arXiv subjects

Qimei Cui

Publications and source records attributed to Qimei Cui.

At least 19 recordsLinked to original sources

arXiv2026

Towards CSI-Native Foundation Models: A Channel-Adaptive Roadmap for 6G

Wireless foundation models offer a path toward reusable channel state information (CSI) intelligence for sixth-generation (6G) systems. However, existing generic-backbone adaptation and CSI pretraining methods often treat CSI as task tensors rather than propagation-conditioned channel responses, thereby failing to capture the intrinsic time-frequency-spatial geometry of wireless environments. This paper presents a channel-adaptive roadmap toward CSI-native foundation models, proposing a unified framework that aligns pretraining, positional modeling, and attention control with three channel requirements: scale-aware heterogeneous exposure, physical time-frequency-antenna coordinates, and correlation-bounded token interaction. Extensive experiments demonstrate the superiority of the proposed framework across three dimensions: zero-shot generalization, reducing NMSE by more than 4 dB across spatial-temporal-frequency tasks; scale extrapolation, yielding up to a 5.4 dB gain under 8 times unseen antenna scaling; and inference efficiency, accelerating mobility-aware processing by up to 18.8%. A system-level evaluation with Sionna SYS further shows that the proposed framework uses only 7.01% of dense-pilot overhead, reaches -18.64 dB average NMSE, and improves average net spectral efficiency by 36.6% over dense LMMSE and 15.5% over WiFo, indicating that CSI-native representation learning can support pilot-efficient radio access.

cs.LG↗

arXiv2026

Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Models

Positional encoding plays a pivotal role in determin?ing the extrapolation and generalization performance of wireless foundation models for channel state information (CSI) modeling, latent characterization, and task-specific prediction. However, existing CSI models inherit static or one-dimensional positional priors from natural language and vision architectures, which fundamentally misalign with the intrinsic physics of wireless channels by lacking explicit relative decay, collapsing the 3D spatio-temporal-frequency structure, and remaining scenario?rigid. This paper proposes Adaptive 3D-RoPE, a physics-aligned rotary positional encoding that establishes the structural corner?stone for wireless foundation models. The framework integrates a learnable, axis-decoupled 3D frequency bank to explicitly disentangle multi-dimensional phase dependencies, coupled with a lightweight channel-conditioned controller that dynamically modulates the prior via compact global CSI descriptors. This sample-adaptive mechanism transforms positional encoding from a static transformer component into a dynamic, coherence-aware inductive bias to resolve heterogeneous channel physics. Extensive experiments across 100 datasets demonstrate the superiority of the proposed scheme in both scale extrapolation and zero-shot generalization. Compared to the state-of-the-art, our method achieves up to a 10.7 dB reduction in normalized mean square error (NMSE) under 8 times antenna scale extrapolation. Given the same CSI input scales, our method can also improve zero-shot NMSE by 1.07 dB across unseen mobility scenarios and 0.90 dB in low-frequency-to-millimeter-wave tasks.

eess.SP↗

arXiv2026

Wireless communication empowers online scheduling of partially-observable transportation multi-robot systems in a smart factory

Achieving agile and reconfigurable production flows in smart factories depends on online multi-robot task assignment (MRTA), which requires online collision-free and congestion-free route scheduling of transportation multi-robot systems (T-MRS), e.g., collaborative automatic guided vehicles (AGVs). Due to the real-time operational requirements and dynamic interactions between T-MRS and production MRS, online scheduling under partial observability in dynamic factory environments remains a significant and under-explored challenge. This paper proposes a novel communication-enabled online scheduling framework that explicitly couples wireless machine-to-machine (M2M) networking with route scheduling, enabling AGVs to exchange intention information, e.g., planned routes, to overcome partial observations and assist complex computation of online scheduling. Specifically, we determine intelligent AGVs' intention and sensor data as new M2M traffic and tailor the retransmission-free multi-link transmission networking to meet real-time operation demands. This scheduling-oriented networking is then integrated with a simulated annealing-based MRTA scheme and a congestion-aware A*-based route scheduling method. The integrated communication and scheduling scheme allows AGVs to dynamically adjust collision-free and congestion-free routes with reduced computational overhead. Numerical experiments shows the impacts from wireless communication on the performance of T-MRS and suggest that the proposed integrated scheme significantly enhances scheduling efficiency compared to other baselines, even under high AGV load conditions and limited channel resources. Moreover, the results reveal that the scheduling-oriented wireless M2M communication design fundamentally differs from human-to-human communications, implying new technological opportunities in a wireless networked smart factory.

cs.LG↗

arXiv2026

Coverage Performance Analysis of FAS-enhanced LoRa Wide Area Networks under both Co-SF and Inter-SF Interference

This paper presents an analytical framework for evaluating the coverage performance of the fluid antenna system (FAS)-enhanced LoRa wide-area networks (LoRaWANs). We investigate the effects of large-scale pathloss in LoRaWAN, small-scale fading characterized by FAS, and dense interference (i.e., packet collisions under the ALOHA protocol) arising from randomly deployed end devices (EDs). Both co-spreading factor (co-SF) interference (with the same SF) and inter-SF interference (with different SFs) are introduced into the network, and their differences in physical characteristics are also considered in the analysis. Additionally, simple yet accurate statistical approximations of the FAS channel envelope and power are derived using the extreme-value theorem. Based on the approximated channel expression, the theoretical coverage probability of the proposed FAS-enhanced LoRaWAN is derived. Numerical results validate our analytical approximations by exhibiting close agreement with the exact correlation model. Notably, it is revealed that a FAS with a normalized aperture of 1 times 1 can greatly enhance network performance, in terms of both ED numbers and coverage range.

eess.SP↗

arXiv2026

HeterCSI: Channel-Adaptive Heterogeneous CSI Pretraining Framework for Generalized Wireless Foundation Models

Wireless foundation models promise transformative capabilities for channel state information (CSI) processing across diverse 6G network applications, yet face fundamental challenges due to the inherent dual heterogeneity of CSI across both scale and scenario dimensions. However, current pretraining approaches either constrain inputs to fixed dimensions or isolate training by scale, limiting the generalization and scalability of wireless foundation models. In this paper, we propose HeterCSI, a channel-adaptive pretraining framework that reconciles training efficiency with robust cross-scenario generalization via a new understanding of gradient dynamics in heterogeneous CSI pretraining. Our key insight reveals that CSI scale heterogeneity primarily causes destructive gradient interference, while scenario diversity actually promotes constructive gradient alignment when properly managed. Specifically, we formulate heterogeneous CSI batch construction as a partitioning optimization problem that minimizes zero-padding overhead while preserving scenario diversity. To solve this, we develop a scale-aware adaptive batching strategy that aligns CSI samples of similar scales, and design a double-masking mechanism to isolate valid signals from padding artifacts. Extensive experiments on 12 datasets demonstrate that HeterCSI establishes a generalized foundation model without scenario-specific finetuning, achieving superior average performance over full-shot baselines. Compared to the state-of-the-art zero-shot benchmark WiFo, it reduces NMSE by 7.19 dB, 4.08 dB, and 5.27 dB for CSI reconstruction, time-domain, and frequency-domain prediction, respectively. The proposed HeterCSI framework also reduces training latency by 53% compared to existing approaches while improving generalization performance by 1.53 dB on average.

cs.LG↗

arXiv2025

Advancing LLM-Based Security Automation with Customized Group Relative Policy Optimization for Zero-Touch Networks

Zero-Touch Networks (ZTNs) represent a transformative paradigm toward fully automated and intelligent network management, providing the scalability and adaptability required for the complexity of sixth-generation (6G) networks. However, the distributed architecture, high openness, and deep heterogeneity of 6G networks expand the attack surface and pose unprecedented security challenges. To address this, security automation aims to enable intelligent security management across dynamic and complex environments, serving as a key capability for securing 6G ZTNs. Despite its promise, implementing security automation in 6G ZTNs presents two primary challenges: 1) automating the lifecycle from security strategy generation to validation and update under real-world, parallel, and adversarial conditions, and 2) adapting security strategies to evolving threats and dynamic environments. This motivates us to propose SecLoop and SA-GRPO. SecLoop constitutes the first fully automated framework that integrates large language models (LLMs) across the entire lifecycle of security strategy generation, orchestration, response, and feedback, enabling intelligent and adaptive defenses in dynamic network environments, thus tackling the first challenge. Furthermore, we propose SA-GRPO, a novel security-aware group relative policy optimization algorithm that iteratively refines security strategies by contrasting group feedback collected from parallel SecLoop executions, thereby addressing the second challenge. Extensive real-world experiments on five benchmarks, including 11 MITRE ATT&CK processes and over 20 types of attacks, demonstrate the superiority of the proposed SecLoop and SA-GRPO. We will release our platform to the community, facilitating the advancement of security automation towards next generation communications.

cs.CR↗

arXiv2025

Reflection-Driven Self-Optimization 6G Agentic AI RAN via Simulation-in-the-Loop Workflows

The escalating complexity of sixth-generation (6G) networks demands unprecedented levels of autonomy beyond the capabilities of traditional optimization-based and current AI-based resource management approaches. While agentic AI has emerged as a promising paradigm for autonomous RAN, current frameworks provide sophisticated reasoning capabilities but lack mechanisms for empirical validation and self-improvement. This article identifies simulation-in-the-loop validation as a critical enabler for truly autonomous networks, where AI agents can empirically verify decisions and learn from outcomes. We present the first reflection-driven self-optimization framework that integrates agentic AI with high-fidelity network simulation in a closed-loop architecture. Our system orchestrates four specialized agents, including scenario, solver, simulation, and reflector agents, working in concert to transform agentic AI into a self-correcting system capable of escaping local optima, recognizing implicit user intent, and adapting to dynamic network conditions. Extensive experiments validate significant performance improvements over non-agentic approaches: 17.1\% higher throughput in interference optimization, 67\% improved user QoS satisfaction through intent recognition, and 25\% reduced resource utilization during low-traffic periods while maintaining service quality.

cs.NI↗

arXiv2025

Sensing and Understanding the World over Air: A Large Multimodal Model for Mobile Networks

Large models (LMs), such as ChatGPT, have made a significant impact across diverse domains and hold great potential to facilitate the evolution of network intelligence. Wireless-native multi-modal large models (WMLMs) can sense and understand the physical world through multi-modal data, serving as a key enabler that integrates communication, sensing, and intelligence, and thus they can boost various smart services to billions of users. However, research on WMLMs remains in its infancy, and the construction of domain-specific multi-modal large models for wireless networks is still underexplored. In this paper, we outlines the key characteristics of WMLMs and summarizes existing methods, on the basis of which a wireless-native multimodal training paradigm is proposed. Specifically, we constructed a GPT-style WMLM model and trained it on a real-world large-scale dataset, leveraging wireless signals as an anchor modality for contrastive learning. Our approach demonstrates outstanding performance compared with existing small-scale models and large multi-modal models, validating the feasibility of using wireless signals as a universal modality and highlighting WMLM's potential to emerge as a new paradigm for future wireless networks.

cs.NI↗

arXiv2025

FourierCompress: Layer-Aware Spectral Activation Compression for Efficient and Accurate Collaborative LLM Inference

Collaborative large language model (LLM) inference enables real-time, privacy-preserving AI services on resource-constrained edge devices by partitioning computational workloads between client devices and edge servers. However, this paradigm is severely hindered by communication bottlenecks caused by the transmission of high-dimensional intermediate activations, exacerbated by the autoregressive decoding structure of LLMs, where bandwidth consumption scales linearly with output length. Existing activation compression methods struggle to simultaneously achieve high compression ratios, low reconstruction error, and computational efficiency. This paper proposes FourierCompress, a novel, layer-aware activation compression framework that exploits the frequency-domain sparsity of LLM activations. We rigorously demonstrate that activations from the first Transformer layer exhibit strong smoothness and energy concentration in the low-frequency domain, making them highly amenable to near-lossless compression via the Fast Fourier Transform (FFT). FourierCompress transforms activations into the frequency domain, retains only a compact block of low-frequency coefficients, and reconstructs the signal at the server using conjugate symmetry, enabling seamless hardware acceleration on DSPs and FPGAs. Extensive experiments on Llama 3 and Qwen2.5 models across 10 commonsense reasoning datasets demonstrate that FourierCompress preserves performance remarkably close to the uncompressed baseline, outperforming Top-k, QR, and SVD. FourierCompress bridges the gap between communication efficiency (an average 7.6x reduction in activation size), near-lossless inference (less than 0.3% average accuracy loss), and significantly faster compression (achieving over 32x reduction in compression time compared to Top-k via hardware acceleration) for edge-device LLM inference.

cs.DC↗

arXiv2025

Learning Function-to-Function Mappings: A Fourier Neural Operator for Next-Generation MIMO Systems

Next-generation multiple-input multiple-output (MIMO) systems, characterized by extremely large-scale arrays, holographic surfaces, three-dimensional architectures, and flexible antennas, are poised to deliver unprecedented data rates, spectral efficiency and stability. However, these advancements introduce significant challenges for physical layer signal processing, stemming from complex near-field propagation, continuous aperture modeling, sub-wavelength antenna coupling effects, and dynamic channel conditions. Conventional model-based and deep learning approaches often struggle with the immense computational complexity and model inaccuracies inherent in these new regimes. This article proposes a Fourier neural operator (FNO) as a powerful and promising tool to address these challenges. The FNO learns function-to-function mappings between infinite-dimensional function spaces, making them exceptionally well-suited for modeling complex physical systems governed by partial differential equations based on electromagnetic wave propagation. We first present the fundamental principles of FNO, demonstrating its mesh-free nature and function-to-function ability to efficiently capture global dependencies in the Fourier domain. Furthermore, we explore a range of applications of FNO in physical-layer signal processing for next-generation MIMO systems. Representative case studies on channel modeling and estimation for novel MIMO architectures demonstrate the superior performance of FNO compared to state-of-the-art methods. Finally, we discuss open challenges and outline future research directions, positioning FNO as a promising technology for enabling the enormous potential of next-generation MIMO systems.

cs.IT↗

arXiv2025

Two-Timescale Learning for Pilot-Free ISAC Systems

A pilot-free integrated sensing and communication (ISAC) system is investigated, in which phase-modulated continuous wave (PMCW) and non-orthogonal multiple access (NOMA) waveforms are co-designed to achieve simultaneous target sensing and data transmission. To enhance effective data throughput (i.e., Goodput) in PMCW-NOMA ISAC systems, we propose a deep learning-based receiver architecture, termed two-timescale Transformer (T3former), which leverages a Transformer architecture to perform joint channel estimation and multi-user signal detection without the need for dedicated pilot signals. By treating the deterministic structure of the PMCW waveform as an implicit pilot, the proposed T3former eliminates the overhead associated with traditional pilot-based methods. The proposed T3former processes the received PMCW-NOMA signals on two distinct timescales, where a fine-grained attention mechanism captures local features across the fast-time dimension, while a coarse-grained mechanism aggregates global spatio-temporal dependencies of the slow-time dimension. Numerical results demonstrate that the proposed T3former significantly outperforms traditional successive interference cancellation (SIC) receivers, which avoids inherent error propagation in SIC. Specifically, the proposed T3former achieves a substantially lower bit error rate and a higher Goodput, approaching the theoretical maximum capacity of a pilot-free system.

cs.IT↗

arXiv2025

When Vision-Language Model (VLM) Meets Beam Prediction: A Multimodal Contrastive Learning Framework

As the real propagation environment becomes in creasingly complex and dynamic, millimeter wave beam prediction faces huge challenges. However, the powerful cross modal representation capability of vision-language model (VLM) provides a promising approach. The traditional methods that rely on real-time channel state information (CSI) are computationally expensive and often fail to maintain accuracy in such environments. In this paper, we present a VLM-driven contrastive learning based multimodal beam prediction framework that integrates multimodal data via modality-specific encoders. To enforce cross-modal consistency, we adopt a contrastive pretraining strategy to align image and LiDAR features in the latent space. We use location information as text prompts and connect it to the text encoder to introduce language modality, which further improves cross-modal consistency. Experiments on the DeepSense-6G dataset show that our VLM backbone provides additional semantic grounding. Compared with existing methods, the overall distance-based accuracy score (DBA-Score) of 0.9016, corresponding to 1.46% average improvement.

eess.SP↗

arXiv2025

Channel Estimation for Flexible Intelligent Metasurfaces: From Model-Based Approaches to Neural Operators

Flexible intelligent metasurfaces (FIMs) offer a new solution for wireless communications by introducing morphological degrees of freedom, dynamically morphing their three-dimensional shape to ensure multipath signals interfere constructively. However, realizing the desired performance gains in FIM systems is critically dependent on acquiring accurate channel state information across a continuous and high-dimensional deformation space. Therefore, this paper investigates this fundamental channel estimation problem for FIM assisted millimeter-wave communication systems. First, we develop model-based frameworks that structure the problem as either function approximation using interpolation and kernel methods or as a sparse signal recovery problem that leverages the inherent angular sparsity of millimeter-wave channels. To further advance the estimation capability beyond explicit assumptions in model-based channel estimation frameworks, we propose a deep learning-based framework using a Fourier neural operator (FNO). By parameterizing a global convolution operator in the Fourier domain, we design an efficient FNO architecture to learn the continuous operator that maps FIM shapes to channel responses with mesh-independent properties. Furthermore, we exploit a hierarchical FNO (H-FNO) architecture to efficiently capture the multi-scale features across a hierarchy of spatial resolutions. Numerical results demonstrate that the proposed H-FNO significantly outperforms the model-based benchmarks in estimation accuracy and pilot efficiency. In particular, the interpretability analysis show that the proposed H-FNO learns an anisotropic spatial filter adapted to the physical geometry of FIM and is capable of accurately reconstructing the non-linear channel response across the continuous deformation space.

cs.IT↗

arXiv2025

A Novel Indicator for Quantifying and Minimizing Information Utility Loss of Robot Teams

The timely exchange of information among robots within a team is vital, but it can be constrained by limited wireless capacity. The inability to deliver information promptly can result in estimation errors that impact collaborative efforts among robots. In this paper, we propose a new metric termed Loss of Information Utility (LoIU) to quantify the freshness and utility of information critical for cooperation. The metric enables robots to prioritize information transmissions within bandwidth constraints. We also propose the estimation of LoIU using belief distributions and accordingly optimize both transmission schedule and resource allocation strategy for device-to-device transmissions to minimize the time-average LoIU within a robot team. A semi-decentralized Multi-Agent Deep Deterministic Policy Gradient framework is developed, where each robot functions as an actor responsible for scheduling transmissions among its collaborators while a central critic periodically evaluates and refines the actors in response to mobility and interference. Simulations validate the effectiveness of our approach, demonstrating an enhancement of information freshness and utility by 98%, compared to alternative methods.

cs.DC↗

arXiv2025

Convergence-Privacy-Fairness Trade-Off in Personalized Federated Learning

Personalized federated learning (PFL), e.g., the renowned Ditto, strikes a balance between personalization and generalization by conducting federated learning (FL) to guide personalized learning (PL). While FL is unaffected by personalized model training, in Ditto, PL depends on the outcome of the FL. However, the clients' concern about their privacy and consequent perturbation of their local models can affect the convergence and (performance) fairness of PL. This paper presents PFL, called DP-Ditto, which is a non-trivial extension of Ditto under the protection of differential privacy (DP), and analyzes the trade-off among its privacy guarantee, model convergence, and performance distribution fairness. We also analyze the convergence upper bound of the personalized models under DP-Ditto and derive the optimal number of global aggregations given a privacy budget. Further, we analyze the performance fairness of the personalized models, and reveal the feasibility of optimizing DP-Ditto jointly for convergence and fairness. Experiments validate our analysis and demonstrate that DP-Ditto can surpass the DP-perturbed versions of the state-of-the-art PFL models, such as FedAMP, pFedMe, APPLE, and FedALA, by over 32.71% in fairness and 9.66% in accuracy.

cs.LG↗

arXiv2025

Enhancing Convergence, Privacy and Fairness for Wireless Personalized Federated Learning: Quantization-Assisted Min-Max Fair Scheduling

Personalized federated learning (PFL) offers a solution to balancing personalization and generalization by conducting federated learning (FL) to guide personalized learning (PL). Little attention has been given to wireless PFL (WPFL), where privacy concerns arise. Performance fairness of PL models is another challenge resulting from communication bottlenecks in WPFL. This paper exploits quantization errors to enhance the privacy of WPFL and proposes a novel quantization-assisted Gaussian differential privacy (DP) mechanism. We analyze the convergence upper bounds of individual PL models by considering the impact of the mechanism (i.e., quantization errors and Gaussian DP noises) and imperfect communication channels on the FL of WPFL. By minimizing the maximum of the bounds, we design an optimal transmission scheduling strategy that yields min-max fairness for WPFL with OFDMA interfaces. This is achieved by revealing the nested structure of this problem to decouple it into subproblems solved sequentially for the client selection, channel allocation, and power control, and for the learning rates and PL-FL weighting coefficients. Experiments validate our analysis and demonstrate that our approach substantially outperforms alternative scheduling strategies by 87.08%, 16.21%, and 38.37% in accuracy, the maximum test loss of participating clients, and fairness (Jain's index), respectively.

cs.DC↗

arXiv2025

Agile Orchestration at Will: An Entire Smart Service-Based Security Architecture Towards 6G

The upcoming 6G will fundamentally reshape mobile networks beyond communications, unlocking a multitude of applications that were once considered unimaginable. Meanwhile, security and resilience are especially highlighted in the 6G design principles. However, safeguarding 6G networks will be quite challenging due to various known and unknown threats from highly heterogeneous networks and diversified security requirements of distinct use cases, calling for a comprehensive re-design of security architecture. This motivates us to propose ES3A (Entire Smart Service-based Security Architecture), a novel security architecture for 6G networks. Specifically, we first discuss six high-level principles of our ES3A that include hierarchy, flexibility, scalability, resilience, endogeny, and trust and privacy. With these goals in mind, we then introduce three guidelines from a deployment perspective, envisioning our ES3A that offers service-based security, end-to-end protection, and smart security automation for 6G networks. Our architecture consists of three layers and three domains. It relies on a two-stage orchestration mechanism to tailor smart security strategies for customized protection in high-dynamic 6G networks, thereby addressing the aforementioned challenges. Finally, we prototype the proposed ES3A on a real-world radio system based on Software-Defined Radio (SDR). Experiments show the effectiveness of our ES3A. We also provide a case to show the superiority of our architecture.

cs.NI↗

arXiv2025

Advancing Expert Specialization for Better MoE

Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input. However, we observe that the commonly used auxiliary load balancing loss often leads to expert overlap and overly uniform routing, which hinders expert specialization and degrades overall performance during post-training. To address this, we propose a simple yet effective solution that introduces two complementary objectives: (1) an orthogonality loss to encourage experts to process distinct types of tokens, and (2) a variance loss to encourage more discriminative routing decisions. Gradient-level analysis demonstrates that these objectives are compatible with the existing auxiliary loss and contribute to optimizing the training process. Experimental results over various model architectures and across multiple benchmarks show that our method significantly enhances expert specialization. Notably, our method improves classic MoE baselines with auxiliary loss by up to 23.79%, while also maintaining load balancing in downstream tasks, without any architectural modifications or additional components. We will release our code to contribute to the community.

cs.CL↗