Searcharxiv⌕ Search

arXiv subjects

Haijun Zhang

Publications and source records attributed to Haijun Zhang.

At least 19 recordsLinked to original sources
arXiv2026

LinearARD: Linear-Memory Attention Distillation for RoPE Restoration

The extension of context windows in Large Language Models is typically facilitated by scaling positional encodings followed by Continued Pre-Training (CPT). While effective, this paradigm is notoriously data-hungry and computationally expensive, requiring massive long-text corpora to recalibrate the model to the shifted positional distribution. We propose LinearARD, a restoration distillation method that restores Rotary Position Embedding (RoPE)-scaled students through attention-structure consistency with a frozen native-RoPE teacher. Rather than next-token prediction or opaque hidden-state matching, LinearARD aligns row-wise distributions of dense $Q/Q$, $K/K$, and $V/V$ self-relation matrices from the final attention layer to directly supervise attention dynamics. To remove the quadratic memory bottleneck of $n \times n$ relation maps, we introduce a linear-activation-memory kernel that stores only per-token log-sum-exp statistics and recomputes logits in the backward pass to obtain exact Kullback-Leibler divergence gradients. Across LLaMA2-7B, LLaMA3-8B, and Mistral-7B-v0.1 extended to 32K context, LinearARD recovers 93.1%/94.2%/94.3% of native short-context performance and achieves strong long-context robustness on RULER using only 4.25M tokens---amounting to just 1.6% (a $\sim$60$\times$ reduction) of the 256M-token budget required by state-of-the-art baselines. Under this severely constrained budget, CPT and LongReD remain near zero on RULER, demonstrating that relation-level restoration provides a substantially better efficiency-quality tradeoff. Our code is available at https://github.com/gracefulning/LinearARD.

cs.CL↗
arXiv2026

Orbital-selective correlations in kagome flat bands of Co$_3$Sn$_2$S$_2$

Geometrical flat bands provide an ideal platform for studying electronic correlations and quantum-geometric effects. Although the ferromagnetic Weyl semimetal \CoSnS is generally considered a moderately correlated system, recent spectroscopy experiments have revealed a flat-band feature near the Fermi level ($\EF$) that is absent in conventional density functional theory (DFT) calculations. Using DFT plus dynamical mean-field theory and a minimal kagome model, we show that this feature arises not from heavy-fermion-like dynamical band renormalization, but from the shifting of a $d_{x^2-y^2}$ dominated geometrical kagome flat band toward $\EF$ driven by orbital- and spin-dependent self-energies. The relocated flat band enhances the local Berry curvature near $\EF$, resulting in a strongly energy-dependent anomalous Hall conductivity and a giant anomalous Nernst effect. Our findings establish an orbital-selective correlation mechanism for positioning geometrical flat bands at $\EF$, and propose anomalous thermoelectric transport as a sensitive probe of flat band induced topology.

cond-mat.str-el↗
arXiv2026

Structured Time-Frequency Representation for Channel Prediction

Accurate CSI forecasting is essential for mitigating channel aging and supporting reliable downlink transmission in high-mobility wireless systems. In FDD systems, forecasting future DL CSI from historical UL observations requires joint temporal extrapolation and cross-band inference. However, defining historical UL as the input and future DL as the target does not specify how elapsed time and UL-to-DL band separation should be represented in a pretrained predictor's positional space. FAR-CSI establishes an FDD-aware representation of channel forecasting within a joint temporal and operating-band positional field. Within this field, historical UL observations and future DL targets occupy segregated regions according to their temporal and operating-band roles, preserving the distinction between observed UL context and unobserved DL prediction targets. This representation is instantiated through a unified structured routing rule that governs encoder positional assignment, decoder-field reconstruction, and future-DL target selection, ensuring the same FDD geometry is preserved from contextual encoding to prediction readout. Under matched backbone, initialization, and training conditions, FDD-aware routing reduces NMSE by 21.44\% relative to generic routing. Across the evaluated FDD baselines, FAR-CSI achieves higher CSI prediction accuracy and MRT-based spectral efficiency, while retaining its predictive advantage across mobility conditions, prediction horizons, reduced training-data regimes, and noisy historical observations.

cs.IT↗
arXiv2026

Multimodal Decoupling for Diversified Recommendation through Semantic and Structural Shaping

Recommender systems often suffer from over-concentrated results when optimized for accuracy, limiting recommendation diversity. While diversity has become an important objective, existing methods still face fundamental limitations from both semantic and structural perspectives. On the one hand, multimodal recommender systems provide rich semantic signals, yet are often treated as auxiliary to ID embeddings, leading to ineffective semantic utilization for diversity. On the other hand, the accuracy--diversity trade-off persists during training, where accuracy gains often come at the cost of diversity. We show that this phenomenon is fundamentally governed by both the structural properties of learned representations and the dynamics of optimization. To address these challenges, we propose MOSS, a unified framework for multimodal decoupling through semantic and structural shaping. Specifically, we first introduce an MLLM-based Decoupled Feature Extraction module to disentangle multimodal content into informative representations. To enhance semantic utilization, we design a Category-aware Embedding Selection module that extracts compact, category-aware semantic features. To address structural limitations, we propose two complementary modules: Alternating Dual-Graph Propagation, which alleviates representation collapse by integrating collaborative and multimodal propagation, and Entropy-based Diversity Regularization, which mitigates optimization bias by promoting balanced category exposure. Extensive experiments on real-world datasets demonstrate that MOSS consistently achieves a superior accuracy--diversity trade-off over strong baselines.

cs.IR↗
arXiv2026

SaTPO: Text-to-Image Safety Alignment via Transition Preference Optimization

Safety alignment of text-to-image diffusion models aims to suppress harmful content without compromising useful generation capabilities. However, preferences over completed images compress multidimensional generation factors into a coarse signal, potentially driving changes beyond those required for safety. To address this, we propose Safety Transition Preference Optimization (SaTPO), which enforces step-wise alignment during denoising. SaTPO leverages the insight that an unsafe prompt and its safe rewrite naturally form a tightly coupled preference pair when conditioned on a shared parent state and noise realization. By anchoring optimization on identical parent states, SaTPO eliminates historical trajectory divergence, confining safety adaptation to an incremental alignment while preserving task-relevant semantics. Multi-scale drift constraints and benign replay further limit behavioral deviation and preserve ordinary generation. We additionally construct CoProPV, a refined dataset ensuring visually verified contrasts. Experiments on Stable Diffusion v1.5 and SDXL demonstrate improved safety-quality trade-offs. Compared with AlignGuard, PerspectiveVision unsafe-detection rates on Inappropriate Image Prompts decrease from 12.70% to 6.00% and from 15.04% to 9.30%, respectively, while FID improves from 32.28 to 25.95 and from 36.50 to 27.51. Warning: this paper includes potentially offensive content.

cs.CV↗
arXiv2026

QoE-Aware Service Function Chain Orchestration in Space-Air-Ground Integrated Networks for In-Flight Internet

In remote regions lacking terrestrial infrastructure, aviation users increasingly demand Internet services comparable to ground cellular networks. This paper proposes a space-air-ground integrated network (SAGIN) architecture that combines ground networks, civil aviation networks, and low Earth orbit (LEO) satellites. Based on real North Atlantic flight data, a heterogeneous aviation Internet is constructed to support diverse aircraft service requirements. A composite Quality of Experience (QoE) metric, characterized by transmission delay, jitter, and content similarity, guides efficient resource utilization. The dynamic connectivity of SAGIN is modeled using a reconfigurable time-expanded graph (RTEG). With Network Function Virtualization (NFV), data delivery is formulated as a Service Function Chain (SFC) deployment across ground stations, relay aircraft, and satellites, resulting in a long-term QoE maximization problem. A tailored Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm incorporating LCSS-based path filtering and softmax-based action selection is developed. Simulation results demonstrate that the proposed approach enables seamless connectivity for heterogeneous aircraft and consistently outperforms game-theoretic and MATD3 methods in terms of QoE.

cs.NI↗
arXiv2026

Offline Policy Optimization with Posterior Sampling

A fundamental challenge in model-based offline reinforcement learning (RL) lies in the trade-off between generalization and robustness against exploitation errors in out-of-distribution (OOD) regions. The key to resolving this trade-off lies in enabling the model to explore OOD regions that remain consistent with underlying physical dynamics. However, achieving this is challenging because limited data cannot uniquely identify the dynamics model, and unconstrained exploration is risky. Existing methods often overlook this nuance, addressing the risk through excessive pessimistic regularization, which ensures robustness but sacrifices generalization. To address this, we propose PSPO, which treats the dynamics model as a random variable rather than a point estimate. This formulation inherently allows for controlled exploration of OOD regions. By alternately updating the posterior distribution and the policy, we design a regularized optimization algorithm with convergence guarantees. Experiments on standard benchmarks demonstrate that PSPO achieves superior performance compared to state-of-the-art baselines. Further analysis confirms that our method attains the desired pessimism-free property while maintaining robustness, and ablation studies verify the effectiveness of each proposed module.

cs.AI↗
arXiv2026

Structured Pose-Conditioned Flow Matching for Generative 5G CSI Augmentation

With the growing demand for privacy-preserving and occlusion-resilient human pose recognition (HPR), 5G channel state information (CSI) offers a promising contactless sensing modality by integrating communication and sensing capabilities. However, collecting large-scale synchronized CSI-pose pairs remains costly in practical 5G systems. To address this limitation, we propose StructFlow-HPR, a structured pose-conditioned flow matching framework for generative CSI augmentation. StructFlow-HPR learns a continuous latent transport process from Gaussian noise to real CSI representations under pose guidance, while preserving the receiver-frequency topology of CSI through a reconstruction-preserving autoencoder. A pose-conditioned Transformer is further designed to model the latent velocity field and generate pose-aligned CSI samples via ordinary differential equation sampling. Experiments on real-world 5G sensing data show that StructFlow-HPR can produce realistic CSI-pose pairs and improve downstream HPR performance under limited-data conditions.

eess.SP↗
arXiv2026

Non-Uniform Activation Aided Distributed Generalized Spatial Modulation for DMIMO Systems

This letter investigates a non-uniform activation aided distributed generalized spatial modulation (DGSM) scheme in a downlink distributed multiple-input multiple-output (DMIMO) system formed by geographically separated transmission reception points (TRPs). Unlike conventional uniform-activation DGSM, the proposed scheme assigns adaptive activation probabilities to different TRP subsets, thereby jointly exploiting the data-domain transmission capability and the index-domain information carried by cooperative subset selection. We derive a mutual-information upper bound under non-uniform activation and formulate a joint activation-probability and power allocation problem subject to a long-term average power constraint. To solve this problem, we develop a semi-closed-form joint probability and power optimization (SC-JPPO) algorithm, where the optimal activation probabilities are shown to follow a Softmax function of the effective utilities. Simulation results demonstrate that the proposed scheme improves spectral efficiency under the same activation scale and power budget compared with existing benchmarks.

cs.IT↗
arXiv2026

TopoCompress: Topology Aware Token Compression Algorithm for Distributed Edge MoE Inference

Mixture-of-experts (MoE) models improve capacity with moderate overhead by sparsely activating experts per token. However, deploying MoE across resource-constrained edge servers incurs substantial cross-server communication as experts are distributed across heterogeneous servers. Existing placement methods optimize for raw token traffic, while conventional compression considers semantics but ignores topology-dependent routing costs. Consequently, independent optimization leads to inefficient communication and resource utilization. This paper proposes TopoCompress, a deployment- and topology-aware token compression framework for communication-efficient distributed edge MoE inference. It jointly optimizes token compression, expert deployment/replication, GPU-CPU residency, and collaborative routing to balance cross-server transmission, quality, and resource use. To address the coupling between token-level compression and epoch-level deployment, TopoCompress employs a two-timescale alternating optimization. In the online fast loop, it identifies and compresses low-importance, high-routing-cost tokens and jointly routes surviving expert activations. In the offline slow loop, it updates expert placement, replication, and GPU-CPU residency according to post-compression traffic accumulated during online inference. We establish the feasibility, optimality, convergence, and computational complexity. Simulations demonstrate that TopoCompress effectively reduces cross-server traffic and deployment resource consumption while maintaining controllable inference quality, enabling efficient distributed MoE inference over bandwidth- and resource-constrained edge infrastructures.

cs.NI↗
arXiv2026

GNN-Based Global CSI Reconstruction for Fronthaul-Limited Distributed MIMO Systems

Global channel state information (CSI) acquisition is essential for cooperative precoding in distributed multiple-input multiple-output (DMIMO) systems, but uploading full instantaneous CSI from all distributed antennas creates heavy fronthaul overhead. This paper proposes a fronthaul-efficient acquisition framework based on graph neural network (GNN) reconstruction and task-driven antenna selection. Each transmission and reception point (TRP) uploads only selected antenna CSI, while the centralized unit (CU) reconstructs the full global CSI from partial observations. A universal mask-conditioned GNN is trained with random upload masks, used to evaluate antenna subsets under a fronthaul budget, and then fine-tuned for the selected deployment mask. Simulation results show improved CSI reconstruction accuracy with lower fronthaul and pilot overhead.

cs.IT↗
arXiv2026

Category-based and Popularity-guided Video Game Recommendation: A Balance-oriented Framework

In recent years, the video game industry has experienced substantial growth, presenting players with a vast array of game choices. This surge in options has spurred the need for a specialized recommender system tailored for video games. However, current video game recommendation approaches tend to prioritize accuracy over diversity, potentially leading to unvaried game suggestions. In addition, the existing game recommendation methods commonly lack the ability to establish strict connections between games to enhance accuracy. Furthermore, many existing diversity-focused methods fail to leverage crucial item information, such as item category and popularity during neighbor modeling and message propagation. To address these challenges, we introduce a novel framework, called CPGRec, comprising three modules, namely accuracy-driven, diversity-driven, and comprehensive modules. The first module extends the state-of-the-art accuracy-focused game recommendation method by connecting games in a more stringent manner to enhance recommendation accuracy. The second module connects neighbors with diverse categories within the proposed game graph and harnesses the advantages of popular game nodes to amplify the influence of long-tail games within the player-game bipartite graph, thereby enriching recommendation diversity. The third module combines the above two modules and employs a new negative-sample rating score reweighting method to balance accuracy and diversity. Experimental results on the Steam dataset demonstrate the effectiveness of our proposed method in improving game recommendations. The dataset and source codes are anonymously released at: https://github.com/CPGRec2024/CPGRec.git.

cs.IR↗
arXiv2026

CPGRec+: A Balance-oriented Framework for Personalized Video Game Recommendations

The rapid expansion of gaming industry requires advanced recommender systems tailored to its dynamic landscape. Existing Graph Neural Network (GNN)-based methods primarily prioritize accuracy over diversity, overlooking their inherent trade-off. To address this, we previously proposed CPGRec, a balance-oriented gaming recommender system. However, CPGRec fails to account for critical disparities in player-game interactions, which carry varying significance in reflecting players' personal preferences and may exacerbate over-smoothness issues inherent in GNN-based models. Moreover, existing approaches underutilize the reasoning capabilities and extensive knowledge of large language models (LLMs) in addressing these limitations. To bridge this gap, we propose two new modules. First, Preference-informed Edge Reweighting (PER) module assigns signed edge weights to qualitatively distinguish significant player interests and disinterests while then quantitatively measuring preference strength to mitigate over-smoothing in graph convolutions. Second, Preference-informed Representation Generation (PRG) module leverages LLMs to generate contextualized descriptions of games and players by reasoning personal preferences from comparing global and personal interests, thereby refining representations of players and games. Experiments on \textcolor{black}{two Steam datasets} demonstrate CPGRec+'s superior accuracy and diversity over state-of-the-art models. The code is accessible at https://github.com/HsipingLi/CPGRec-Plus.

cs.IR↗
arXiv2026

Multi-Turn Reasoning LLMs for Task Offloading in Mobile Edge Computing

Emerging computation-intensive applications impose stringent latency requirements on resource-constrained mobile devices. Mobile Edge Computing (MEC) addresses this challenge through task offloading. However, designing effective policies remains difficult due to dynamic task arrivals, time-varying channels, and the spatio-temporal coupling of server queues. Conventional heuristics lack adaptability, while Deep Reinforcement Learning (DRL) suffers from limited generalization and architectural rigidity, requiring retraining when network topology changes. Although Large Language Models (LLMs) offer semantic reasoning capabilities, standard Supervised Fine-Tuning (SFT) yields myopic policies that greedily minimize immediate latency without accounting for long-term system evolution. To address these limitations, we propose COMLLM, a generative framework that enables foresighted decision-making in MEC systems. COMLLM integrates Group Relative Policy Optimization (GRPO) with a Look-Ahead Collaborative Simulation (LACS) mechanism, which performs multi-step Monte Carlo rollouts while jointly modeling server queue dynamics. By incorporating these rollouts into the reward design, the framework captures the long-term impact of current decisions on future system states. Experimental results demonstrate that COMLLM achieves near-optimal latency and improved load-balancing fairness. Notably, it exhibits zero-shot topological scalability, allowing a model trained on small-scale networks to generalize to larger, unseen topologies without retraining, outperforming SFT, DRL, and heuristic baselines.

cs.LG↗
arXiv2026

LLM-Driven Large-Scale Spectrum Access

Efficient spectrum management in massive-scale wireless networks is increasingly challenged by explosive action spaces and the computational intractability of traditional optimization. This study proposes a LLM-Driven Large-Scale Spectrum Access (LSA) framework rooted in Group Relative Policy Optimization (GRPO). To overcome the computational intractability caused by ultra-long prompts in large-scale scenarios, we develop a hierarchical state serialization mechanism that synthesizes global environment statistics with localized critical constraints, enabling the LLM to perform high-dimensional reasoning within a bounded context window. Simulation results under strictly time-bounded inference protocols reveal that the code-driven paradigm eliminates the Supervised Fine-Tuning (SFT) cold-start bottleneck and leverages direct execution feedback to achieve superior scaling laws. The framework maintains robust spectral utility and generalization across varying network scales, yielding consistent and empirically superior performance over stochastic heuristics, and surpassing partitioned classical solvers in ultra-dense regimes under matched compute budgets. Code is available at https://github.com/Xtdzs/LLM-Driven-Large-Scale-Spectrum-Access.

cs.NI↗
arXiv2026

TrimMoE A communication aware and adaptive depth framework for distributed edge inference

Serving Mixture-of-Experts (MoE) large language models across distributed edge servers is bottlenecked by the cross-server expert transmission. The existing approaches mainly focus on how to reach a remote expert faster. However, in this paper, we instead consider whether a given layer, and the layers after it, need to be executed at all. To this end, a communication-aware adaptive-depth framework is proposed in this paper, termed TrimMoE, which couples layer skipping and confidence-based early exit with substitute execution and server-expert selection under a unified quality budget. Specifically, in the offline stage, TrimMoE freezes the backbone, trains the lightweight per-layer exit heads, calibrates the per-layer importance thresholds, and allocates the expert replicas by a skip/exit-aware redundancy benefit. In the online stage, a transition-aware look-ahead anticipates the token movement, so that the depth reduction targets the costliest transmissions, and besides, two feedback rules adapt the delay-quality weights and the exit threshold. Moreover, we prove that the substitution-and-skipping proxy degradation never exceeds the configured budget, and that the early exit is admitted only under a calibrated confidence gate. On a heterogeneous 10-server testbed with Switch-Base-8E, Qwen-MoE-A2.7B, and Mixtral-8x7B, TrimMoE reduces the average latency by up to 62.8%, lowers the cross-server traffic and the remote-execution ratio, and sustains high throughput under load, while keeping the task-quality degradation within a 2% bound.

cs.NI↗
arXiv2026

HetRoute Heterogeneous and Cost-aware Collaborative Routing Framework for Distributed Edge MoE Inference

Mixture-of-Experts (MoE) models have become a dominant architecture for large-scale AI services, yet deploying them over geo-distributed heterogeneous edge servers remains challenging. When the Top-k activated experts of a token are spread across multiple servers, the optimal routing depends jointly on cross-server link bandwidth, heterogeneous GPU computing capability, GPU-CPU expert loading delay, instantaneous queueing backlog, and replica-level quantization quality loss. Existing distributed inference and MoE serving methods address these factors separately and do not provide a unified framework for online multi-server collaborative routing. In this paper, we propose HetRoute, a heterogeneous-cost-aware collaborative routing framework for distributed edge MoE inference. HetRoute introduces a unified per-assignment cost model that explicitly captures four cost components: cross-server transmission, GPU-CPU offloading, GPU computation with queueing, and quantization-induced quality penalty. Guided by this model, the offline stage determines expert server placement, GPU-CPU residency, and replica precision through a routing-cost-coupled deployment algorithm, while the online stage routes the Top-k activated expert set as a whole by minimizing the bottleneck layer cost via exact enumeration or beam search. Theoretical analysis establishes fallback feasibility, a bound on the number of participating servers, per-layer optimality for small candidate domains, and online computational complexity. Trace-driven evaluation on three MoE models over a heterogeneous 10-server edge testbed shows that HetRoute reduces average inference latency by up to 59.0% and P99 latency by up to 58.0%, cuts cross-server traffic by up to 72.1%, and achieves 2.13x throughput improvement compared with representative baselines, while keeping quality degradation within the configured budget.

cs.NI↗
arXiv2026

Beamforming and Phase Shift Design for STAR-RIS Assisted Secure Sensing and Communication in ISAC Systems

Integrated sensing and communication(ISAC), as a rapidly advancing technique, introduces a fresh approach for achieving secure communication and intelligent sensing for future wireless networks. An ISAC framework empowered by simultaneously transmitting and reflecting reconfigurable intelligent surfaces(STAR-RIS) is explored in this paper, where a base station equipped with multiple antennas establishes wireless links to users each with a single antenna during the detection of a point target. The point target, regarded as an eavesdropper, trying to intercept users' information. Cramer-Rao bound(CRB) serves as evaluation criterion to assess sensing accuracy of point eavesdropper, whereas the secrecy rate is employed to quantify the security level of the communication link. To optimize sensing-communication tradeoff, a joint optimization problem is constructed. To approach the formulated problem, a hybrid Block Coordinate Descent(BCD)-based algorithm is developed, which alternately updates the transmission beamforming and STAR-RIS phase shifts, using successive convex approximation(SCA) technique, penalty dual decomposition (PDD) framework and projected gradient method(PGM).

eess.SP↗