arXiv subjects

Wei Xiang

Publications and source records attributed to Wei Xiang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Spectrally Distilled Representations Aligned with Instruction-Augmented LLMs for Satellite Imagery

Vision-language foundation models (VLFMs) promise zero-shot and retrieval understanding for Earth observation. While operational satellite systems often lack full multi-spectral coverage, making RGB-only inference highly desirable for scalable deployment, the adoption of VLFMs for satellite imagery remains hindered by two factors: (1) multi-spectral inputs are informative but difficult to exploit consistently due to band redundancy and misalignment; and (2) CLIP-style text encoders limit semantic expressiveness and weaken fine-grained alignment. We present SATtxt, a spectrum-aware VLFM that operates with RGB inputs only at inference while retaining spectral cues learned during training. Our framework comprises two stages. First, Spectral Representation Distillation transfers spectral priors from a frozen multi-spectral teacher to an RGB student via a lightweight projector. Second, Spectrally Grounded Alignment with Instruction-Augmented LLMs bridges the distilled visual space and an expressive LLM embedding space. Across EuroSAT, BigEarthNet, and ForestNet, SATtxt improves zero-shot classification on average by 4.2%, retrieval by 5.9%, and linear probing by 2.7% over baselines, showing an efficient path toward spectrum-aware vision-language learning for Earth observation. Project page: https://ikhado.github.io/sattxt/

cs.CV↗

arXiv2026

Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chaining

Deep topological data analysis (TDA) offers a principled framework for capturing structural invariants such as connectivity and cycles that persist across scales, making it a natural fit for anomaly segmentation (AS). Unlike thresholdbased binarisation, which produces brittle masks under distribution shift, TDA allows anomalies to be characterised as disruptions to global structure rather than local fluctuations. We introduce TopoOT, a topology-aware optimal transport (OT) framework that integrates multi-filtration persistence diagrams (PDs) with test-time adaptation (TTA). Our key innovation is Optimal Transport Chaining, which sequentially aligns PDs across thresholds and filtrations, yielding geodesic stability scores that identify features consistently preserved across scales. These stabilityaware pseudo-labels supervise a lightweight head trained online with OT-consistency and contrastive objectives, ensuring robust adaptation under domain shift. Across standard 2D and 3D anomaly detection benchmarks, TopoOT achieves state-of-the-art performance, outperforming the most competitive methods by up to +24.1% mean F1 on 2D datasets and +10.2% on 3D AS benchmarks.

cs.CV↗

arXiv2026

Transonic shock solutions for steady 3-D axisymmetric full Euler flows with large swirl velocity in a finite cylindrical nozzle

This paper concerns the existence and location of three-dimensional axisymmetric transonic shocks with large swirl velocity for shock solutions of the steady compressible full Euler system in a cylindrical nozzle with prescribed receiver pressure. As far as we know, it is the first mathematical result on the three-dimensional transonic shock with either large vorticity or large swirl velocity. One of the key difficulties is the fact that the Euler system is elliptic-hyperbolic composite for the flow behind the shock front, and its elliptic part and hyperbolic part are strongly coupled in the lower order terms because of the large swirl velocity, such that they cannot be simply decoupled in the principal parts as the case for the flow without swirls or with small swirl velocity. New decomposition techniques for the elliptic-hyperbolic composite system are developed to deal with this difficulty, and the solvability condition for the boundary value problem is deduced to determine the location of the shock front. It finally turns out that the non-zero swirl velocity, which brings new challenging difficulties in the analysis, plays an essential and fundamental role in determining the location of the shock front. Another key difficulty in the analysis is that there are no readily established shock solutions available. Non-trivial special shock solutions are first constructed as background solutions under the assumption that the flow parameters depend only on the radial distance to the symmetric axis. Necessary and sufficient conditions for the existence of such solutions are also found. Even though the shock location can be arbitrarily shifted for the special shock solutions, it will be shown that the shock solution with a determined shock position can be established as the boundary data are perturbations of one of the established special shock solutions under certain conditions.

math.AP↗

arXiv2026

Learning the Basis: A Kolmogorov-Arnold Network Approach Embedding Green's Function Priors

The Method of Moments (MoM) is constrained by the usage of static, geometry-defined basis functions, such as the Rao-Wilton-Glisson (RWG) basis. This letter reframes electromagnetic modeling around a learnable basis representation rather than solving for the coefficients over a fixed basis. We first show that the RWG basis is essentially a static and piecewise-linear realization of the Kolmogorov-Arnold representation theorem. Inspired by this insight, we propose PhyKAN, a physics-informed Kolmogorov-Arnold Network (KAN) that generalizes RWG into a learnable and adaptive basis family. Derived from the EFIE, PhyKAN integrates a local KAN branch with a global branch embedded with Green's function priors to preserve physical consistency. It is demonstrated that, across canonical geometries, PhyKAN achieves sub-0.01 reconstruction errors as well as accurate, unsupervised radar cross section predictions, offering an interpretable, physics-consistent bridge between classical solvers and modern neural network models for electromagnetic modeling.

cs.LG↗

arXiv2026

3D Dynamic Radio Map Prediction Using Vision Transformers for Low-Altitude Wireless Networks

Low-altitude wireless networks (LAWN) are rapidly expanding with the growing deployment of unmanned aerial vehicles (UAVs) for logistics, surveillance, and emergency response. Reliable connectivity remains a critical yet challenging task due to three-dimensional (3D) mobility, time-varying user density, and limited power budgets. The transmit power of base stations (BSs) fluctuates dynamically according to user locations and traffic demands, leading to a highly non-stationary 3D radio environment. Radio maps (RMs) have emerged as an effective means to characterize spatial power distributions and support radio-aware network optimization. However, most existing works construct static or offline RMs, overlooking real-time power variations and spatio-temporal dependencies in multi-UAV networks. To overcome this limitation, we propose a 3D dynamic radio map (3D-DRM) framework that learns and predicts the spatio-temporal evolution of received power. Specially, a Vision Transformer (ViT) encoder extracts high-dimensional spatial representations from 3D RMs, while a Transformer-based module models sequential dependencies to predict future power distributions. Experiments unveil that 3D-DRM accurately captures fast-varying power dynamics and substantially outperforms baseline models in both RM reconstruction and short-term prediction.

cs.LG↗

arXiv2026

Diffusion Model-Enhanced Environment Reconstruction in ISAC

Recently, environment reconstruction (ER) in integrated sensing and communication (ISAC) systems has emerged as a promising approach for achieving high-resolution environmental perception. However, the initial results obtained from ISAC systems are coarse and often unsatisfactory due to the high sparsity of the point clouds and significant noise variance. To address this problem, we propose a noise-sparsity-aware diffusion model (NSADM) post-processing framework. Leveraging the powerful data recovery capabilities of diffusion models, the proposed scheme exploits spatial features and the additive nature of noise to enhance point cloud density and denoise the initial input. Simulation results demonstrate that the proposed method significantly outperforms existing model-based and deep learning-based approaches in terms of Chamfer distance and root mean square error.

cs.NI↗

arXiv2025

Joint Channel Estimation and Localization in Pinching-Antenna OFDM Systems: The Blessing of Multipath

Pinching-antenna systems (PASS) have recently attracted considerable attention owing to their capability of flexibly reconfiguring large-scale wireless channels. Motivated by this potential, we investigate the issue of joint localization and channel estimation for the uplink PASS in the presence of multipath dispersion. To this end, a comprehensive multi-user orthogonal frequency division multiplexing (OFDM) uplink PASS model is first established, where the use of a cyclic prefix (CP) enables the multipath-induced time-domain dispersion to be transformed into a set of superimposed sinusoids in the frequency domain. Building upon this model, we propose a hybrid inference framework capable of accurately estimating both channel parameters and user locations. Specifically, expectation propagation is first employed to mitigate multi-user interference, while the path delays are then extracted from noisy channel state information using an orthogonal matching pursuit (OMP) based approach, or a hybrid belief propagation-variational inference (BP-VI) algorithm. Then the estimated delays are subsequently refined through the embedded geometric information via an iterative localization procedure, wherein the estimated channel matrices are recursively fed back to EP. Furthermore, the Cramer-Rao lower bound (CRLB) is derived to characterize the fundamental estimation limits. Finally, simulation results validate that our proposed framework closely approaches the CRLB, with performance comparable to cooperative multi-base station localization, with significantly fewer RF chains and reduced hardware complexity.

eess.SP↗

arXiv2025

Visionary Co-Driver: Enhancing Driver Perception of Potential Risks with LLM and HUD

Drivers' perception of risky situations has always been a challenge in driving. Existing risk-detection methods excel at identifying collisions but face challenges in assessing the behavior of road users in non-collision situations. This paper introduces Visionary Co-Driver, a system that leverages large language models to identify non-collision roadside risks and alert drivers based on their eye movements. Specifically, the system combines video processing algorithms and LLMs to identify potentially risky road users. These risks are dynamically indicated on an adaptive heads-up display interface to enhance drivers' attention. A user study with 41 drivers confirms that Visionary Co-Driver improves drivers' risk perception and supports their recognition of roadside risks.

cs.HC↗

arXiv2025

Joint Optimization of Cooperation Efficiency and Communication Covertness for Target Detection with AUVs

This paper investigates underwater cooperative target detection using autonomous underwater vehicles (AUVs), with a focus on the critical trade-off between cooperation efficiency and communication covertness. To tackle this challenge, we first formulate a joint trajectory and power control optimization problem, and then present an innovative hierarchical action management framework to solve it. According to the hierarchical formulation, at the macro level, the master AUV models the agent selection process as a Markov decision process and deploys the proximal policy optimization algorithm for strategic task allocation. At the micro level, each selected agent's decentralized decision-making is modeled as a partially observable Markov decision process, and a multi-agent proximal policy optimization algorithm is used to dynamically adjust its trajectory and transmission power based on its local observations. Under the centralized training and decentralized execution paradigm, our target detection framework enables adaptive covert cooperation while satisfying both energy and mobility constraints. By comprehensively modeling the considered system, the involved signals and tasks, as well as energy consumption, theoretical insights and practical solutions for the efficient and secure operation of multiple AUVs are provided, offering significant implications for the execution of underwater covert communication tasks.

cs.LG↗

arXiv2025

SocializeChat: A GPT-Based AAC Tool Grounded in Personal Memories to Support Social Communication

Elderly people with speech impairments often face challenges in engaging in meaningful social communication, particularly when using Augmentative and Alternative Communication (AAC) tools that primarily address basic needs. Moreover, effective chats often rely on personal memories, which is hard to extract and reuse. We introduce SocializeChat, an AAC tool that generates sentence suggestions by drawing on users' personal memory records. By incorporating topic preference and interpersonal closeness, the system reuses past experience and tailors suggestions to different social contexts and conversation partners. SocializeChat not only leverages past experiences to support interaction, but also treats conversations as opportunities to create new memories, fostering a dynamic cycle between memory and communication. A user study shows its potential to enhance the inclusivity and relevance of AAC-supported social interaction.

cs.HC↗

arXiv2025

Split-Fuse-Transport: Annotation-Free Saliency via Dual Clustering and Optimal Transport Alignment

Salient object detection (SOD) aims to segment visually prominent regions in images and serves as a foundational task for various computer vision applications. We posit that SOD can now reach near-supervised accuracy without a single pixel-level label, but only when reliable pseudo-masks are available. We revisit the prototype-based line of work and make two key observations. First, boundary pixels and interior pixels obey markedly different geometry; second, the global consistency enforced by optimal transport (OT) is underutilized if prototype quality is weak. To address this, we introduce POTNet, an adaptation of Prototypical Optimal Transport that replaces POT's single k-means step with an entropy-guided dual-clustering head: high-entropy pixels are organized by spectral clustering, low-entropy pixels by k-means, and the two prototype sets are subsequently aligned by OT. This split-fuse-transport design yields sharper, part-aware pseudo-masks in a single forward pass, without handcrafted priors. Those masks supervise a standard MaskFormer-style encoder-decoder, giving rise to AutoSOD, an end-to-end unsupervised SOD pipeline that eliminates SelfMask's offline voting yet improves both accuracy and training efficiency. Extensive experiments on five benchmarks show that AutoSOD outperforms unsupervised methods by up to 26% and weakly supervised methods by up to 36% in F-measure, further narrowing the gap to fully supervised models.

cs.CV↗

arXiv2025

2D_3D Feature Fusion via Cross-Modal Latent Synthesis and Attention Guided Restoration for Industrial Anomaly Detection

Industrial anomaly detection (IAD) increasingly benefits from integrating 2D and 3D data, but robust cross-modal fusion remains challenging. We propose a novel unsupervised framework, Multi-Modal Attention-Driven Fusion Restoration (MAFR), which synthesises a unified latent space from RGB images and point clouds using a shared fusion encoder, followed by attention-guided, modality-specific decoders. Anomalies are localised by measuring reconstruction errors between input features and their restored counterparts. Evaluations on the MVTec 3D-AD and Eyecandies benchmarks demonstrate that MAFR achieves state-of-the-art results, with a mean I-AUROC of 0.972 and 0.901, respectively. The framework also exhibits strong performance in few-shot learning settings, and ablation studies confirm the critical roles of the fusion architecture and composite loss. MAFR offers a principled approach for fusing visual and geometric information, advancing the robustness and accuracy of industrial anomaly detection. Code is available at https://github.com/adabrh/MAFR

cs.CV↗

arXiv2025

Hypergraph Contrastive Sensor Fusion for Multimodal Fault Diagnosis in Induction Motors

Reliable induction motor (IM) fault diagnosis is vital for industrial safety and operational continuity, mitigating costly unplanned downtime. Conventional approaches often struggle to capture complex multimodal signal relationships, are constrained to unimodal data or single fault types, and exhibit performance degradation under noisy or cross-domain conditions. This paper proposes the Multimodal Hypergraph Contrastive Attention Network (MM-HCAN), a unified framework for robust fault diagnosis. To the best of our knowledge, MM-HCAN is the first to integrate contrastive learning within a hypergraph topology specifically designed for multimodal sensor fusion, enabling the joint modelling of intra- and inter-modal dependencies and enhancing generalisation beyond Euclidean embedding spaces. The model facilitates simultaneous diagnosis of bearing, stator, and rotor faults, addressing the engineering need for consolidated di- agnostic capabilities. Evaluated on three real-world benchmarks, MM-HCAN achieves up to 99.82% accuracy with strong cross-domain generalisation and resilience to noise, demonstrating its suitability for real-world deployment. An ablation study validates the contribution of each component. MM-HCAN provides a scalable and robust solution for comprehensive multi-fault diagnosis, supporting predictive maintenance and extended asset longevity in industrial environments.

cs.AI↗

arXiv2025

Direction-aware multi-scale gradient loss for infrared and visible image fusion

Infrared and visible image fusion aims to integrate complementary information from co-registered source images to produce a single, informative result. Most learning-based approaches train with a combination of structural similarity loss, intensity reconstruction loss, and a gradient-magnitude term. However, collapsing gradients to their magnitude removes directional information, yielding ambiguous supervision and suboptimal edge fidelity. We introduce a direction-aware, multi-scale gradient loss that supervises horizontal and vertical components separately and preserves their sign across scales. This axis-wise, sign-preserving objective provides clear directional guidance at both fine and coarse resolutions, promoting sharper, better-aligned edges and richer texture preservation without changing model architectures or training protocols. Experiments on open-source model and multiple public benchmarks demonstrate effectiveness of our approach.

cs.CV↗

arXiv2025

Well-Posedness of the Cauchy Problem for First-order Quasilinear Equations with Non-Lipschitz Source Terms and Its Applications

We are concerned with the well-posedness of the Cauchy problem for the first-order quasilinear equations with non-Lipschitz source terms and the global structures of the multi-dimensional Riemann solutions. For such quasilinear equations with initial data in $L^\infty$, when the source term $g(t, x, u)$ is only right-Lipschitz (not necessarily left-Lipschitz) in $u$, we first prove that the Kruzkov entropy condition is sufficient to guarantee the well-posdeness of entropy solutions. Next, we analyze the structures of global multi-dimensional Riemann solutions for scalar conservation laws with non-Lipschitz source terms, where the Riemann-type initial data consist of two different constant states separated by a smooth hypersurface. More precisely, we construct the global multidimensional Riemann solutions with non-selfsimilar structures, including nonselfsimilar shock waves and nonselfsimilar rarefaction waves, and prove that these two kinds of basic waves can be expressed via the implicit functions of functional equation determined by the initial discontinuity, the flux functions, and the non-Lipschitz source term. Moreover, we discover two new phenomena: (i) such kinds of basic waves can disappear in a finite time and (ii) the new-type rarefaction wave can contain some weak discontinuities in its interior. These behaviors are in stark contrast to the case of the Lipschitz source term, where these two kinds of basic waves persist globally and the rarefaction waves remain smooth in the interior. Finally, we provide two examples to respectively demonstrate the uniqueness of Riemann solutions in the case of the source term being non-Lipschitz from left (necessarily right-Lipschitz), and the non-uniqueness of Riemann solutions in the case of the source term being non-Lipschitz from right.

math.AP↗

arXiv2025

ProbRadarM3F: mmWave Radar based Human Skeletal Pose Estimation with Probability Map Guided Multi-Format Feature Fusion

Millimeter wave (mmWave) radar is a non-intrusive privacy and relatively convenient and inexpensive device, which has been demonstrated to be applicable in place of RGB cameras in human indoor pose estimation tasks. However, mmWave radar relies on the collection of reflected signals from the target, and the radar signals containing information is difficult to be fully applied. This has been a long-standing hindrance to the improvement of pose estimation accuracy. To address this major challenge, this paper introduces a probability map guided multi-format feature fusion model, ProbRadarM3F. This is a novel radar feature extraction framework using a traditional FFT method in parallel with a probability map based positional encoding method. ProbRadarM3F fuses the traditional heatmap features and the positional features, then effectively achieves the estimation of 14 keypoints of the human body. Experimental evaluation on the HuPR dataset proves the effectiveness of the model proposed in this paper, outperforming other methods experimented on this dataset with an AP of 69.9 %. The emphasis of our study is focusing on the position information that is not exploited before in radar singal. This provides direction to investigate other potential non-redundant information from mmWave rader.

cs.CV↗

arXiv2025

Exploring Micro Accidents and Driver Responses in Automated Driving: Insights from Real-world Videos

Automated driving in level 3 autonomy has been adopted by multiple companies such as Tesla and BMW, alleviating the burden on drivers while unveiling new complexities. This article focused on the under-explored territory of micro accidents during automated driving, characterized as not fatal but abnormal aberrations such as abrupt deceleration and snake driving. These micro accidents are basic yet pervasive events that might results in more severe accidents. Through collecting a comprehensive dataset of user generated video recording such micro accidents in natural driving scenarios, this article locates key variables pertaining to environments and autonomous agents using machine learning methods. Subsequently, crowdsourcing method provides insights into human risk perceptions and reactions to these micro accidents. This article thus describes features of safety critical scenarios other than crashes and fatal accidents, informing and potentially advancing the design of automated driving systems.

cs.HC↗

arXiv2025

Hand by Hand: LLM Driving EMS Assistant for Operational Skill Learning

Operational skill learning, inherently physical and reliant on hands-on practice and kinesthetic feedback, has yet to be effectively replicated in large language model (LLM)-supported training. Current LLM training assistants primarily generate customized textual feedback, neglecting the crucial kinesthetic modality. This gap derives from the textual and uncertain nature of LLMs, compounded by concerns on user acceptance of LLM driven body control. To bridge this gap and realize the potential of collaborative human-LLM action, this work explores human experience of LLM driven kinesthetic assistance. Specifically, we introduced an "Align-Analyze-Adjust" strategy and developed FlightAxis, a tool that integrates LLM with Electrical Muscle Stimulation (EMS) for flight skill acquisition, a representative operational skill domain. FlightAxis learns flight skills from manuals and guides forearm movements during simulated flight tasks. Our results demonstrate high user acceptance of LLM-mediated body control and significantly reduced task completion times. Crucially, trainees reported that this kinesthetic assistance enhanced their awareness of operation flaws and fostered increased engagement in the training process, rather than relieving perceived load. This work demonstrated the potential of kinesthetic LLM training in operational skill acquisition.

cs.HC↗