overheads, channel reciprocity impairments, and complicated resource optimization. To address these issues, this paper proposes a low-complexity joint antenna selection and beamforming scheme for squared position error bound (SPEB) minimization. The scheme first performs correlation-guided thresholding to extract an informative subspace, which provides a high-quality warm start. It then applies a closed-form worst-case reformulation of reciprocity mismatch, converting the original minmax SPEB design into a deterministic worst-case surrogate that is efficiently optimized via projected-gradient (PG) beamforming updates. A gating-based sensitivity proxy is further employed to refine the active antenna subset without expensive combinatorial search. Theoretical and numerical results show that our proposed scheme can achieve sub-meter localization accuracy while significantly reducing computational complexity.
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications
- Vol. PP (15361284) , 1-10
TREE: Token-Responsive Energy Efficiency Framework For Green AI-Integrated 6G Networks
As wireless networks evolve toward AI-integrated intelligence, conventional energy-efficiency metrics fail to capture the value of AI tasks. In this paper, we propose a novel EE metric called Token-Responsive Energy Efficiency (TREE), which incorporates the token throughput of large models as network utility carriers into the system utility. Based on this metric, we analyze the design principles of AI-integrated 6G networks from the perspective of three critical AI elements, namely computing power, model and data. Case studies validate TREE’s unique capability to expose energy-service asymmetries in hybrid traffic scenarios where conventional metrics prove inadequate. Although it is impossible to determine every design detail of AI-integrated 6G network at current time, we believe that the proposed TREE based framework will help the network operators to quantify the operating energy cost of AI services and continue to evolve towards sustainable 6G networks.
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications
- Vol. PP (15361284) , 1-10
TREE: Token-Responsive Energy Efficiency Framework For Green AI-Integrated 6G Networks
As wireless networks evolve toward AI-integrated intelligence, conventional energy-efficiency metrics fail to capture the value of AI tasks. In this paper, we propose a novel EE metric called Token-Responsive Energy Efficiency (TREE), which incorporates the token throughput of large models as network utility carriers into the system utility. Based on this metric, we analyze the design principles of AI-integrated 6G networks from the perspective of three critical AI elements, namely computing power, model and data. Case studies validate TREE’s unique capability to expose energy-service asymmetries in hybrid traffic scenarios where conventional metrics prove inadequate. Although it is impossible to determine every design detail of AI-integrated 6G network at current time, we believe that the proposed TREE based framework will help the network operators to quantify the operating energy cost of AI services and continue to evolve towards sustainable 6G networks.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- p. 1
GAP-LWLM: Geometry-Aware Prompt Tuning for Cross-Scene Localization with a Wireless Foundation Model
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- p. 1
Open AccessGAP-LWLM: Geometry-Aware Prompt Tuning for Cross-Scene Localization with a Wireless Foundation Model
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 25, 21449-21464
Large Wireless Localization Model (LWLM): A Foundation Model for Positioning in 6G Networks
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 25, 21449-21464
Open AccessLarge Wireless Localization Model (LWLM): A Foundation Model for Positioning in 6G Networks
- 20 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 14 (8) , 2426-2430
A Three-Stage Physics-Driven Transmission Scheme for Integrated Sensing and Communication Systems With Noisy Angular Information
Integrated sensing and communication (ISAC) can facilitate both data transmission and environment sensing on a unified hardware platform. In the physical environment, the sensing targets may serve as part of the communication channel scatterers, which results in correlations between communication and sensing channel. In this letter, we propose to exploit such physics-driven correlations to design a three-stage transmission schemes to enhance the robustness of the ISAC system against noisy angular information, which refers to the error for estimating the angle of departure/arrival (AoD/AoA). In particular, we match angle information driven by the physical environment and fune-tune the matched pairs. Furthermore, we exploit this correlations to design a beamforming hybrid design algorithm based on optimal performance bound, which improving the robustness of system. Through numerical simulations, we verify that the correlation between communication and sensing channels can be effectively exploited to design transmission schemes that showcase improved sensing and communication performances with noisy angular information.
- 20 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 14 (8) , 2426-2430
A Three-Stage Physics-Driven Transmission Scheme for Integrated Sensing and Communication Systems With Noisy Angular Information
Integrated sensing and communication (ISAC) can facilitate both data transmission and environment sensing on a unified hardware platform. In the physical environment, the sensing targets may serve as part of the communication channel scatterers, which results in correlations between communication and sensing channel. In this letter, we propose to exploit such physics-driven correlations to design a three-stage transmission schemes to enhance the robustness of the ISAC system against noisy angular information, which refers to the error for estimating the angle of departure/arrival (AoD/AoA). In particular, we match angle information driven by the physical environment and fune-tune the matched pairs. Furthermore, we exploit this correlations to design a beamforming hybrid design algorithm based on optimal performance bound, which improving the robustness of system. Through numerical simulations, we verify that the correlation between communication and sensing channels can be effectively exploited to design transmission schemes that showcase improved sensing and communication performances with noisy angular information.
- 6 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (14) , 28582-28597
A Unified QoS-Aware Multiplexing Framework for Next-Generation Immersive Communication With Legacy Wireless Applications
Immersive communication, including emerging augmented reality, virtual reality, and holographic telepresence, has been identified as a key service for enabling next-generation wireless applications. To align with legacy wireless applications, such as enhanced mobile broadband or ultrareliable low-latency communication, network slicing (NS) has been widely adopted. However, attempting to statistically isolate the above types of wireless applications through different network slices may lead to throughput degradation and increased queue backlog. To address these challenges, we establish a unified Quality of Service-aware framework that supports immersive communication and legacy wireless applications simultaneously. Based on the Lyapunov drift theorem, we transform the original long-term throughput maximization problem into an equivalent short-term throughput maximization weighted by virtual queue length. Moreover, to cope with the challenges introduced by the interaction between large-timescale NS and short-timescale resource allocation, we propose an adaptive adversarial slicing (Ad2S) scheme for networks with invarying channel statistics. To track the network channel variations, we also propose a measurement extrapolation-Kalman filter (ME-KF)-based method and refine our scheme into Ad2S-nonstationary refinement (Ad2S-NR). Through extended numerical examples, we demonstrate that our proposed schemes achieve 3.86 Mb/s throughput improvement and 63.96% latency reduction with 24.36% convergence time reduction. Within our framework, the tradeoff between total throughput and user service experience can be achieved by tuning systematic parameters.
- 6 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (14) , 28582-28597
A Unified QoS-Aware Multiplexing Framework for Next-Generation Immersive Communication With Legacy Wireless Applications
Immersive communication, including emerging augmented reality, virtual reality, and holographic telepresence, has been identified as a key service for enabling next-generation wireless applications. To align with legacy wireless applications, such as enhanced mobile broadband or ultrareliable low-latency communication, network slicing (NS) has been widely adopted. However, attempting to statistically isolate the above types of wireless applications through different network slices may lead to throughput degradation and increased queue backlog. To address these challenges, we establish a unified Quality of Service-aware framework that supports immersive communication and legacy wireless applications simultaneously. Based on the Lyapunov drift theorem, we transform the original long-term throughput maximization problem into an equivalent short-term throughput maximization weighted by virtual queue length. Moreover, to cope with the challenges introduced by the interaction between large-timescale NS and short-timescale resource allocation, we propose an adaptive adversarial slicing (Ad2S) scheme for networks with invarying channel statistics. To track the network channel variations, we also propose a measurement extrapolation-Kalman filter (ME-KF)-based method and refine our scheme into Ad2S-nonstationary refinement (Ad2S-NR). Through extended numerical examples, we demonstrate that our proposed schemes achieve 3.86 Mb/s throughput improvement and 63.96% latency reduction with 24.36% convergence time reduction. Within our framework, the tradeoff between total throughput and user service experience can be achieved by tuning systematic parameters.
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (12) , 19636-19646
A Novel Multimodal Feature-Level Fusion Scheme for High-Accurate Indoor Localization
Smartphone based indoor localization has been widely explored to meet the demand for high-precision, cost-effective solutions within indoor positioning systems. Prior methodologies have predominantly concentrated on enhancing the localization accuracy inherent in single-sensor-based localization, thereby potentially constraining their applications. In this article, we introduce an innovative WiFi-visual multi-modal framework designed for achieving high-precision, low-cost indoor localization. The initial stages involve the utilization of two modal-specific encoders for feature extraction. Then, we propose a multi-modal fusion transformer to incorporate the global context and adopt element-wise summation to fuse the two deep features. Finally, we leverage a task-specific decoder for position prediction. During training, WiFi-aided learning is adopted to confer enhanced reliability to the labeling process. The efficacy of the proposed method is assessed in a corridor scenario and a laboratory scenario of a typical building. During testing, we propose backend optimization to get smooth and globally consistent location predictions. Experimental outcomes affirm that the proposed WiFi-visual multi-modal approach introduced herein attains a localization accuracy of less than half a meter, concurrently exhibiting commendable runtime efficiency.
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (12) , 19636-19646
A Novel Multimodal Feature-Level Fusion Scheme for High-Accurate Indoor Localization
Smartphone based indoor localization has been widely explored to meet the demand for high-precision, cost-effective solutions within indoor positioning systems. Prior methodologies have predominantly concentrated on enhancing the localization accuracy inherent in single-sensor-based localization, thereby potentially constraining their applications. In this article, we introduce an innovative WiFi-visual multi-modal framework designed for achieving high-precision, low-cost indoor localization. The initial stages involve the utilization of two modal-specific encoders for feature extraction. Then, we propose a multi-modal fusion transformer to incorporate the global context and adopt element-wise summation to fuse the two deep features. Finally, we leverage a task-specific decoder for position prediction. During training, WiFi-aided learning is adopted to confer enhanced reliability to the labeling process. The efficacy of the proposed method is assessed in a corridor scenario and a laboratory scenario of a typical building. During testing, we propose backend optimization to get smooth and globally consistent location predictions. Experimental outcomes affirm that the proposed WiFi-visual multi-modal approach introduced herein attains a localization accuracy of less than half a meter, concurrently exhibiting commendable runtime efficiency.
- 12 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (9) , 13788-13796
An Efficient Angular Separation Maximization Antenna Selection Scheme for High-Precision Fingerprint-Based Indoor Positioning: A Review
High-precision indoor positioning based on fingerprint usually requires more observation samples, either time or frequency. Our previous work explores the possibility of enlarging the observation window in the spatial domain, which requires significant baseband and radio frequency (RF) processing capabilities to deal with multiple antennas. In this paper, we propose a low-complexity antenna selection-based positioning scheme in order to trade off the positioning performance and hardware cost or computational complexity. The optimal antenna subset is selected with the help of the theoretical error-bound analysis, which ensures robust and high-precision positioning performance. Based on the numerical results, we show that our proposed antenna selection mechanism is able to reserve the positioning precision improvement provided by the spatial domain observations and reduce more than 100-200 times implementation complexity in terms of running times, if compared with other baseline selection algorithms.
- 12 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (9) , 13788-13796
An Efficient Angular Separation Maximization Antenna Selection Scheme for High-Precision Fingerprint-Based Indoor Positioning: A Review
High-precision indoor positioning based on fingerprint usually requires more observation samples, either time or frequency. Our previous work explores the possibility of enlarging the observation window in the spatial domain, which requires significant baseband and radio frequency (RF) processing capabilities to deal with multiple antennas. In this paper, we propose a low-complexity antenna selection-based positioning scheme in order to trade off the positioning performance and hardware cost or computational complexity. The optimal antenna subset is selected with the help of the theoretical error-bound analysis, which ensures robust and high-precision positioning performance. Based on the numerical results, we show that our proposed antenna selection mechanism is able to reserve the positioning precision improvement provided by the spatial domain observations and reduce more than 100-200 times implementation complexity in terms of running times, if compared with other baseline selection algorithms.