Searcharxiv⌕ Search

arXiv subjects

Junhui Zhao

Publications and source records attributed to Junhui Zhao.

At least 19 recordsLinked to original sources
arXiv2026

GAN-Based Semantic Communication for Image Transmission in IoV

For cooperative perception in the internet of vehicles, this paper proposes a generative adversarial network-based semantic communication framework to address the efficiency and fidelity bottlenecks of traditional communication systems in visual data transmission under limited bandwidth and dynamic channel conditions. At the transmitter, the framework adopts a pyramid attention network to extract semantic label maps and introduces a semantic priority preservation mechanism. It assigns differentiated weights to distinct semantic categories based on driving safety, guiding bit allocation and loss function design. At the receiver, an image reconstruction module integrating a coarse to-fine multi-resolution generator and multi-scale discriminator is designed. Combined with the temporal consistency branch, spatial pyramid pooling and class-aware convolutional layers, it achieves high-fidelity reconstruction of high-quality images from corrupted semantic labels. The model is trained with combined adversarial, feature matching and perceptual losses, effectively improving semantic consistency and visual realism of generated images. Experimental results on the Cityscapes dataset show that the proposed method outperforms existing counterparts in both semantic segmentation accuracy and reconstructed image quality, and maintains stable reconstruction performance under AWGN and Rayleigh channels.

cs.CV↗
arXiv2026

Securing Cooperative Sensing in UAV Swarms Against Conformity-Driven Byzantine Attacks

In integrated sensing and communication (ISAC) enabled 6G unmanned aerial vehicle (UAV) swarm networks, the widely adopted imitation-based conformity cooperation mechanism can be exploited by Byzantine attackers to fabricate false consensus, causing the effective error probability of normal UAVs to evolve dynamically and far exceed their inherent sensing errors, which invalidates conventional fusion methods built on the independence assumption. This paper proposes a conformity-aware Byzantine-resilient fusion framework that couples evolutionary game theory with maximum a posteriori (MAP) estimation. First, the strategy updates of normal UAVs are characterized by bounded-rational opinion dynamics, and the evolution dynamics of the misinformation ratio together with its evolutionarily stable state (ESS) are derived under death birth updating. Three theoretical results are then established: under heterogeneous per-node sensing errors, the zeroth-order ESS depends on the error distribution only through its mean; a closed-form first-order weak-selection correction to the ESS is obtained, together with an exact mean-field fixed point valid for arbitrary selection intensity; and it is revealed that swarm level misinformation can overwhelm the majority if and only if the attack probability exceeds one half, with this threshold independent of both the sensing error and the malicious ratio. Embedding the predicted error dynamics into a per-node MAP rule, the resulting fusion mechanism achieves nearly 100% situation-inference accuracy under different network topologies, attack intensities, network scales, and sensing-error distributions, and maintains accuracy above 99% under +-20% parameter mismatch. In contrast, majority voting, reputation weighting, and independent fusion collapse completely once the majority-flip threshold is crossed.

eess.SY↗
arXiv2026

Reliability-Constrained Hybrid Beamforming for Multistatic ISAC in Vehicular Networks

This letter investigates reliability constrained hybrid beamforming for transceiver separated multistatic integrated sensing and communication in vehicular networks. A target position Cramer Rao bound minimization problem is formulated under outage probability, transmit-power, and analog constant modulus constraints. To handle the constrained non convex problem, we develop a proportional-integral Lagrangian proximal policy optimization algorithm. Simulation results show that the proposed algorithm keeps the average outage probability at or below the reliability threshold, around 8%-10%, improves constraint satisfaction, and achieves stable sensing performance.

eess.SY↗
arXiv2026

The Cross-Domain Generalization Cost of Offensive Language Detection

Offensive language detection models generally suffer performance degradation when deployed across datasets and across languages, yet most existing studies stop at reporting this phenomenon and lack a systematic methodology for decomposing the causes of degradation into attributable components and quantifying the cost of remediation. This paper proposes a diagnosis and optimization framework composed of three coordinated technical components. First, a zero-shot transfer loss decomposition that separates the performance degradation from OLID to MLMA into two independently measurable components, namely dataset effect and language effect. Second, a controlled fine-tuning protocol that quantifies both adaptation efficiency and the hidden damage inflicted on the source task by comparing few shot learning curves under continued fine-tuning and cold-start starting points. Third, three joint training strategies incorpo rating temperature sampling and experience replay, which offer a controllable Pareto trade-off between improving multilingual capability and preserving source-task performance. Experiments built on this framework show that the dataset effect dominates the zero-shot transfer loss and substantially outweighs the language effect. Few-shot adaptation without a replay mechanism, though data-efficient, inflicts source task damage 4 to 9 times greater than that of the joint training strategies, and its damage magnitude is highly unstable. The three joint training strategies trade 3.2 to 4.1 percentage points of source-task performance for 8.1 to 42.6 percentage points of multilingual capability gain, forming a clear and controllable Pareto trade-off.

cs.CL↗
arXiv2026

Cascading versus Joint Modeling for Hierarchical Offensive Language Detection

Fine-grained offensive language detection organizes labels into a hierarchical structure, for which two modeling paradigms exist: cascaded decomposition and joint multi-task modeling. Prior work rarely provides a direct, controlled comparison of the two paradigms in terms of accuracy, parameter count, and inference latency, and rarely verifies whether a chosen class-imbalance handling strategy is actually optimal. This paper proposes a three-level cascaded detection system whose training strategy is customized per subtask, together with two verification mechanisms. First, a controlled ablation study determines the best class-imbalance handling strategy for each subtask. Second, a joint multi-task model with a shared encoder is trained as an architectural control, yielding real measurements along the dimensions of accuracy, parameter count, and inference latency. Experiments show that the cascaded system attains macro-F1 scores of 0.795, 0.716, and 0.557 on the three subtasks of the official test set. The ablation study reveals that configuring the loss function purely by imbalance-severity intuition is suboptimal; reconfiguring based on the ablation results improves both performance and stability. End-to-end cascade evaluation shows that roughly one-fifth of the errors in the cascade pipeline originate from the first-stage filter and cannot be corrected by subsequent stages. Relative to the joint multi-task model, the cascaded architecture achieves higher accuracy on all three subtasks, with a 7.1-point macro-F1 gain on the most severely imbalanced subtask, at the cost of three times the parameters and 1.67 times the inference latency. Together, these results establish an explicit, quantifiable trade-off between the accuracy advantage of cascaded architectures and their deployment cost.

cs.CL↗
arXiv2026

Variational Inference for Bird's Eye View Segmentation in Autonomous Driving

The bird's eye view (BEV) has emerged as a pivotal approach for environmental perception in autonomous driving, providing a unified spatial representation for vehicles. Nevertheless, despite BEV's significance in addressing the challenges inherent to autonomous driving, effectively fusing data from multiple camera sensors and operating in complex external driving environments remains a considerable challenge. To mitigate this issue, we recast the BEV segmentation problem within a variational inference framework. In this paper, we propose a novel transformer-based variational flow transformation network for BEV segmentation, denoted as TVB. Our architecture implicitly learns the mapping from multiple camera views to a unified canonical BEV map during training by exploiting posterior BEV supervision. TVB employs a conditional variational auto encoder (CVAE) as its backbone and produces multiple BEV map candidates. To augment the realism of the generated BEV maps, we integrate normalizing flows into the map generation process, enabling the construction of more complex and expressive probability distributions. Furthermore, we design a BEV-attention fusion (BAF) module that harnesses attention mechanisms to adaptively integrate the multiple candidate BEV maps. Experimental results, evaluated on both the nuScenes and OPV2Vdatasets, demonstrate that our proposed method achieves superior performance in multi-camera view BEV segmentation and lane environment perception.

cs.CV↗
arXiv2026

LEO-NA Walker Constellation Design with Bi-objective Optimisation Approaches

Low Earth Orbit (LEO) constellation design for navigation augmentation (NA) has attracted increasing attention in navigation satellite system studies, yet balancing navigation performance and deployment cost remains a fundamental challenge. To address this issue, this paper proposes a bi-objective optimization framework for LEO Walker constellation design. The problem is formulated as a bi-objective optimization model with constellation cost and positioning accuracy as objectives. In the formulation, PDOP tail risk and satellite visibility are incorporated into the objective formulation to better characterize navigation performance. The Pareto-optimal solution set isobtained using the Non-dominated Sorting Genetic Algorithm II (NSGA-II). Simulation results show that, under the same satellite deployment cost, the proposed LEO-NA Walker constellation improves the average number of visible satellites by 42.5% and 24.4%, and reduces the mean PDOP by 18.9% and 10.5% compared with representative Polar and optimized-LFC constellations, respectively, thereby enhancing service continuity and resource utilization efficiency. These results provide useful guidance for the design and deployment of LEO-NA constellations.

eess.SY↗
arXiv2026

Cross-Platform Chinese Offensive Comment Detection via Dual-Threshold Hard Example Mining

Cross-platform deployment of offensive comment detection for Chinese social media suffers performance degradation. The paper proposes a dual-threshold hard mining method to address this. First, the clean-Chinese-base RoBERTa is finetuned on COLD to establish a binary baseline for fair comparison. Second, a three-class fine-labeled test set covering Weibo, Xiaohongshu, Tieba, and Zhihu is constructed, domain distances from the source are quantified using Jaccard and Proxy-A Distance, as well as the degradation bottleneck of the baseline under domain shift is systematically revealed. Herein, a dual threshold hard example mining strategy is proposed. High- and low-confidence error-prone samples are filtered from unlabeled corpora by prediction confidence. The model is secondarily finetuned under implicit contexts with merely a small set of manually labeled hard examples, realizing low-cost cross-platform domain adaptation. Experiments reveal significant performance gains of the optimized model across four platforms.

cs.CL↗
arXiv2026

Adaptive Joint Beamforming and Fluid Antenna System Design for 6G ISAC

Fixed-Position Antennas (FPAs) are constrained by static physical topologies and struggle to adapt to rapidly varying wireless environments. By dynamically reconfiguring the antenna positions, Fluid Antenna Systems (FASs) introduce additional spatial Degrees of Freedom (DoF) for wireless optimization. This paper investigates the joint optimization of Fluid Antenna System (FAS) topology reconfiguration and active beamforming for mobile Integrated Sensing and Communication (ISAC) systems. To enable real-time decision making, an end-to-end optimization framework based on the Soft Actor-Critic (SAC) algorithm is proposed. Simulation results show that the proposed scheme achieves an online inference latency of only 4 ms. Compared to the widely used alternating optimization, it improves communication performance by 42%. Moreover, it achieves performance comparable to the SCA-SDR benchmark while requiring 57% fewer antennas, demonstrating superior hardware efficiency.

eess.SY↗
arXiv2026

Local Conformity-Based Evolutionary Game Modeling of UAV Swarm Under Byzantine Attack

Leveraging their flexible and efficient deployment capabilities, unmanned aerial vehicle (UAV) swarms have been widely applied in various mission scenarios. However, the open communication environment also exposes them to the threat of Byzantine attacks. Most existing studies assume independent decision-making by each UAV, neglecting that local conformity amplifies false information propagation. This paper constructs an evolutionary game model for UAV swarm under malicious attacks based on graph evolutionary game theory, revealing how local conformity rules govern the spread of deceptive strategies. Using death-birth updating rules, we derive the macroscopic dynamic equation for the fraction of deceptive strategies and the analytical solutions to its evolutionary stable states. Sim ulations reveal observation errors weaken malicious induction, while higher proportions of malicious nodes and greater attack intensity drastically amplify attack impacts. Moreover, the model exhibits strong topological robustness across regular, scale-free and random networks.

eess.SY↗
arXiv2026

Dual-Polarized Massive MIMO Based on Precoding for Vehicle-To-Ground Communication in Urban Rail Transit

The development of intelligent and diversified ser vices in urban rail transit (URT) has resulted in an increasing de mand for high-rate communication between vehicles and ground equipment. However, existing URT communication systems strug gle to handle the massive data exchange required for vehicle-to ground (V2G) communication. To address this issue, we propose a distributed dual-polarized MIMO architecture suitable for URT tunnel scenarios. Specifically, the channel model is based on spatial three-dimensional (3D) non-stationary geometry-based stochastic model (GBSM), which takes into account the geometric distribution of URT tunnels and the cross-polarization effects between dual-polarized antennas. For dual-polarized MIMO systems, the polarized-aware sparse channel estimation (PASCE) method is proposed for effective channel estimation. Additionally, we derive closed-form expressions for the MMSE and MR precoding schemes. The polarized-aware dynamic interference cancellation (PADIC) algorithm is developed to eliminate in terference between different polarization modes and multiple users. The simulation results demonstrate that the proposed dual-polarized precoding algorithm can withstand high cross polarization correlation (XPC) and improve the efficiency of V2G communication to achieve high rates.

eess.SY↗
arXiv2026

Fed-DLoRA: Efficient Wireless Federated Learning with Dynamic Low-Rank Adaptation

Federated learning (FL) offers a promising distributed learning paradigm for internet of vehicles (IoV) applications. However, it faces challenges from communication overhead and dynamic environments. Model compression techniques reduce computing and communication burden yet create trade-offs between compression ratios and vehicle participation strategies. In this paper, we propose a lightweight FL algorithm named federated learning with dynamic low-rank adaptation (Fed-DLoRA), which is combined with low-rank adaptation (LoRA) to effectively reduce parameters and communication costs while enhancing training efficiency. The convergence analysis of Fed-DLoRA is conducted through stochastic gradient descent optimization coupled with singular value decomposition. This analysis establishes the theoretical relationships among LoRA rank, vehicular scheduling strategies and the model's convergence characteristics. Building on these insights, we formulate a joint optimization problem aimed at maximizing system performance. To address this problem, we propose an adaptive rank, bandwidth and vehicle selection (ARBVS) algorithm that integrates enumeration with greedy optimization strategies. The algorithm provides efficient rank selection and resource scheduling strategies for each FL communication round, thereby achieving effective performance improvements for the FL system. Experimental results demonstrate that Fed-DLoRA achieves superior performance compared to conventional federated learning approaches, exhibiting enhanced accuracy, faster convergence, and improved communication efficiency.

cs.LG↗
arXiv2026

Lightweight Low-SNR-Robust Semantic Communication System for Autonomous Driving

Image transmission for vehicle-to-vehicle collaborative perception in autonomous driving faces challenges including limited on-board terminal resources, time-varying wireless channel fading, and poor robustness under low signal-to-noise (SNR) ratio. Traditional separate source-channel coding schemes suffer from the cliff effect, while existing semantic communication models are limited by large parameter sizes and weak digital compatibility. This paper proposes a lightweight, low-SNR-robust deep joint source-channel coding (JSCC) semantic communication system. First, structured pruning is implemented based on batch normalization layer scaling factors and L1 regularization, which significantly reduces model complexity while ensuring image reconstruction quality. Second, a uniform quantization and M-QAM modulation scheme adapted to JSCC features is designed, and a training-deployment separation strategy is adopted to address the non-differentiable quantization problem, enabling compatibility with existing digital communication systems. Simulation results on the Cityscapes dataset show that the pruned model maintains comparable performance and robustness to the original one, even with over half of its parameters removed. Notably, the proposed scheme exhibits significant advantages over conventional communication methods under low SNR conditions.

eess.SY↗
arXiv2026

Adaptive Multi-Dimensional Coordinated Comprehensive Routing Scheme for IoV

The characteristics of high-speed node movement and dynamic topology changes pose great challenges to the design of internet of vehicles (IoV) routing protocols. Existing schemes suffer from common problems such as insufficient adaptability and lack of global consideration, making it difficult to achieve a globally optimal balance between routing reliability, real-time performance and transmission efficiency. This paper proposes an adaptive multi-dimensional coordinated comprehensive routing scheme for IoV environments. A complete IoV system model including network topology, communication links, hierarchical congestion and transmission delay is first constructed, the routing problem is abstracted into a single-objective optimization model with multiple constraints, and a single-hop link comprehensive routing metric integrating link reliability, node local load, network global congestion and link stability is defined. Second, an intelligent transmission switching mechanism is designed: candidate nodes are screened through dual criteria of connectivity and progressiveness, a dual decision-making of primary and backup paths and a threshold switching strategy are introduced to avoid link interruption and congestion, and an adaptive update function is constructed to dynamically adjust weight coefficients and switching thresholds to adapt to changes in network status. Simulation results show that the proposed scheme can effectively adapt to the high dynamic topology and network congestion characteristics of IoV, perform excellently in key indicators such as routing interruption times, packet delivery rate and end-to-end delay, and its comprehensive performance is significantly superior to traditional routing schemes.

cs.NI↗
arXiv2026

Dual-Channel Feature Fusion for Joint Prediction in Dynamic Signed Weighted Networks

Link prediction is central to unraveling social network evolution and node relationships, as well as understanding the characteristic mechanisms of complex networks. Currently, research on link prediction for complex dynamic networks integrating temporal evolution, relational polarity and edge weight information remains significantly underexplored, failing to meet practical demands. For dynamic signed-weighted networks, this paper proposes a tripartite joint prediction framework for unified forecasting of links, signs and weights. First, the dynamic network is decomposed into temporal snapshots, and node semantic embeddings are generated via sign-aware weighted random walks. We then design multi-hop structural balance and temporal difference features to capture the structural characteristics and dynamic evolution laws of the network, respectively. The model adopts a dual-channel feature decoupling mechanism: node semantic embeddings are used for link existence prediction, while relational sign features are fed into a Transformer encoder to model temporal dependencies. Finally, prediction results are output synergistically through a multi-task unit. Simulation experiments demonstrate that, compared with baseline methods, the proposed framework achieves an average 2%-4% improvement in the performance of link existence and relational sign prediction, and a significant 40%-50% reduction in edge weight prediction error.

eess.SY↗
arXiv2026

Towards Governance of Localized VANET: An Adjustable Degree Distribution Model

Vehicular Ad-hoc Networks (VANETs) serve as a critical enabler for intelligent transportation systems. However, their practical deployment faces a core governance dilemma: the network topology requires a dynamic trade-off between robustness against targeted attacks and ensuring low-latency information transmission. Most existing models generate fixed degree distributions, lacking the ability to adapt autonomously to the demands of diverse traffic scenarios. To address this challenge, this paper innovatively proposes a schedulable degree distribution model for localized VANETs. The core of this model lies in introducing a hybrid connection mechanism. When establishing connections, newly joining nodes do not follow a single rule but instead collaboratively perform random attachment and preferential attachment. Through theoretical derivation and simulation validation, this study demonstrates that by adjusting the cooperative weighting between these two mechanisms, the overall network degree distribution can achieve a continuous and controllable transition between a uniform distribution and a power-law distribution. The former effectively disperses attack risks and enhances robustness, while the latter facilitates the formation of hub nodes, shortening transmission paths to reduce latency. Experimental results based on the real-world road network of Beijing indicate that this model can precisely regulate node connection heterogeneity, attack resistance, and average transmission path length through the reshaping of the underlying topology. This provides a forward-looking and practical governance paradigm for constructing next-generation VANETs capable of dynamically adapting to complex environments.

eess.SY↗
arXiv2026

Hierarchical Optimization Based Multi-objective Dynamic Regulation Scheme for VANET Topology

As a core technology of intelligent transportation systems, vehicular ad-hoc networks support latency-sensitive services such as safety warning and cooperative perception via vehicle-to-everything communications. However, their highly dynamic topology increases average path length, raises latency, and reduces throughput, severely limiting communication performance. Existing topology optimization methods lack capabilities in multi-objective coordination, dynamic adaptation, and global-local synergy. To address this, this paper proposes a two-layer dynamic topology regulation scheme combining local feature aggregation and global adjustment. The scheme constructs a dynamic multi-objective optimization model integrating average path length, end-to-end latency, and network throughput, and achieves multi-index coordination via link adaptability metrics and a dynamic normalization mechanism. it quickly responds to local link changes via feature fusion of local node feature extraction and dynamic neighborhood sensing, and balances optimization accuracy and real-time performance using a dual-mode adaptive solving strategy for global topology adjustment. It reduces network oscillation risks by introducing a performance improvement threshold and a topology validity verification mechanism. Simulation results on real urban road networks via the SUMO platform show that the proposed scheme outperforms traditional methods in average path length (stabilizing at ~4 hops), end-to-end latency (remaining ~0.01 s), and network throughput.

eess.SY↗
arXiv2026

NLP-Based Review for Toxic Comment Detection Tailored to the Chinese Cyberspace

With the in-depth integration of mobile Internet and widespread adoption of social platforms, user-generated content in the Chinese cyberspace has witnessed explosive growth. Among this content, the proliferation of toxic comments poses severe challenges to individual mental health, community atmosphere and social trust. Owing to the strong context dependence, cultural specificity and rapid evolution of Chinese cyber language, toxic expressions are often conveyed through complex forms such as homophones and metaphors, imposing notable limitations on traditional detection methods. To address this issue, this review focuses on the core topic of natural language processing based toxic comment detection in the Chinese cyberspace, systematically collating and critically analyzing the research progress and key challenges in this field. This review first defines the connotation and characteristics of Chinese toxic comments, and analyzes the platform ecology and transmission mechanisms they rely on. It then comprehensively reviews the construction methods and limitations of existing public datasets, and proposes a novel fine-grained and scalable framework for toxic comment definition and classification, along with corresponding data annotation and quality assessment strategies. We systematically summarize the evolutionary path of detection models from traditional methods to deep learning, with special emphasis on the importance of interpretability in model design. Finally, we thoroughly discuss the open challenges faced by current research and provide forward-looking suggestions for future research directions.

eess.AS↗