arXiv subjects

Zixin Wang

Publications and source records attributed to Zixin Wang.

At least 19 recordsLinked to original sources

arXiv2026

GSBF: Gaussian Splatting for Environment-Aware Beamforming

Beamforming plays a key role in multiple-input-multiple-output (MIMO) communication systems. However, conventional beamforming design normally requires accurate instantaneous channel state information (CSI) and iterative optimization, which incur substantial pilot overhead and computational complexity. Recognizing that radio propagation is intrinsically governed by the physical geometry, we develop a 3D Gaussian splatting for environment-aware beamforming (GSBF) pipeline based on multi-modal data, which characterizes the environment through a persistent 3D Gaussian representation. Specifically, GSBF models the environmental scattering response with reciprocity-preserving bidirectional spherical Gaussian (Bi-SG) kernels and performs two-sided electromagnetic rasterization to render an angular propagator map. The rendered map is then aggregated through an over-complete array-manifold dictionary and projected to the constant-modulus beamformers, thereby synthesizing beams directly from the access point (AP) pose and user position without online instantaneous CSI. Simulations demonstrate that GSBF consistently outperforms baselines such as exhaustive beam alignment (EBA) with lower latency.

cs.AI↗

arXiv2026

Task-Oriented Precoding for Edge Inference over Large-Scale MIMO Systems

Future wireless networks are expected to support networked artificial intelligence (AI) services, where multiple devices transmit learned features to an edge server for distributed inference. This setting calls for task-oriented physical-layer optimization, where wireless transmission should preserve useful information for inference rather than only maximize the rate or reconstruct the transmitted signals. A key physical-layer control variable is the multiple-input multiple-output precoder, which determines how device features are shaped and combined over wireless channels. Existing task-oriented precoding methods typically adapt the precoder to instantaneous channel state information at the transmitter (CSIT). However, in multi-device MIMO systems, acquiring the aggregate channel, feeding back CSI or optimized precoders, and reoptimizing across coherence blocks introduce substantial overhead. This paper develops a random-matrix-theoretic framework based on statistical CSIT that designs a slow-timescale precoder from channel covariance statistics and training-set feature statistics, without requiring instantaneous CSIT. We adopt maximal coding rate reduction (MCR${^2}$) to measure the class separability of the received features, yielding a task-aware utility for MIMO precoder design. Since this utility still depends on random small-scale fading, we derive a deterministic approximation that converts it into a fixed-point objective depending only on long-term statistics and large-system dimension ratios via random matrix theory. A projected block-coordinate ascent and successive convex approximation algorithm is developed to optimize this deterministic objective under per-device power constraints. Experiments on ModelNet10 verify the approximation and show that the proposed statistical precoder improves task-aware mode allocation and inference performance over competitive benchmarks.

cs.IT↗

arXiv2026

Defending the Core: A Centrality-Based Protection Strategy for Supply Chain Security in npm Dependency Network

The modern software supply chain, taking Node Package Manager (npm) dependency network for example, relies heavily on shared open-source dependencies. While this promotes rapid development, it introduces systemic vulnerabilities as well. Concerning this potential risk, we analyze the npm dependency network by modeling 53,481 packages and 78,520 dependency edges, and classify the network as a scale-free topology. Thus, we demonstrate its inherent vulnerability to targeted attacks on high-degree hubs. To mitigate this, we propose and evaluate a dual-pronged defense strategy consisting of Centrality-Based Node-Hardening and Dependency Weight Warning system. Moreover, by simulating the network under various attack scenarios, we prove that applying strict security protocols to just the top 1% of nodes, combined with pruning 30% of structurally trivial edges, prevents catastrophic network collapse and neutralizes cascading malware infections. The source code can be found at https://github.com/5tarWhee1/Centrality-Based-Protection-Strategy-for-Supply-Chain-Security-in-npm-Dependency-Network.

cs.CR↗

arXiv2026

Automated Gaze-based Behavioral Segmentation and Temporal Representation for Bridge Inspection in Unconstrained 3D Environments

Visual bridge inspection is a knowledge-intensive task in which inspectors coordinate visual search, spatial navigation, structural reasoning, and defect identification and documentation. It is a central maintenance task for bridges and a key basis for safety assessments, yet its results are susceptible to individual subjectivity. While eye-tracking-based behavioral studies quantify underlying processes, existing research often imposes restrictive simplifications to reduce environmental complexity, thereby compromising ecological validity. This study proposes an automated data analytics framework for converting multimodal inspection data into an inspection mode time series. Unconstrained 3D gaze, head-movement, drone navigation, and scene geometry data are segmented into temporal windows and classified into three functional modes: global scanning, local inspection, and navigation. The resulting temporal representation enables the extraction of interpretable behavioral descriptors, including transition probabilities, dwell times, transition entropy, fixation measures, and spatial revisit metrics. A feasibility study using a virtual bridge inspection platform demonstrates that the proposed representation captures meaningful differences in inspection strategy and reveals exploratory relationships with inspection performance. This study contributes a framework for human-informed computer-aided infrastructure inspection systems, inspector training, and data-driven assessment of constructed facilities.

cs.HC↗

arXiv2026

SmartFont: Dynamic Condition Allocation for Few-Shot Font Generation

Few-shot font generation simultaneously requires global structural completeness and fine-grained local style fidelity. Existing methods usually either rely on global content-style modeling, which is robust but imperfectly disentangled, or emphasize component/local modeling, which captures fine details but relies heavily on local priors and reference coverage. We argue that the key challenge is not merely to learn purer conditions, but to organize complementary yet biased global and local conditions through multi-level allocation during generation. To this end, we propose SmartFont, a diffusion-based few-shot font generation framework that combines global content-style generation with weakly supervised local corrective experts. The local branch performs semantic-spatial allocation by learning expert-wise local concepts and semantically meaningful spatial maps under weak component supervision, enabling fine-grained correction without requiring explicit component-conditioned inference. On top of this, a denoising-state condition allocation module adaptively weights global content, global style, and local corrective feature across timesteps and injection blocks. Extensive experiments show that SmartFont achieves better global-local balance, improves glyph quality and local detail fidelity.

cs.CV↗

arXiv2026

Sensing-Assisted Channel Estimation for Flexible-Antenna Systems: A Unified Framework

Flexible-antenna systems, which use a small number of radio frequency (RF) chains to dynamically access a large set of candidate antenna locations, have emerged as a hardware-efficient architecture for 6G networks. Acquiring accurate channel state information (CSI) is critical for these systems, but it typically incurs a prohibitive pilot overhead that scales with the massive number of candidate locations. To address this bottleneck, we propose a unified sensing-assisted channel estimation framework tailored for flexible-antenna systems. It reduces the full CSI reconstruction problem to a consistent two-stage process: it first resolves the dominant DOAs from the uplink data symbols by exploiting the spatial geometry, requiring no dedicated sensing pilot, and then calibrates the associated path gains using a minimal number of calibration pilots. Building on this pipeline, we develop two Newton-MUSIC algorithms tailored to different propagation environments. For line-of-sight (LOS)-dominant environments with uncorrelated sources, we propose SOC-Newton-MUSIC, which leverages second-order covariance (SOC) for low-complexity DOA sensing. For non-line-of-sight (NLOS) environments with coherent multipath, where the number of sources may exceed the number of activated RF chains, we propose FOC-Newton-MUSIC, which exploits fourth-order cumulants (FOC) to restore source identifiability and structurally expand the available spatial degrees of freedom (DOFs) through a continuous difference co-array. In both cases, by reformulating the spatial spectrum search as a continuous optimization problem, we replace exhaustive dense grid searches with parallelized Newton refinements.

eess.SP↗

arXiv2026

Rethinking Mutual Coupling in Movable Antenna MIMO Systems: Modeling and Optimization

Movable antennas (MAs) have attracted growing interest for their ability to improve channel conditions via adaptive antenna movement. Nevertheless, such movement inevitably introduces mutual coupling (MC), whose impact has been largely overlooked in existing MA literature. In this paper, we show that MC is not merely an unavoidable electromagnetic effect, but also a new source of capacity gains in MA-enabled multiple-input multiple-output (MIMO) systems. To leverage MC effects, we develop an optimization framework for both narrowband and wideband systems based on a rigorous circuit-theoretic model. For narrowband systems, capacity maximization is formulated as a non-convex optimization problem, which is solved via a block coordinate ascent (BCA) framework. Because optimizing MA positions is challenging due to analytically intractable MC matrices, we develop a trust region method (TRM)-based algorithm that utilizes Sylvester equations to compute the derivatives of the inverse square roots of the MC matrices. We further consider wideband systems and formulate a sum-rate maximization problem. To find a unified set of MA positions that balances varying subcarrier conditions, the BCA framework and the TRM-based MA position optimization algorithm are extended to wideband systems. Simulation results demonstrate that exploiting MC effects in MA-MIMO systems yields significant performance gains in both narrowband and wideband systems under various channel conditions. These gains highlight the benefits of MC-induced superdirectivity and designable MC matrices.

cs.IT↗

arXiv2026

Infrastructure First: Enabling Embodied AI for Science in the Global South

Embodied AI for Science (EAI4S) brings intelligence into the laboratory by uniting perception, reasoning, and robotic action to autonomously run experiments in the physical world. For the Global South, this shift is not about adopting advanced automation for its own sake, but about overcoming a fundamental capacity constraint: too few hands to run too many experiments. By enabling continuous, reliable experimentation under limits of manpower, power, and connectivity, EAI4S turns automation from a luxury into essential scientific infrastructure. The main obstacle, however, is not algorithmic capability. It is infrastructure. Open-source AI and foundation models have narrowed the knowledge gap, but EAI4S depends on dependable edge compute, energy-efficient hardware, modular robotic systems, localized data pipelines, and open standards. Without these foundations, even the most capable models remain trapped in well-resourced laboratories. This article argues for an infrastructure-first approach to EAI4S and outlines the practical requirements for deploying embodied intelligence at scale, offering a concrete pathway for Global South institutions to translate AI advances into sustained scientific capacity and competitive research output.

cs.CY↗

arXiv2026

A Learning-Based Cooperative Coevolution Framework for Heterogeneous Large-Scale Global Optimization

Cooperative Coevolution (CC) effectively addresses Large-Scale Global Optimization (LSGO) via decomposition but struggles with the emerging class of Heterogeneous LSGO (H-LSGO) problems arising from real-world applications, where subproblems exhibit diverse dimensions and distinct landscapes. The prevailing CC paradigm, relying on a fixed low-dimensional optimizer, often fails to navigate this heterogeneity. To address this limitation, we propose the Learning-Based Heterogeneous Cooperative Coevolution Framework (LH-CC). By formulating the optimization process as a Markov Decision Process, LH-CC employs a meta-agent to adaptively select the most suitable optimizer for each subproblem. We also introduce a flexible benchmark suite to generate diverse H-LSGO problem instances. Extensive experiments on 3000-dimensional problems with complex coupling relationships demonstrate that LH-CC achieves superior solution quality and computational efficiency compared to state-of-the-art baselines. Furthermore, the framework exhibits robust generalization across varying problem instances, optimization horizons, and optimizers. Our findings reveal that dynamic optimizer selection is a pivotal strategy for solving complex H-LSGO problems.

cs.NE↗

arXiv2026

Service Function Chain Routing in LEO Networks Using Shortest-Path Delay Statistical Stability

Low Earth orbit (LEO) satellite constellations have become a critical enabler for global coverage, utilizing numerous satellites orbiting Earth at high speeds. By decomposing complex network services into lightweight service functions, network function virtualization (NFV) transforms global network services into diverse service function chains (SFCs), coordinated by resource-constrained LEOs. However, the dynamic topology of satellite networks, marked by highly variable inter-satellite link delays, poses significant challenges for designing efficient routing strategies that ensure reliable and low-latency communication. Many existing routing methods suffer from poor scalability and degraded performance, limiting their practical implementation. To address these challenges, this paper proposes a novel SFC routing approach that leverages the statistical properties of network link states to mitigate instability caused by instantaneous modeling in dynamic satellite networks. Through comprehensive simulations on end-to-end shortest-path propagation delays in LEO networks, we identify and validate the statistical stability of multi-hop routes. Building on this insight, we introduce the Stability-Aware Multi-Stage Graph Routing (SA-MSGR) algorithm, which incorporates pre-computed average delays into a multi-stage graph optimization framework. Extensive simulations demonstrate the superior performance of SA-MSGR, achieving significantly lower and more predictable end-to-end SFC delays compared to representative baseline strategies.

cs.NI↗

arXiv2026

Unseen Cost of Space Computing: Quantifying LEO Battery Aging via Physics-Driven Modeling

Low Earth Orbit (LEO) satellite constellations in the 6G era are evolving into intelligent in-orbit computational platforms, forming Space Computing Power Networks (SCPNs) to deliver global-scale computing services. However, the intensive computation within SCPN incurs a significant ``unseen cost'': the frequent charge-discharge cycles accelerate the physical degradation of satellites' life-limiting and high-cost batteries, thereby threatening the long-term operational viability of such a system. Existing approaches, often relying on indirect metrics like Depth of Discharge (DoD) and neglecting the complex, nonlinear degradation process of battery aging, fail to accurately quantify this cost. To address this, we introduce a high-fidelity, physics-driven model that quantitatively links computational workload parameters to the nonlinear battery degradation. Building on this model, we formulate a degradation-aware scheduling problem and analyze heuristic policies across different energy regimes. Simulations reveal that the optimal strategy should be adaptive: in solar-rich conditions, a myopic policy maximizing instantaneous solar utilization is superior, whereas under energy scarcity, a reactive policy leveraging real-time battery state significantly extends lifetime.

eess.SP↗

arXiv2026

Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping

Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance on the design-to-code task, i.e., generating UI code from UI mock-ups. However, existing benchmarks only contain static web pages for evaluation and ignore the dynamic interaction, limiting the practicality, usability and user engagement of the generated webpages. To bridge these gaps, we present the first systematic investigation of MLLMs in generating interactive webpages. Specifically, we formulate the Interaction-to-Code task and establish the Interaction2Code benchmark, encompassing 127 unique webpages and 374 distinct interactions across 15 webpage types and 31 interaction categories. Through comprehensive experiments utilizing state-of-the-art (SOTA) MLLMs, evaluated via both automatic metrics and human assessments, we identify four critical limitations of MLLM on Interaction-to-Code task: (1) inadequate generation of interaction compared with full page, (2) prone to ten types of failure, (3) poor performance on visually subtle interactions, and (4) insufficient undestanding on interaction when limited to single-modality visual descriptions. To address these limitations, we propose four enhancement strategies: Interactive Element Highlighting, Failureaware Prompting (FAP), Visual Saliency Enhancement, and Visual-Textual Descriptions Combination, all aiming at improving MLLMs' performance on the Interaction-toCode task. The Interaction2Code benchmark and code are available in https://github. com/WebPAI/Interaction2Code.

cs.SE↗

arXiv2026

Modular Foundation Model Inference at the Edge: Network-Aware Microservice Optimization

Foundation models (FMs) unlock unprecedented multimodal and multitask intelligence, yet their cloud-centric deployment precludes real-time responsiveness and compromises user privacy. Meanwhile, monolithic execution at the edge remains infeasible under stringent resource limits and uncertain network dynamics. To bridge this gap, we propose a microservice-based FM inference framework that exploits the intrinsic functional asymmetry between heavyweight core services and agile light services. Our two-tier deployment strategy ensures robust Quality of Service (QoS) under resource contention. Specifically, core services are placed statically via a long-term network-aware integer program with sparsity constraints to form a fault-tolerant backbone. On the other hand, light services are orchestrated dynamically by a low-complexity online controller that integrates effective capacity theory with Lyapunov optimization, providing probabilistic latency guarantees under real-time workload fluctuations. Simulations demonstrate that our framework achieves over 84% average on-time task completion with moderate deployment costs and maintains strong robustness as the system load scales.

cs.DC↗

arXiv2025

Bridging simulation and reality in subsurface radar-based sensing: physics-guided hierarchical domain adaptation with deep adversarial learning

Accurate estimation of subsurface material properties, such as soil moisture, is critical for wildfire risk assessment and precision agriculture. Ground-penetrating radar (GPR) is a non-destructive geophysical technique widely used to characterize subsurface conditions. Data-driven parameter estimation methods typically require large amounts of labeled training data, which is expensive to obtain from real-world GPR scans under diverse subsurface conditions. A physics-based GPR model using the finite-difference time-domain (FDTD) method can be employed to generate large synthetic datasets through simulations across varying material parameters, which are then utilized to train data-driven models. A key limitation, however, is that simulated data (source domain) and real-world data (target domain) often follow different distributions, which can cause data-driven models trained on simulations to underperform in real-world scenarios. To address this challenge, this study proposes a novel physics-guided hierarchical domain adaptation framework with deep adversarial learning for robust subsurface material property estimation from GPR signals. The proposed framework is systematically evaluated through the laboratory tests for single- and two-layer materials, as well as the field tests for single- and two-layer materials, and is benchmarked against state-of-the-art methods, including the one-dimensional convolutional neural network (1D CNN) and domain adversarial neural network (DANN). The results demonstrate that the proposed framework achieves higher correlation coefficients R and lower Bias between the predicted and measured parameter values, along with smaller standard deviations in the estimations, thereby validating their effectiveness in bridging the domain gap between simulated and real-world radar signals and enabling efficient subsurface material property retrieval.

eess.SP↗

arXiv2025

RapVerse: Coherent Vocals and Whole-Body Motions Generations from Text

In this work, we introduce a challenging task for simultaneously generating 3D holistic body motions and singing vocals directly from textual lyrics inputs, advancing beyond existing works that typically address these two modalities in isolation. To facilitate this, we first collect the RapVerse dataset, a large dataset containing synchronous rapping vocals, lyrics, and high-quality 3D holistic body meshes. With the RapVerse dataset, we investigate the extent to which scaling autoregressive multimodal transformers across language, audio, and motion can enhance the coherent and realistic generation of vocals and whole-body human motions. For modality unification, a vector-quantized variational autoencoder is employed to encode whole-body motion sequences into discrete motion tokens, while a vocal-to-unit model is leveraged to obtain quantized audio tokens preserving content, prosodic information and singer identity. By jointly performing transformer modeling on these three modalities in a unified way, our framework ensures a seamless and realistic blend of vocals and human motions. Extensive experiments demonstrate that our unified generation framework not only produces coherent and realistic singing vocals alongside human motions directly from textual inputs, but also rivals the performance of specialized single-modality generation systems, establishing new benchmarks for joint vocal-motion generation.

cs.CV↗

arXiv2025

TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation

In this work, we present TalkCuts, a large-scale dataset designed to facilitate the study of multi-shot human speech video generation. Unlike existing datasets that focus on single-shot, static viewpoints, TalkCuts offers 164k clips totaling over 500 hours of high-quality human speech videos with diverse camera shots, including close-up, half-body, and full-body views. The dataset includes detailed textual descriptions, 2D keypoints and 3D SMPL-X motion annotations, covering over 10k identities, enabling multimodal learning and evaluation. As a first attempt to showcase the value of the dataset, we present Orator, an LLM-guided multi-modal generation framework as a simple baseline, where the language model functions as a multi-faceted director, orchestrating detailed specifications for camera transitions, speaker gesticulations, and vocal modulation. This architecture enables the synthesis of coherent long-form videos through our integrated multi-modal video generation module. Extensive experiments in both pose-guided and audio-driven settings show that training on TalkCuts significantly enhances the cinematographic coherence and visual appeal of generated multi-shot speech videos. We believe TalkCuts provides a strong foundation for future work in controllable, multi-shot speech video generation and broader multimodal learning.

cs.CV↗

arXiv2025

MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in visual mathematical reasoning across various existing benchmarks. However, these benchmarks are predominantly based on clean or processed multimodal inputs, without incorporating the images provided by real-world Kindergarten through 12th grade (K-12) educational users. To address this gap, we introduce MathReal, a meticulously curated dataset comprising 2,000 mathematical questions with images captured by handheld mobile devices in authentic scenarios. Each question is an image, containing the question text and visual element. We systematically classify the real images into three primary categories: image quality degradation, perspective variation, and irrelevant content interference, which are further delineated into 14 subcategories. Additionally, MathReal spans five core knowledge and ability categories, which encompass three question types and are divided into three difficulty levels. To comprehensively evaluate the multimodal mathematical reasoning abilities of state-of-the-art MLLMs in real-world scenarios, we design six experimental settings that enable a systematic analysis of their performance. Through extensive experimentation, we find that the problem-solving abilities of existing MLLMs are significantly challenged in realistic educational contexts. Based on this, we conduct a thorough analysis of their performance and error patterns, providing insights into their recognition, comprehension, and reasoning capabilities, and outlining directions for future improvements. Data and code: https://github.com/junfeng0288/MathReal.

cs.CV↗

arXiv2025

EnergyPatchTST: Multi-scale Time Series Transformers with Uncertainty Estimation for Energy Forecasting

Accurate and reliable energy time series prediction is of great significance for power generation planning and allocation. At present, deep learning time series prediction has become the mainstream method. However, the multi-scale time dynamics and the irregularity of real data lead to the limitations of the existing methods. Therefore, we propose EnergyPatchTST, which is an extension of the Patch Time Series Transformer specially designed for energy forecasting. The main innovations of our method are as follows: (1) multi-scale feature extraction mechanism to capture patterns with different time resolutions; (2) probability prediction framework to estimate uncertainty through Monte Carlo elimination; (3) integration path of future known variables (such as temperature and wind conditions); And (4) Pre-training and Fine-tuning examples to enhance the performance of limited energy data sets. A series of experiments on common energy data sets show that EnergyPatchTST is superior to other commonly used methods, the prediction error is reduced by 7-12%, and reliable uncertainty estimation is provided, which provides an important reference for time series prediction in the energy field.

cs.LG↗