arXiv subjects

Jiayi Zhang

Publications and source records attributed to Jiayi Zhang.

At least 109 records · Page 6Linked to original sources

arXiv2025

6G-Enabled Smart Railways

Smart railways integrate advanced information technologies into railway operating systems to improve efficiency and reliability. Although the development of 5G has enhanced railway services, future smart railways require ultra-high speeds, ultra-low latency, ultra-high security, full coverage, and ultra-high positioning accuracy, which 5G cannot fully meet. Therefore, 6G is envisioned to provide green and efficient all-day operations, strong information security, fully automatic driving, and low-cost intelligent maintenance. To achieve these requirements, we propose an integrated network architecture leveraging communications, computing, edge intelligence, and caching in railway systems. We have conducted in-depth investigations on key enabling technologies for reliable transmissions and wireless coverage. For high-speed mobile scenarios, we propose an AI-enabled cross-domain channel modeling and orthogonal time-frequency space-time spread multiple access mechanism to alleviate the conflict between limited spectrum availability and massive user access. The roles of blockchain, edge intelligence, and privacy technologies in endogenously secure rail communications are also evaluated. We further explore the application of emerging paradigms such as integrated sensing and communications, AI-assisted Internet of Things, semantic communications, and digital twin networks for railway maintenance, monitoring, prediction, and accident warning. Finally, possible future research and development directions are discussed.

eess.SY↗

arXiv2025

TrafficKAN-GCN: Graph Convolutional-based Kolmogorov-Arnold Network for Traffic Flow Optimization

Urban traffic optimization is critical for improving transportation efficiency and alleviating congestion, particularly in large-scale dynamic networks. Traditional methods, such as Dijkstra's and Floyd's algorithms, provide effective solutions in static settings, but they struggle with the spatial-temporal complexity of real-world traffic flows. In this work, we propose TrafficKAN-GCN, a hybrid deep learning framework combining Kolmogorov-Arnold Networks (KAN) with Graph Convolutional Networks (GCN), designed to enhance urban traffic flow optimization. By integrating KAN's adaptive nonlinear function approximation with GCN's spatial graph learning capabilities, TrafficKAN-GCN captures both complex traffic patterns and topological dependencies. We evaluate the proposed framework using real-world traffic data from the Baltimore Metropolitan area. Compared with baseline models such as MLP-GCN, standard GCN, and Transformer-based approaches, TrafficKAN-GCN achieves competitive prediction accuracy while demonstrating improved robustness in handling noisy and irregular traffic data. Our experiments further highlight the framework's ability to redistribute traffic flow, mitigate congestion, and adapt to disruptive events, such as the Francis Scott Key Bridge collapse. This study contributes to the growing body of work on hybrid graph learning for intelligent transportation systems, highlighting the potential of combining KAN and GCN for real-time traffic optimization. Future work will focus on reducing computational overhead and integrating Transformer-based temporal modeling for enhanced long-term traffic prediction. The proposed TrafficKAN-GCN framework offers a promising direction for data-driven urban mobility management, balancing predictive accuracy, robustness, and computational efficiency.

cs.LG↗

arXiv2025

ROMA: ROtary and Movable Antenna

The rotary and movable antenna (ROMA) architecture represents a next-generation multi-antenna technology that enables flexible adjustment of antenna position and array rotation angles of the transceiver. In this letter, we propose a ROMA-aided multi-user MIMO communication system to fully enhance the efficiency and reliability of system transmissions. By deploying ROMA panels at both the transmitter and receiver sides, and jointly optimizing the three-dimensional (3D) rotation angles of each ROMA panel and the relative positions of antenna elements based on the spatial distribution of users and channel state information (CSI), we can achieve the objective of maximizing the average spectral efficiency (SE). Subsequently, we conduct a detailed analysis of the average SE performance of the system under the consideration of maximum ratio (MR) precoding. Due to the non-convexity of the optimization problem in the ROMA multi-user MIMO system, we propose an efficient solution based on an alternating optimization (AO) algorithm. Finally, simulation results demonstrate that the AO-based ROMA architecture can significantly improve the average SE. Furthermore, the performance improvement becomes more pronounced as the size of the movable region and the transmission power increase.

eess.SP↗

arXiv2025

Energy-Efficient SIM-assisted Communications: How Many Layers Do We Need?

The stacked intelligent metasurface (SIM), comprising multiple layers of reconfigurable transmissive metasurfaces, is becoming an increasingly viable solution for future wireless communication systems. In this paper, we explore the integration of SIM in a multi-antenna base station for application to downlink multi-user communications, and a realistic power consumption model for SIM-assisted systems is presented. Specifically, we focus on maximizing the energy efficiency (EE) for hybrid precoding design, i.e., the base station digital precoding and SIM wave-based beamforming. Due to the non-convexity and high complexity of the formulated problem, we employ the quadratic transformation method to reformulate the optimization problem and propose an alternating optimization (AO)-based joint precoding framework. Specifically, a successive convex approximation (SCA) algorithm is adopted for the base station precoding design. For the SIM wave-based beamforming, two algorithms are employed: the high-performance semidefinite programming (SDP) method and the low-complexity projected gradient ascent (PGA) algorithm. In particular, the results indicate that while the optimal number of SIM layers for maximizing the EE and spectral efficiency differs, a design of 2 to 5 layers can achieve satisfactory performance for both. Finally, numerical results are illustrated to evaluate the effectiveness of the proposed hybrid precoding framework and to showcase the performance enhancement achieved by the algorithm in comparison to benchmark schemes.

cs.IT↗

arXiv2025

Segregation and Context Aggregation Network for Real-time Cloud Segmentation

Cloud segmentation from intensity images is a pivotal task in atmospheric science and computer vision, aiding weather forecasting and climate analysis. Ground-based sky/cloud segmentation extracts clouds from images for further feature analysis. Existing methods struggle to balance segmentation accuracy and computational efficiency, limiting real-world deployment on edge devices, so we introduce SCANet, a novel lightweight cloud segmentation model featuring Segregation and Context Aggregation Module (SCAM), which refines rough segmentation maps into weighted sky and cloud features processed separately. SCANet achieves state-of-the-art performance while drastically reducing computational complexity. SCANet-large (4.29M) achieves comparable accuracy to state-of-the-art methods with 70.9% fewer parameters. Meanwhile, SCANet-lite (90K) delivers 1390 fps in FP16, surpassing real-time standards. Additionally, we propose an efficient pre-training strategy that enhances performance even without ImageNet pre-training.

cs.CV↗

arXiv2025

AFlow: Automating Agentic Workflow Generation

Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing these workflows requires significant human effort, limiting scalability and generalizability. Recent research has sought to automate the generation and optimization of these workflows, but existing methods still rely on initial manual setup and fall short of achieving fully automated and effective workflow generation. To address this challenge, we reformulate workflow optimization as a search problem over code-represented workflows, where LLM-invoking nodes are connected by edges. We introduce AFlow, an automated framework that efficiently explores this space using Monte Carlo Tree Search, iteratively refining workflows through code modification, tree-structured experience, and execution feedback. Empirical evaluations across six benchmark datasets demonstrate AFlow's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines. Furthermore, AFlow enables smaller models to outperform GPT-4o on specific tasks at 4.55% of its inference cost in dollars. The code is available at https://github.com/FoundationAgents/AFlow.

cs.AI↗

arXiv2025

White-Box AI Model: Next Frontier of Wireless Communications

White-box AI (WAI), or explainable AI (XAI) model, a novel tool to achieve the reasoning behind decisions and predictions made by the AI algorithms, makes it more understandable and transparent. It offers a new approach to address key challenges of interpretability and mathematical validation in traditional black-box models. In this paper, WAI-aided wireless communication systems are proposed and investigated thoroughly to utilize the promising capabilities. First, we introduce the fundamental principles of WAI. Then, a detailed comparison between WAI and traditional black-box model is conducted in terms of optimization objectives and architecture design, with a focus on deep neural networks (DNNs) and transformer networks. Furthermore, in contrast to the traditional black-box methods, WAI leverages theory-driven causal modeling and verifiable optimization paths, thereby demonstrating potential advantages in areas such as signal processing and resource allocation. Finally, we outline future research directions for the integration of WAI in wireless communication systems.

cs.IT↗

arXiv2025

APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers

Vision Transformers (ViTs) have become one of the most commonly used backbones for vision tasks. Despite their remarkable performance, they often suffer significant accuracy drops when quantized for practical deployment, particularly by post-training quantization (PTQ) under ultra-low bits. Recently, reconstruction-based PTQ methods have shown promising performance in quantizing Convolutional Neural Networks (CNNs). However, they fail when applied to ViTs, primarily due to the inaccurate estimation of output importance and the substantial accuracy degradation in quantizing post-GELU activations. To address these issues, we propose \textbf{APHQ-ViT}, a novel PTQ approach based on importance estimation with Average Perturbation Hessian (APH). Specifically, we first thoroughly analyze the current approximation approaches with Hessian loss, and propose an improved average perturbation Hessian loss. To deal with the quantization of the post-GELU activations, we design an MLP Reconstruction (MR) method by replacing the GELU function in MLP with ReLU and reconstructing it by the APH loss on a small unlabeled calibration set. Extensive experiments demonstrate that APHQ-ViT using linear quantizers outperforms existing PTQ methods by substantial margins in 3-bit and 4-bit across different vision tasks. The source code is available at https://github.com/GoatWu/APHQ-ViT.

cs.CV↗

arXiv2025

Movable Cell-Free Massive MIMO For High-Speed Train Communications: A PPO-Based Antenna Position Optimization

In recent years, high-speed trains (HSTs) communications have developed rapidly to enhance the stability of train operations and improve passenger connectivity experiences. However, as the train continues to accelerate, urgent technological innovations are needed to overcome challenges such as frequency handover and significant Doppler effects. In this paper, we present a novel architecture featuring movable antennas (MAs) to fully exploit macro spatial diversity, enabling a cell-free (CF) massive multiple-input multiple-output (MIMO) system that supports high-speed train communications. Considering the high likelihood of line-of-sight (LoS) transmission in HST scenario, we derive the uplink spectral efficiency (SE) expression for the movable CF massive MIMO system. Moreover, an optimization problem is formulated to maximize the sum SE of the considered system by optimizing the positions of the antennas. Since the formulated problem is non-convex and highly non-linear, we improve a deep reinforcement learning algorithm to address it by using proximal policy optimization (PPO). Different from traditional optimization approaches, which optimize variables separately and alternately, our improved PPO-based approach optimizes all the variables in unison. Simulation results demonstrate that movable CF massive MIMO effectively suppresses the negative impact of the Doppler effect in HST communications.

eess.SP↗

arXiv2025

Optimal Bilinear Equalizer for Cell-Free Massive MIMO Systems over Correlated Rician Channels

In this paper, we explore the low-complexity optimal bilinear equalizer (OBE) combining scheme design for cell-free massive multiple-input multiple-output networks with spatially correlated Rician fading channels. We provide a spectral efficiency (SE) performance analysis framework for both the centralized and distributed processing schemes with bilinear equalizer (BE)-structure combining schemes applied. The BE-structured combining is a set of schemes that are constructed by the multiplications of channel statistics-based BE matrices and instantaneous channel estimates. Notably, we derive closed-form achievable SE expressions for centralized and distributed BE-structured combining schemes. We propose one centralized and two distributed OBE schemes: Centralized OBE (C-OBE), Distributed OBE based on Global channel statistics (DG-OBE), and Distributed OBE based on Local channel statistics (DL-OBE), which maximize their respective SE expressions. OBE matrices in these schemes are tailored based on varying levels of channel statistics. Notably, we obtain new and insightful closed-form results for the C-OBE, DG-OBE, and DL-OBE combining schemes. Numerical results demonstrate that the proposed OBE schemes can achieve excellent SE, even in scenarios with severe pilot contamination.

eess.SP↗

arXiv2025

Optimal Bilinear Equalizer Beamforming Design for Cell-Free Massive MIMO Networks with Arbitrary Channel Estimators

This paper studies the distributed optimal bilinear equalizer (OBE) beamforming design for both the uplink and downlink cell-free massive multiple-input multiple-output networks. We consider arbitrary statistics-based channel estimators over spatially correlated Rician fading channels. In the uplink, we derive the achievable spectral efficiency (SE) performance and OBE combining schemes with arbitrary statistics-based channel estimators and compute their respective closed-form expressions. It is insightful to explore that the achievable SE performance is not dependent on the choice of channel estimator when OBE combining schemes are applied over Rayleigh channels. In the downlink, we derive the achievable SE performance expressions with BE precoding schemes and arbitrary statistics-based channel estimators utilized and compute them in closed form. Then, we obtain the OBE precoding scheme leveraging insights from uplink OBE combining schemes.

cs.IT↗

arXiv2025

Analytical Framework for Effective Degrees of Freedom in Near-Field XL-MIMO

Extremely large-scale multiple-input-multiple-output (XL-MIMO) is an emerging transceiver technology for enabling next-generation communication systems, due to its potential for substantial enhancement in both the spectral efficiency and spatial resolution. However, the achievable performance limits of various promising XL-MIMO configurations have yet to be fully evaluated, compared, and discussed. In this paper, we develop an effective degrees of freedom (EDoF) performance analysis framework specifically tailored for near-field XL-MIMO systems. We explore five representative distinct XL-MIMO hardware designs, including uniform planar array (UPA)-based with infinitely thin dipoles, two-dimensional (2D) continuous aperture (CAP) plane-based, UPA-based with patch antennas, uniform linear array (ULA)-based, and one-dimensional (1D) CAP line segment-based XL-MIMO systems. Our analysis encompasses two near-field channel models: the scalar and dyadic Green's function-based channel models. More importantly, when applying the scalar Green's function-based channel, we derive EDoF expressions in the closed-form, characterizing the impacts of the physical size of the transceiver, the transmitting distance, and the carrier frequency. In our numerical results, we evaluate and compare the EDoF performance across all examined XL-MIMO designs, confirming the accuracy of our proposed closed-form expressions. Furthermore, we observe that with an increasing number of antennas, the EDoF performance for both UPA-based and ULA-based systems approaches that of 2D CAP plane and 1D CAP line segment-based systems, respectively. Moreover, we unveil that the EDoF performance for near-field XL-MIMO systems is predominantly determined by the array aperture size rather than the sheer number of antennas.

cs.IT↗

arXiv2025

Joint Power Allocation and Phase Shift Design for Stacked Intelligent Metasurfaces-aided Cell-Free Massive MIMO Systems with MARL

Cell-free (CF) massive multiple-input multiple-output (mMIMO) systems offer high spectral efficiency (SE) through multiple distributed access points (APs). However, the large number of antennas increases power consumption. We propose incorporating stacked intelligent metasurfaces (SIM) into CF mMIMO systems as a cost-effective, energy-efficient solution. This paper focuses on optimizing the joint power allocation of APs and the phase shift of SIMs to maximize the sum SE. To address this complex problem, we introduce a fully distributed multi-agent reinforcement learning (MARL) algorithm. Our novel algorithm, the noisy value method with a recurrent policy in multi-agent policy optimization (NVR-MAPPO), enhances performance by encouraging diverse exploration under centralized training and decentralized execution. Simulations demonstrate that NVR-MAPPO significantly improves sum SE and robustness across various scenarios.

cs.IT↗

arXiv2025

Robust Multidimensional Graph Neural Networks for Signal Processing in Wireless Communications with Edge-Graph Information Bottleneck

Signal processing is crucial for satisfying the high data rate requirements of future sixth-generation (6G) wireless networks. However, the rapid growth of wireless networks has brought about massive data traffic, which hinders the application of traditional optimization theory-based algorithms. Meanwhile, traditional graph neural networks (GNNs) focus on compressing inputs onto vertices to update representations, which often leads to their inability to effectively distinguish input features and severely weakens performance. In this context, designing efficient signal processing frameworks becomes imperative. Moreover, actual scenarios are susceptible to multipath interference and noise, resulting in specific differences between the received and actual information. To address these challenges, this paper incorporates multidimensional graph neural networks (MDGNNs) with edge-graph information bottleneck (EGIB) to design a robust framework for signal processing. Specifically, MDGNNs utilize hyper-edges instead of vertices to update representations to avoid indistinguishable features and reduce information loss, while EGIB encourages providing minimal sufficient information about outputs to avoid aggregation of irrelevant information. We numerically demonstrate that compared with existing frameworks, the proposed frameworks achieve excellent performance in terms of spectrum efficiency (SE) and network overhead under multiple signal processing tasks. Remarkably, as the interference noise increases, the SE performance of the proposed frameworks gradually stabilizes. This reveals the proposed frameworks have excellent robustness in interference prone environments, especially in wireless policies related to channel matrices.

eess.SP↗

arXiv2025

Multi-Agent Reinforcement Learning in Wireless Distributed Networks for 6G

The introduction of intelligent interconnectivity between the physical and human worlds has attracted great attention for future sixth-generation (6G) networks, emphasizing massive capacity, ultra-low latency, and unparalleled reliability. Wireless distributed networks and multi-agent reinforcement learning (MARL), both of which have evolved from centralized paradigms, are two promising solutions for the great attention. Given their distinct capabilities, such as decentralization and collaborative mechanisms, integrating these two paradigms holds great promise for unleashing the full power of 6G, attracting significant research and development attention. This paper provides a comprehensive study on MARL-assisted wireless distributed networks for 6G. In particular, we introduce the basic mathematical background and evolution of wireless distributed networks and MARL, as well as demonstrate their interrelationships. Subsequently, we analyze different structures of wireless distributed networks from the perspectives of homogeneous and heterogeneous. Furthermore, we introduce the basic concepts of MARL and discuss two typical categories, including model-based and model-free. We then present critical challenges faced by MARL-assisted wireless distributed networks, providing important guidance and insights for actual implementation. We also explore an interplay between MARL-assisted wireless distributed networks and emerging techniques, such as information bottleneck and mirror learning, delivering in-depth analyses and application scenarios. Finally, we outline several compelling research directions for future MARL-assisted wireless distributed networks.

cs.IT↗

arXiv2025

Carelessness Detection using Performance Factor Analysis: A New Operationalization with Unexpectedly Different Relationship to Learning

Detection of carelessness in digital learning platforms has relied on the contextual slip model, which leverages conditional probability and Bayesian Knowledge Tracing (BKT) to identify careless errors, where students make mistakes despite having the knowledge. However, this model cannot effectively assess carelessness in questions tagged with multiple skills due to the use of conditional probability. This limitation narrows the scope within which the model can be applied. Thus, we propose a novel model, the Beyond Knowledge Feature Carelessness (BKFC) model. The model detects careless errors using performance factor analysis (PFA) and behavioral features distilled from log data, controlling for knowledge when detecting carelessness. We applied the BKFC to detect carelessness in data from middle school students playing a learning game on decimal numbers and operations. We conducted analyses comparing the careless errors detected using contextual slip to the BKFC model. Unexpectedly, careless errors identified by these two approaches did not align. We found students' post-test performance was (corresponding to past results) positively associated with the carelessness detected using the contextual slip model, while negatively associated with the carelessness detected using the BKFC model. These results highlight the complexity of carelessness and underline a broader challenge in operationalizing carelessness and careless errors.

cs.CY↗

arXiv2025

Examining the Robustness of Large Language Models across Language Complexity

With the advancement of large language models (LLMs), an increasing number of student models have leveraged LLMs to analyze textual artifacts generated by students to understand and evaluate their learning. These student models typically employ pre-trained LLMs to vectorize text inputs into embeddings and then use the embeddings to train models to detect the presence or absence of a construct of interest. However, how reliable and robust are these models at processing language with different levels of complexity? In the context of learning where students may have different language backgrounds with various levels of writing skills, it is critical to examine the robustness of such models to ensure that these models work equally well for text with varying levels of language complexity. Coincidentally, a few (but limited) research studies show that the use of language can indeed impact the performance of LLMs. As such, in the current study, we examined the robustness of several LLM-based student models that detect student self-regulated learning (SRL) in math problem-solving. Specifically, we compared how the performance of these models vary using texts with high and low lexical, syntactic, and semantic complexity measured by three linguistic measures.

cs.CL↗

arXiv2025

RAINER: A Robust Ensemble Learning Grid Search-Tuned Framework for Rainfall Patterns Prediction

Rainfall prediction remains a persistent challenge due to the highly nonlinear and complex nature of meteorological data. Existing approaches lack systematic utilization of grid search for optimal hyperparameter tuning, relying instead on heuristic or manual selection, frequently resulting in sub-optimal results. Additionally, these methods rarely incorporate newly constructed meteorological features such as differences between temperature and humidity to capture critical weather dynamics. Furthermore, there is a lack of systematic evaluation of ensemble learning techniques and limited exploration of diverse advanced models introduced in the past one or two years. To address these limitations, we propose a robust ensemble learning grid search-tuned framework (RAINER) for rainfall prediction. RAINER incorporates a comprehensive feature engineering pipeline, including outlier removal, imputation of missing values, feature reconstruction, and dimensionality reduction via Principal Component Analysis (PCA). The framework integrates novel meteorological features to capture dynamic weather patterns and systematically evaluates non-learning mathematical-based methods and a variety of machine learning models, from weak classifiers to advanced neural networks such as Kolmogorov-Arnold Networks (KAN). By leveraging grid search for hyperparameter tuning and ensemble voting techniques, RAINER achieves promising results within real-world datasets.

cs.LG↗