arXiv subjects

Guangxu Zhu

Publications and source records attributed to Guangxu Zhu.

At least 19 recordsLinked to original sources

arXiv2026

VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference

While Vision Large Language Models (VLLMs) have achieved remarkable success in multimodal reasoning, their long-context inference remains prohibitively expensive due to the massive computation and memory overhead of visual Key-Value (KV) caches. Existing KV compression methods often apply uniform pruning across visual tokens and layers, leading to substantial information loss and degraded performance.To address this challenge, we propose \textbf{VisCache}, a plug-and-play framework for coarse-to-fine \textbf{Vis}ual KV \textbf{Cache} pruning without training, which consists of two synergistic stages. First, a lightweight VLM filters temporal redundancy by selectively forwarding semantically informative keyframes. Second, we introduce {PruneKV}, a surgical KV compression algorithm tailored to the attention dynamics of VLLMs. Unlike rigid pruning strategies, PruneKV adopts a parabolic layer-wise budget allocation together with an asymmetric update mechanism that selectively prunes keys while fusing values, thereby preserving critical contextual information. Extensive experiments demonstrate that VisCache substantially improves inference efficiency, achieving up to {2.35$\times$ speedup} and significant memory reduction while maintaining competitive performance with only {19--28\%} KV cache retention. VisCache consistently outperforms existing baselines, establishing a new Pareto frontier between efficiency and performance for long-context VLLM inference. Code is available at https://github.com/Wlklk/VisCache

cs.CV↗

arXiv2026

Error-Aware Reverse Auction Mechanism for Large Language Model Routing

Routing each query to a cost-effective large language model (LLM) is critical for balancing quality and cost, yet most routers rely on a centralized task center to predict model performance, creating an information-risk mismatch and a scalability bottleneck as the model pool grows. We propose a market-based routing paradigm that shifts ex-ante prediction to LLM providers via a reverse auction, where providers bid with self-predicted success probabilities and execution costs. To account for inherently noisy provider predictions and center evaluations, we introduce the \textit{\textbf{E}rror-\textbf{A}ware \textbf{R}everse \textbf{A}uction \textbf{M}echanism} (EA-RAM), which explicitly models this inherent Dual Error. We prove that EA-RAM is Bayesian incentive compatible and individually rational under the Dual Error, establish sufficient conditions for center rationality, and derive an explicit welfare-loss bound. We further identify robustness effects: opposite-signed errors can cancel, vanishing-tail link functions (e.g., logistic) stabilize clear-cut cases via saturation, and extra noise smooths belief maps, reducing the gains from marginal manipulation. Experiments on simulations and real-world benchmarks show that EA-RAM is robust to the Dual Error and achieves a better cost--performance Pareto frontier than centralized baselines, with additional gains when providers contribute local information, validating its practical effectiveness.

cs.GT↗

arXiv2026

Pruning-Aware Multi-Cluster Co-Inference for Large AI Models in AI-RANs

The increasing scale and computational demands of large artificial intelligence models (LAIMs) present significant challenges for efficient inference in resource-constrained distributed environments. In this paper, we propose a multi-cluster LAIM co-inference framework, where an edge server equipped with multiple graphics processing units (GPUs) coordinates multiple user clusters to execute inference tasks collaboratively. Within each cluster, devices capture data from diverse perspectives and employ lightweight on-device LAIMs to extract local features. These features are then transmitted to the edge server, where they are aggregated and fused to generate a more accurate inference outcome. To reveal the fundamental trade-off between model pruning and collaborative inference performance, we develop a theoretical framework that characterizes the impact of pruning ratios and device contributions using rate-distortion theory and partial information decomposition. Based on this analysis, we formulate a joint optimization problem that determines the model pruning ratio, the task scheduling strategy, the bandwidth allocation, and the transmission power, with the goal of minimizing the inference distortion while satisfying the constraints of latency, energy consumption, and server capacity. Extensive simulation results demonstrate that the proposed framework significantly outperforms existing benchmark schemes, achieving superior inference accuracy and resource efficiency in multi-cluster edge intelligence networks.

cs.DC↗

arXiv2026

Bounded Deep Unfolding for Joint Beamforming and Scheduling in Multi-Cell MIMO Networks

This paper investigates the joint resource block group (RBG) scheduling and beamforming optimization problem for weighted sum-rate (WSR) maximization in multi-cell multiuser multiple-input multiple-output (MU-MIMO) downlink networks. While the Fast Fractional Programming (FastFP) framework provides a reliable model-driven solution, it suffers from conservative continuous beamforming updates and prohibitive computational overhead during the discrete RBG matching phase. To address these bottlenecks, we propose a joint deep unfolding framework comprising two core modules: P-Net and K-Net. Specifically, P-Net learns an adaptive relaxation factor along the FastFP direction, strictly bounded within an ascent-preserving interval to accelerate convergence while retaining stationary-point guarantees. Meanwhile, K-Net learns a long-horizon priority policy to guide a low-complexity greedy assignment, maintaining high assignment quality while bypassing the computationally expensive Hungarian matching. Both networks leverage analytical algorithmic priors and utilize recurrent parameter sharing, enabling flexible inference beyond the training horizon. Extensive simulations demonstrate that the proposed joint framework achieves higher WSR and faster execution times than conventional model-driven baselines, while generalizing robustly across unseen network scales and channel conditions without retraining.

cs.IT↗

arXiv2026

AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence

Mixture of Experts (MoE) are increasingly deployed over wireless cloud-edge networks, as a single edge device lacks sufficient resources to host large-scale models locally. In this distributed architecture, a cloud-hosted pretrained Large Model (LM) acts as a shared backbone for latent feature extraction, while heterogeneous experts deployed across distributed, wirelessly-connected clients collaboratively form the task head. However, deploying MoE over wireless links exposes two coupled bottlenecks. On the one hand, routing which clients to activate generally overloads bandwidth-limited uplinks due to required raw feature transmission. On the other hand, aggregating the activated experts' outputs over wireless links is hindered by channel noise and poor scalability. To break these bottlenecks, we propose a statistic-augmented over-the-air MoE (AirMoE) paradigm. Specifically, on the routing side, each client queries its local Feature Retrieval Library (FRL) with a cloud-broadcast compact query, retrieves a prototype-induced statistic, and reports it digitally to the cloud, drastically reducing uplink traffic; the cloud then selects the most relevant clients by aligning these statistics with the LM-extracted features via Jensen--Shannon (JS) divergence. On the aggregating side, selected experts simultaneously transmit their outputs over the multiple-access channel, which physically computes the reweighted sum via waveform superposition, with reweighting coefficients realized through channel-aware power control. The two mechanisms are thus decoupled both algorithmically and physically. We further provide theoretical analyses on convergence and iteration complexity. Taking semantic segmentation task as an example, extensive experiments demonstrate that AirMoE outperforms MoE baselines and single-model competitors. Ablations further confirm the effectiveness of each incorporated component.

cs.DC↗

arXiv2026

Cross-Domain Radiomap Prediction for Multi-Scatterer Environment: A Spherical-Wave-Based Approach

Radiomap prediction has found extensive applications in network planning and optimization. The radiomap is implicitly determined by electromagnetic (EM) wave propagation. The evolution of wireless communication toward higher frequency spectra has highlighted the effect of mesoscopic (i.e. wavelength-comparable scale) scatterers, which is negligible in the sub-6 GHz spectrum. To address this challenge, we develop a linear forward channel model to capture the propagation behavior in the multi-scatterer environment. The proposed model utilizes spherical-wave mode expansion to track the source radiation pattern, including scattering from a single scatterer and interactions among multiple scatterers. Both phenomena are represented as a superposition of spherical-wave modes, effectively capturing the multipath effect from a wave-based perspective. This forward model is then employed to formulate an inverse optimization problem, where the scattering responses and scatterer locations are jointly learned from sparse field measurements. Simulation results demonstrate that the proposed model accurately reconstructs and extrapolates the radiomap in both the spatial and the beam domain, further enables frequency-domain channel interpolation.

cs.IT↗

arXiv2026

The Universal Language of CSI:Unifying Wireless Sensing Across Devices and Environments

WiFi sensing based on Channel State Information (CSI) promises ubiquitous, device-free perception, yet current research remains trapped in a Tower of Babel - fragmented into isolated silos where models are tailored to specific hardware dialects, fixed environments, and narrow tasks. The primary bottleneck is the Heterogeneity Gap: the disparity in signal dimensions, sampling rates, and semantic labels that prevents cross-system understanding. To bridge this gap, we propose a foundation-model framework that treats CSI not merely as raw signals but as a structured language with a learnable universal grammar. We first curate and standardize a large collection of heterogeneous real-world CSI datasets, establishing a unified infrastructure that allows incompatible signal formats to be treated as a single corpus. Second, we introduce a modular architecture that acts as a universal translator where lightweight dataset-specific adapters tokenize diverse signal inputs into a shared latent vocabulary, while a shared self-supervised Transformer backbone learns the temporal syntax of human motion and environmental dynamics. This design decouples sensing semantics from hardware syntax. Extensive evaluations show that by mastering this universal language, our approach consistently outperforms task-specific baselines and exhibits strong generalization capability in new environments, achieving superior efficiency in few-shot scenarios. By effectively absorbing heterogeneity, the framework offers a path toward robust, general-purpose wireless sensing, mirroring the linguistic generalization observed in Large Language Models. The code implementation is available at: https://github.com/cjychenjiayi/WiLLM.

eess.SP↗

arXiv2026

Performance Analysis for Heterogeneous Air-Ground ISAC in Coordinated Multipoint Networks

The emergence of the \textit{low-altitude economy} (LAE) calls for highly integrated and reliable wireless systems that can simultaneously support \textit{communication and sensing} (C\&S) functions. Although \textit{integrated sensing and communication} (ISAC) has been widely studied, most existing works focused on link-level or single-cell architectures in terrestrial environments, leaving the potential of network-level cooperative air-ground ISAC largely unexplored. To bridge this gap, a heterogeneous air-ground ISAC network architecture based on \textit{coordinated multipoint} (CoMP) is proposed, which incorporates a cooperative hybrid mono/bi-static sensing scheme to enhance spatial diversity and sensing capability. In the proposed architecture, a two-tier \textit{base station} (BS) deployment is adopted: master BSs are arranged in a hexagonal lattice, while slave BSs follow a Poisson point process distribution. This structure concurrently supports communication for terrestrial users and sensing for aerial targets. A holistic performance analysis framework for both C\&S is further developed, accounting for key channel and network parameters. Simulation results reveal inherent trade-offs between C\&S performance, especially under multi-BS cooperation and varying network density. These findings provide practical guidance for the deployment of scalable and efficient ISAC networks in LAE scenarios.

cs.IT↗

arXiv2026

Sense Smarter, Think Better: A Survey on Edge Perception for Next-Generation Networks

Edge perception has emerged as a foundational capability for future wireless networks, enabling the network edge to proactively sense, interpret, and interact with the physical environment in a task-oriented and resource-aware manner. This survey provides a comprehensive and structured overview of edge perception. We first review representative sensing modalities and edge artificial intelligence (AI) techniques as the fundamental building blocks. We then examine their synergistic interactions. We systematically analyze how edge AI enhances sensing capabilities, encompassing both in-band and out-of-band modalities, as well as multi-modal sensor data fusion. Moreover, we discuss the role of task-driven sensing in facilitating edge AI, including integrated sensing-communication-computation designs, and active perception frameworks that dynamically adapt sensing strategies for downstream applications. Finally, we identify key challenges and open issues. By consolidating fragmented research across sensing, communication, and edge AI, this survey provides forward-looking insights for the design and implementation of edge perception systems for sixth-generation (6G) networks.

eess.SP↗

arXiv2026

QoEReasoner: An Agentic Reasoning Framework for Automated and Explainable QoE Diagnosis in RANs

Diagnosing Quality-of-Experience (QoE) degradations in operational Radio Access Networks (RANs) is a critical but notoriously complex task, traditionally requiring labor-intensive expert analysis over high-dimensional, cross-layer telemetry. While Large Language Models (LLMs) offer unprecedented reasoning capabilities, they are fundamentally unsuited for raw RANs troubleshooting: they fail at numeric time-series analysis, hallucinate protocol-violating causal links, and lack the stateful rigor required for multi-step fault localization. To bridge this gap, we present QoEReasoner, an end-to-end, LLM-driven agentic system designed for automated and explainable QoE diagnosis. QoEReasoner tames the inherent unpredictability of LLMs by grounding their reasoning in the physical realities of the network. It employs deterministic tools to reliably translate raw numeric KPIs into structured evidence, enforces protocol-consistent fault propagation through a domain-specific Knowledge Base, and leverages a Historical Bank of expert-validated cases to guide hypothesis generation. A stateful central planner orchestrates this closed-loop process across anomaly detection, causal tracing, and root-cause localization. Evaluations on real-world operational RANs datasets demonstrate that QoEReasoner outperforms strong baselines by 18\%-40\% in accuracy across multiple diagnostic tasks. Furthermore, it reduces diagnostic time from approximately 30 minutes of manual expert analysis to just 3 minutes per session, delivering highly interpretable, expert-grade reports while remaining robust across diverse LLM backbones.

cs.MA↗

arXiv2026

STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series Prediction

Recently, spatio-temporal time-series prediction has developed rapidly, yet existing deep learning methods struggle with learning complex long-term spatio-temporal dependencies efficiently. The long-term spatio-temporal dependency learning brings two new challenges: 1) The long-term temporal sequence naturally includes multiscale information, which is hard to extract efficiently; 2) The multiscale temporal information from different nodes is highly correlated and hard to model. To address these challenges, we propose Spatio-Temporal Mixture of Multiscale Mamba (STM3). STM3 integrates a Multiscale Mamba architecture within a novel Disentangled Mixture-of-Experts (DMoE) framework to capture diverse multiscale information efficiently, while utilizing an adaptive graph causal network to model complex spatial dependencies. To ensure robust representation learning, we introduce a stable routing strategy and a causal contrastive learning strategy, which work in tandem with hierarchical information aggregation to guarantee scale distinguishability. We theoretically prove that STM3 achieves superior routing smoothness and guarantees pattern disentanglement for each expert. Extensive experiments on 10 real-world benchmarks across domains demonstrate STM3's superior performance, achieving state-of-the-art results in long-term spatio-temporal time-series prediction. Notably, on the PEMSD8 dataset, it achieves significant improvements, surpassing the second-best model by 7.1% in MAE, 8.5% in RMSE, and 15.9% in MAPE. Code is available at https://github.com/IfReasonable/STM3_KDD26.

cs.LG↗

arXiv2026

UAV Trajectory and Bandwidth Allocation for Efficient Data Collection in Low-Altitude Intelligent IoT: A Hierarchical DRL Approach

The low-altitude Internet of Things (IoT), supported by unmanned aerial vehicles (UAVs), provides ground sensing networks with advanced real-time monitoring and data collection. To maximize data collection volume from distributed IoT nodes, AI-powered data collection technology plays a critical role in enabling intelligent decision-making. Among them, deep reinforcement learning (DRL) has gained particular attention. However, existing DRL-based work on UAV-assisted IoT data collection rarely addresses challenges such as interference and dynamic data volume, while also suffering from high computational demands and slow convergence. To address these challenges, a hierarchical DRL (HDRL) is designed to optimize UAV trajectories and bandwidth allocation to maximize data collection volume. Firstly, the proposed scenario incorporates interference, dynamic data volume of IoT nodes, and multiple types of obstacles. The entire task is hierarchically structured: the upper-level makes flight trajectory decisions at a coarse temporal granularity, while the lower-level makes bandwidth allocation decisions at a finer temporal granularity. Secondly, a trajectory and bandwidth allocation optimization algorithm based on hierarchical deep deterministic policy gradients (TBH-DDPG) is proposed to solve the problem. Finally, simulation results demonstrate that the proposed algorithm improves convergence speed by 44.44%, and reduces computational cost by 58.05%, compared to non-hierarchical algorithm.

cs.CE↗

arXiv2026

OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization

The global deployment of edge intelligence operates across heterogeneous legal frameworks. While some regions permit centralized learning (CL) via cloud data aggregation, others enforce strict data localization, necessitating federated learning (FL). This operational dichotomy introduces two incompatible optimization regimes (i.e., unbiased global gradients yet coupled with internal covariate shift in CL versus biased, drift-prone local updates in FL), resulting in that any naive integration of the two lacks rigorous theoretical guarantees. To fill this gap, we propose OmniISR, a unified framework that fuses pure CL, pure FL, and hybrid CL-FL training modes via equipping intermediate supervision and regularization (ISR) signals at multiple hidden layers. Specifically, we propose (i) to use mutual-information (MI) as intermediate supervision to align shifting internal covariate in CL and client-drifting representations in FL, and (ii) to adopt negative-entropy (NE) as intermediate regularizer to penalize overconfident prediction, preserve representational uncertainty, and avoid device-specific collapse. On the theory side, we derive (i) a unified, ISR-agnostic, and non-asymptotic O(1/sqrt(T)) convergence bound that shows the introduced ISR does not violate standard SGD convergence, (ii) a federated drift-bound that quantifies the ISR-reduced client drift, (iii) a gradient-alignment guarantee that ensures non-conflicting CL and FL updates under mild bias, and (iv) an explicit escape-time bound that indicates that CL-FL hybrid mixing enlarges effective stochasticity and accelerates escape from strict saddles. Extensive experiments demonstrate that OmniISR consistently improves model performance in both centralized and federated paradigms, reduces the CL-FL gap by 22.60%, and yields 37/48 paired metric wins across multiple FL algorithms.

cs.LG↗

arXiv2026

AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments

Fine-tuning LLMs is necessary for various dedicated downstream tasks, but classic backpropagation-based fine-tuning methods require substantial GPU memory. To this end, a recent work, MeZO, which relies solely on forward passes to fine-tune LLMs, significantly reduces GPU requirements at the cost of slower convergence due to its indifference to loss landscapes. Standard solutions, such as Adam, explore loss landscapes by estimating the first- and second-order moments and storing them in memory to guide the model's movement through dimensions with lower curvature and vice versa. However, directly applying Adam negates MeZO's advantage as it will triple the memory requirement. In light of this, we propose AdaMeZO, a zeroth-order optimizer that leverages Adam-style first- and second-moment estimates without maintaining them in memory. We present a theoretical analysis of AdaMeZO, corroborated by extensive experiments demonstrating AdaMeZO's performance, showing that AdaMeZO can outperform MeZO while requiring up to $70\%$ fewer forward passes. Trajectory visualizations affirm AdaMeZO's ability to adapt to diverse loss landscapes.

cs.LG↗

arXiv2026

Three Birds, One Stone: Solving the Communication-Memory-Privacy Trilemma in LLM Fine-tuning Over Wireless Networks with Zeroth-Order Optimization

Federated Learning (FL) offers a promising pathway for collaboratively fine-tuning Large Language Models (LLMs) at the edge; however, this paradigm faces a critical bottleneck: the prohibitive communication and memory overheads incurred by exchanging high-dimensional gradients. Furthermore, recent studies reveal that user training data can still be recovered from these local gradients, undermining the core privacy promise of FL. In this paper, we address this trilemma of communication, memory, and privacy by proposing pAirZero, a novel framework that synergizes Zeroth-Order (ZO) optimization with Over-the-Air (OTA) computation. Uniquely, pAirZero enables resource-constrained devices to submit their local gradient with only bit-level communication loads while participating in federated fine-tuning of LLMs with inference-level memory costs. This approach not only eliminates the high memory requirements needed for LLM fine-tuning but also alleviates the strict synchronization requirements that plague conventional OTA methods. We further formulate a rigorous optimization model to adaptively determine the optimal transmit power and noise levels, ensuring consistent privacy protection regardless of channel conditions. Numerical experiments demonstrate the superiority of pAirZero in enabling secure, efficient LLM fine-tuning over wireless networks, with only 25% peak memory cost on OPT-125M and communication load orders of magnitude lower than conventional methods.

cs.DC↗

arXiv2026

Bridging Large-Model Reasoning and Real-Time Control via Agentic Fast-Slow Planning

Large foundation models enable powerful reasoning for autonomous systems, but mapping semantic intent to reliable real-time control remains challenging. Existing approaches either (i) let Large Language Models (LLMs) generate trajectories directly - brittle, hard to verify, and latency-prone - or (ii) adjust Model Predictive Control (MPC) objectives online - mixing slow deliberation with fast control and blurring interfaces. We propose Agentic Fast-Slow Planning, a hierarchical framework that decouples perception, reasoning, planning, and control across natural timescales. The framework contains two bridges. Perception2Decision compresses scenes into ego-centric topologies using an on-vehicle Vision-Language Model (VLM) detector, then maps them to symbolic driving directives in the cloud with an LLM decision maker - reducing bandwidth and delay while preserving interpretability. Decision2Trajectory converts directives into executable paths: Semantic-Guided A* embeds language-derived soft costs into classical search to bias solutions toward feasible trajectories, while an Agentic Refinement Module adapts planner hyperparameters using feedback and memory. Finally, MPC tracks the trajectories in real time, with optional cloud-guided references for difficult cases. Experiments in CARLA show that Agentic Fast-Slow Planning improves robustness under perturbations, reducing lateral deviation by up to 45% and completion time by over 12% compared to pure MPC and an A*-guided MPC baseline. Code is available at https://github.com/cjychenjiayi/icra2026_AFSP.

cs.RO↗

arXiv2026

A Disentangled Representation Learning Framework for Low-altitude Network Coverage Prediction

The expansion of the low-altitude economy has underscored the significance of Low-Altitude Network Coverage (LANC) prediction for designing aerial corridors. While accurate LANC forecasting hinges on the antenna beam patterns of Base Stations (BSs), these patterns are typically proprietary and not readily accessible. Operational parameters of BSs, which inherently contain beam information, offer an opportunity for data-driven low-altitude coverage prediction. However, collecting extensive low-altitude road test data is cost-prohibitive, often yielding only sparse samples per BS. This scarcity results in two primary challenges: imbalanced feature sampling due to limited variability in high-dimensional operational parameters against the backdrop of substantial changes in low-dimensional sampling locations, and diminished generalizability stemming from insufficient data samples. To overcome these obstacles, we introduce a dual strategy comprising expert knowledge-based feature compression and disentangled representation learning. The former reduces feature space complexity by leveraging communications expertise, while the latter enhances model generalizability through the integration of propagation models and distinct subnetworks that capture and aggregate the semantic representations of latent features. Experimental evaluation confirms the efficacy of our framework, yielding a 7% reduction in error compared to the best baseline algorithm. Real-network validations further attest to its reliability, achieving practical prediction accuracy with MAE errors at the 5dB level.

cs.NI↗

arXiv2026

FlexSpec: Frozen Drafts Meet Evolving Targets in Edge-Cloud Collaborative LLM Speculative Decoding

Deploying large language models (LLMs) in mobile and edge computing environments is constrained by limited on-device resources, scarce wireless bandwidth, and frequent model evolution. Although edge-cloud collaborative inference with speculative decoding (SD) can reduce end-to-end latency by executing a lightweight draft model at the edge and verifying it with a cloud-side target model, existing frameworks fundamentally rely on tight coupling between the two models. Consequently, repeated model synchronization introduces excessive communication overhead, increasing end-to-end latency, and ultimately limiting the scalability of SD in edge environments. To address these limitations, we propose FlexSpec, a communication-efficient collaborative inference framework tailored for evolving edge-cloud systems. The core design of FlexSpec is a shared-backbone architecture that allows a single and static edge-side draft model to remain compatible with a large family of evolving cloud-side target models. By decoupling edge deployment from cloud-side model updates, FlexSpec eliminates the need for edge-side retraining or repeated model downloads, substantially reducing communication and maintenance costs. Furthermore, to accommodate time-varying wireless conditions and heterogeneous device constraints, we develop a channel-aware adaptive speculation mechanism that dynamically adjusts the speculative draft length based on real-time channel state information and device energy budgets. Extensive experiments demonstrate that FlexSpec achieves superior performance compared to conventional SD approaches in terms of inference efficiency.

cs.DC↗