arXiv subjects

Hua Wang

Publications and source records attributed to Hua Wang.

At least 55 records · Page 3Linked to original sources

arXiv2026

Time-TK: A Multi-Offset Temporal Interaction Framework Combining Transformer and Kolmogorov-Arnold Networks for Time Series Forecasting

Time series forecasting is crucial for the World Wide Web and represents a core technical challenge in ensuring the stable and efficient operation of modern web services, such as intelligent transportation and website throughput. However, we have found that existing methods typically employ a strategy of embedding each time step as an independent token. This paradigm introduces a fundamental information bottleneck when processing long sequences, the root cause of which is that independent token embedding destroys a crucial structure within the sequence - what we term as multi-offset temporal correlation. This refers to the fine-grained dependencies embedded within the sequence that span across different time steps, which is especially prevalent in regular Web data. To fundamentally address this issue, we propose a new perspective on time series embedding. We provide an upper bound on the approximate reconstruction performance of token embedding, which guides our design of a concise yet effective Multi-Offset Time Embedding method to mitigate the performance degradation caused by standard token embedding. Furthermore, our MOTE can be integrated into various existing models and serve as a universal building block. Based on this paradigm, we further design a novel forecasting architecture named Time-TK. This architecture first utilizes a Multi-Offset Interactive KAN to learn and represent specific temporal patterns among multiple offset sub-sequences. Subsequently, it employs an efficient Multi-Offset Temporal Interaction mechanism to effectively capture the complex dependencies between these sub-sequences, achieving global information integration. Extensive experiments on 14 real-world benchmark datasets, covering domains such as traffic flow and BTC/USDT throughput, demonstrate that Time-TK significantly outperforms all baseline models, achieving state-of-the-art forecasting accuracy.

cs.LG↗

arXiv2026

Electrical Regulation of Transverse Spin Currents in Unconventional Magnetic Ferroeletrics

We identify hexagonal YMnO$_3$ as a material realization of the elusive $β$-phase of unconventional magnetism, a noncollinear, noncoplanar antiferromagnetic state defined by intrinsic spin-momentum locking and a topological spin texture. First-principle calculations reveal that this unique electronic structure enables a perpendicular electric field to generate a transverse pure spin current, a response that occurs without requiring relativistic spin-orbit coupling. Symmetry analysis demonstrates that this spin current is intimately related to the material's ferroelectric polarization that breaks the inversion symmetry and is rigorously forbidden at domain walls where electrical polarization vanishes. This provides a blueprint for a non-volatile transistor where a gate voltage switches the spin current conductivity by controlling domain wall density, enabling all-electrical control for energy-efficient antiferromagnetic spintronics.

cond-mat.mtrl-sci↗

arXiv2025

From Trial to Deployment: A SEM Analysis of Traveler Adoptions to Fully Operational Autonomous Taxis

Autonomous taxi services represent a transformative advancement in urban mobility, offering safety, efficiency, and round-the-clock operations. While existing literature has explored user acceptance of autonomous taxis through stated preference experiments and hypothetical scenarios, few studies have investigated actual user behavior based on operational AV services. This study addresses that gap by leveraging survey data from Wuhan, China, where Baidu's Apollo Robotaxi service operates at scale. We design a realistic survey incorporating actual service attributes and collect 336 valid responses from actual users. Using Structural Equation Modeling, we identify six latent psychological constructs, namely Trust \& Policy Support, Cost Sensitivity, Performance, Behavioral Intention, Lifestyle, and Education. Their influences on adoption behavior, measured by the selection frequency of autonomous taxis in ten scenarios, are examined and interpreted. Results show that Cost Sensitivity and Behavioral Intention are the strongest positive predictors of adoption, while other latent constructs play more nuanced roles. The model demonstrates strong goodness-of-fit across multiple indices. Our findings offer empirical evidence to support policymaking, fare design, and public outreach strategies for scaling autonomous taxis deployments in real-world urban settings.

cs.LG↗

arXiv2025

IdealTSF: Can Non-Ideal Data Contribute to Enhancing the Performance of Time Series Forecasting Models?

Deep learning has shown strong performance in time series forecasting tasks. However, issues such as missing values and anomalies in sequential data hinder its further development in prediction tasks. Previous research has primarily focused on extracting feature information from sequence data or addressing these suboptimal data as positive samples for knowledge transfer. A more effective approach would be to leverage these non-ideal negative samples to enhance event prediction. In response, this study highlights the advantages of non-ideal negative samples and proposes the IdealTSF framework, which integrates both ideal positive and negative samples for time series forecasting. IdealTSF consists of three progressive steps: pretraining, training, and optimization. It first pretrains the model by extracting knowledge from negative sample data, then transforms the sequence data into ideal positive samples during training. Additionally, a negative optimization mechanism with adversarial disturbances is applied. Extensive experiments demonstrate that negative sample data unlocks significant potential within the basic attention architecture for time series forecasting. Therefore, IdealTSF is particularly well-suited for applications with noisy samples or low-quality data.

cs.LG↗

arXiv2025

Effective Attention-Guided Multi-Scale Medical Network for Skin Lesion Segmentation

In the field of healthcare, precise skin lesion segmentation is crucial for the early detection and accurate diagnosis of skin diseases. Despite significant advances in deep learning for image processing, existing methods have yet to effectively address the challenges of irregular lesion shapes and low contrast. To address these issues, this paper proposes an innovative encoder-decoder network architecture based on multi-scale residual structures, capable of extracting rich feature information from different receptive fields to effectively identify lesion areas. By introducing a Multi-Resolution Multi-Channel Fusion (MRCF) module, our method captures cross-scale features, enhancing the clarity and accuracy of the extracted information. Furthermore, we propose a Cross-Mix Attention Module (CMAM), which redefines the attention scope and dynamically calculates weights across multiple contexts, thus improving the flexibility and depth of feature capture and enabling deeper exploration of subtle features. To overcome the information loss caused by skip connections in traditional U-Net, an External Attention Bridge (EAB) is introduced, facilitating the effective utilization of information in the decoder and compensating for the loss during upsampling. Extensive experimental evaluations on several skin lesion segmentation datasets demonstrate that the proposed model significantly outperforms existing transformer and convolutional neural network-based models, showcasing exceptional segmentation accuracy and robustness.

cs.CV↗

arXiv2025

Decoding with Structured Awareness: Integrating Directional, Frequency-Spatial, and Structural Attention for Medical Image Segmentation

To address the limitations of Transformer decoders in capturing edge details, recognizing local textures and modeling spatial continuity, this paper proposes a novel decoder framework specifically designed for medical image segmentation, comprising three core modules. First, the Adaptive Cross-Fusion Attention (ACFA) module integrates channel feature enhancement with spatial attention mechanisms and introduces learnable guidance in three directions (planar, horizontal, and vertical) to enhance responsiveness to key regions and structural orientations. Second, the Triple Feature Fusion Attention (TFFA) module fuses features from Spatial, Fourier and Wavelet domains, achieving joint frequency-spatial representation that strengthens global dependency and structural modeling while preserving local information such as edges and textures, making it particularly effective in complex and blurred boundary scenarios. Finally, the Structural-aware Multi-scale Masking Module (SMMM) optimizes the skip connections between encoder and decoder by leveraging multi-scale context and structural saliency filtering, effectively reducing feature redundancy and improving semantic interaction quality. Working synergistically, these modules not only address the shortcomings of traditional decoders but also significantly enhance performance in high-precision tasks such as tumor segmentation and organ boundary extraction, improving both segmentation accuracy and model generalization. Experimental results demonstrate that this framework provides an efficient and practical solution for medical image segmentation.

cs.CV↗

arXiv2025

Distinguish the Orientation of Sliding Ferroelectricity by Second-Harmonic Generation

As the emerging ferroelectric (FE) materials, the ultrathin two-dimensional (2D) sliding ferroelectrics without phase-matching bottleneck, usually exhibit the pronounced second harmonic generation (SHG) responses. Despite the structural polarity of sliding ferroelectrics can be precisely detected via SHG characterizations, distinguishing the orientations of sliding ferroelectricity based on SHG responses has rarely been realized, as SHG intensities for upward and downward polarization states are supposed to be same. In current work, combining computational simulations and experimental characterizations, the orientation of sliding ferroelectricity is demonstrated to be readily distinguishable via SHG responses in 2D SnP2S6 (SnP2Se6), a new sliding FE material. Specifically, owing to the unique symmetry operation within FE-SnP2S6 (SnP2Se6), the intersection between \c{hi}xxx and \c{hi}yyy SHG susceptibility coefficients with opposite signs leads to the effective rotation of SHG polar directions upon switching of sliding ferroelectricity. Moreover, the remarkable dependence of SHG polar directions on the orientation of sliding ferroelectricity is further validated by experimental characterizations performed on SnP2S6 crystal in a single FE domain structural form. This work opens up the avenue for in-situ detecting the ferroelectricity orientation of 2D sliding ferroelectrics based on SHG nonlinear optical responses, and also demonstrates the controllable optical nonlinearly for new "slidetronics" applications.

cond-mat.mtrl-sci↗

arXiv2025

Combinatorics of positional colored compositions

We consider colored compositions where only some parts are allowed different colors, depending on their locations in the composition. The counting sequences are obtained through generating functions. Connections to many other combinatorial objects are discussed, with combinatorial arguments provided and generalized for these observations.

math.CO↗

arXiv2025

Some interpolation inequalities in Lorentz, Morrey and BMO spaces

In this paper, the author establishes some interpolation results between Lorentz, Morrey and BMO spaces. Let $1<p<\infty$ and $p\leq r\leq\infty$. It is proved that the space $L^{p,r}(\mathbb R^n)\cap\mathrm{BMO}(\mathbb R^n)$ is continuously embedded into $L^q(\mathbb R^n)$ for all $q$ with $p<q<\infty$, where $L^{p,r}(\mathbb R^n)$ denotes the classical Lorentz space with indices $p$ and $r$. Moreover, the author establishes the optimal growth rate of this embedding constant as $q\to\infty$. Based on Morrey spaces, the author introduces a new family of function spaces called Lorentz--Morrey spaces $LM^{p,r;κ}(\mathbb R^n)$ with indices $p$, $r$ and $κ$, and then shows that the space $LM^{p,r;κ}(\mathbb R^n)\cap \mathrm{BMO}(\mathbb R^n)$ is continuously embedded into $L^{q;κ}(\mathbb R^n)$ for all $q$ with $p<q<\infty$, where $1<p<\infty$, $p\leq r\leq\infty$ and $0<κ<1$. Furthermore, the asymptotically optimal growth order of this embedding constant is also established. As an application of the above interpolation results, some new bilinear estimates in the setting of Lorentz and Lorentz--Morrey spaces are also obtained, which can be used in the study of the global existence and regularity of weak solutions to elliptic and parabolic partial differential equations of the second order.

math.CA↗

arXiv2025

Extremal graphs for the maximum $A_α$-spectral radius of graphs with order and size

In 1986, Brualdi and Solheid firstly proposed the problem of determining the maximum spectral radius of graphs in the set $\mathcal{H}_{n,m}$ consisting of all simple connected graphs with $n$ vertices and $m$ edges, which is a very tough problem and far from resolved. The $A_α$-spectral radius of a simple graph of order $n$, denoted by $ρ_α(G)$, is the largest eigenvalue of the matrix $A_α(G)$ which is defined as $αD(G)+(1-α)A(G)$ for $0\le α< 1$, where $D(G)$ and $A(G)$ are the degree diagonal and adjacency matrices of $G$, respectively. In this paper, if $r$ is a positive integer, $n>30r$ and $n-1\leq m \le rn-\frac{r(r+1)}{2}$, we characterize all extremal graphs which have the maximum $A_α$-spectral radius of graphs in the set $\mathcal{H}_{n,m}$. Moreover, the problem on $A_α$-spectral radius proposed by Chang and Tam [T.-C. Chang and B.-T. Tam, Graphs of fixed order and size with maximal $A_α$-index. Linear Algebra Appl. 673 (2023), 69-100] has been solved.

math.CO↗

arXiv2025

Some Examples of Bicrossed Products with the Rapid Decay Property

We consider bicrossed products obtained by twisting compact semi-direct products by a suitable finite subgroup. Under some restriction, we give a practical criterion for the discrete dual of such bicrossed products to have the rapid decay property (property (RD)). Using this theory, we construct some examples of discrete quantum groups with (RD) but do not grow polynomially. Further examples that do not satisfy the hypothesis of our main result are also constructed.

math.OA↗

arXiv2025

Electronic-Photonic Interface for Multiuser Optical Wireless Communication

We demonstrate an electronic-photonic (EP) interface for multiuser optical wireless communication (OWC), consisting of a multibeam optical phased array (MBOPA) along with co-integrated electro-optic (EO) modulators and high-speed CMOS drivers. The MBOPA leverages a path-length difference in the optical phased array (OPA) along with wavelength-division multiplexing technology for spatial carrier aggregation and multiplexing. To generate two and four pulsed amplitude modulation signals, and transmit them to multiple users, we employ an optical digital-to-analog converter technique by using two traveling-wave electrode Mach-Zehnder modulators, which are monolithically integrated with high-speed, wide-output-swing CMOS drivers. The MBOPA and monolithic EO modulator are implemented by silica wafer through planar lightwave circuit fabrication process and a 45-nm monolithic silicon photonics technology, respectively. We measured and analyzed two-channel parallel communication at a data rate of 54 Gbps per user over the wireless distance of 1 m. To the best of our knowledge, this is the first system level demonstration of the multi-user OWC using the in-house-designed photonic and monolithically integrated chips. Finally, we suggest best modulation format for different data rate and the number of multibeams, considering effects of the proposed OPA and the monolithic modulator.

physics.optics↗

arXiv2025

Towards Spectrally Efficient and Physically Reconfigurable Architectures for Multibeam-Waveform Co-Design in Joint Communication and Sensing

Joint Communication and Sensing (JCAS) platforms are emerging as a foundation of next-generation mmWave (MMW) and sub-THz systems, enabling both high-throughput data transfer and angular localization within a shared signal path. This paper investigates multibeam architectures for JCAS that simultaneously optimize waveform shaping and beamforming across the time, frequency, code, and direct analog/ radio frequency (RF) domains. The paper compares Orthogonal Frequency-Division Multiplexing (OFDM), Frequency Modulated Arrays (FMA), Time-Modulated Arrays (TMA), direct RF/MMW modulation, and Code-Division Multiple Access (CDMA)-based systems with respect to spectral efficiency, beam orthogonality, latency, and Angle-of-Arrival (AoA) estimation accuracy. The results highlight architecture-specific tradeoffs among beam agility, efficiency, accuracy and resolution, and complexity. It also provides a framework for selecting JCAS front ends optimized for power, latency, inter-beam and multi-user interference, and rapid system reconfiguration

eess.SP↗

arXiv2025

A Nonconforming Finite Element Method for Elliptic Interface Problems on Locally Anisotropic Meshes

We propose a new nonconforming $P_1$ finite element method for elliptic interface problems. The method is constructed on a locally anisotropic mixed mesh, which is generated by fitting the interface through a simple connection of intersection points on an interface-unfitted background mesh, as introduced in \cite{Hu2021optimal}. We first establish interpolation error estimates on quadrilateral elements satisfying the regular decomposition property (RDP). Building on this, the main contribution of this work is a novel consistency error analysis for nonconforming elements, which removes the quasi-regularity assumption commonly required in existing approaches. Numerical results confirm the theoretical convergence rates and demonstrate the robustness and accuracy of the proposed method.

math.NA↗

arXiv2025

Homogeneous fractional integral operators on weighted Lebesgue, Morrey and Campanato spaces

Let $0<α<n$ and $T_{Ω,α}$ be the homogeneous fractional integral operator which is defined by \begin{equation*} T_{Ω,α}f(x):=\int_{\mathbb R^n}\frac{Ω(x-y)}{|x-y|^{n-α}}f(y)\,dy, \end{equation*} where $Ω$ is homogeneous of degree zero in $\mathbb R^n$ for $n\geq2$, and is integrable on the unit sphere $\mathbb{S}^{n-1}$. In this paper we study boundedness properties of the homogeneous fractional integral operator $T_{Ω,α}$ acting on weighted Lebesgue and Morrey spaces. Under certain Dini-type smoothness condition on $Ω$, we prove that $T_{Ω,α}$ is bounded from $L^{p}(ω^p)$ to $\mathcal{C}^{γ,\ell}_ω$(a class of Campanato spaces) for appropriate indices, when $n/α<p<\infty$. Moreover, we prove that if $Ω$ satisfies certain Dini-type smoothness condition on $\mathbb{S}^{n-1}$, then $T_{Ω,α}$ is bounded from $\mathcal{M}^{p,κ}(ω^p,ω^q)$ to $\mathcal{C}^{γ,\ell}(ω^q)$(weighted Campanato spaces) for appropriate indices, when $p/q<κ<1$.

math.CA↗

arXiv2025

LiteGS: A High-performance Framework to Train 3DGS in Subminutes via System and Algorithm Codesign

3D Gaussian Splatting (3DGS) has emerged as promising alternative in 3D representation. However, it still suffers from high training cost. This paper introduces LiteGS, a high performance framework that systematically optimizes the 3DGS training pipeline from multiple aspects. At the low-level computation layer, we design a ``warp-based raster'' associated with two hardware-aware optimizations to significantly reduce gradient reduction overhead. At the mid-level data management layer, we introduce dynamic spatial sorting based on Morton coding to enable a performant ``Cluster-Cull-Compact'' pipeline and improve data locality, therefore reducing cache misses. At the top-level algorithm layer, we establish a new robust densification criterion based on the variance of the opacity gradient, paired with a more stable opacity control mechanism, to achieve more precise parameter growth. Experimental results demonstrate that LiteGS accelerates the original 3DGS training by up to 13.4x with comparable or superior quality and surpasses the current SOTA in lightweight models by up to 1.4x speedup. For high-quality reconstruction tasks, LiteGS sets a new accuracy record and decreases the training time by an order of magnitude.

cs.CV↗

arXiv2025

DanceText: A Training-Free Layered Framework for Controllable Multilingual Text Transformation in Images

We present DanceText, a training-free framework for multilingual text editing in images, designed to support complex geometric transformations and achieve seamless foreground-background integration. While diffusion-based generative models have shown promise in text-guided image synthesis, they often lack controllability and fail to preserve layout consistency under non-trivial manipulations such as rotation, translation, scaling, and warping. To address these limitations, DanceText introduces a layered editing strategy that separates text from the background, allowing geometric transformations to be performed in a modular and controllable manner. A depth-aware module is further proposed to align appearance and perspective between the transformed text and the reconstructed background, enhancing photorealism and spatial consistency. Importantly, DanceText adopts a fully training-free design by integrating pretrained modules, allowing flexible deployment without task-specific fine-tuning. Extensive experiments on the AnyWord-3M benchmark demonstrate that our method achieves superior performance in visual quality, especially under large-scale and complex transformation scenarios. Code is avaible at https://github.com/YuZhenyuLindy/DanceText.git.

cs.CV↗

arXiv2025

ABG-NAS: Adaptive Bayesian Genetic Neural Architecture Search for Graph Representation Learning

Effective and efficient graph representation learning is essential for enabling critical downstream tasks, such as node classification, link prediction, and subgraph search. However, existing graph neural network (GNN) architectures often struggle to adapt to diverse and complex graph structures, limiting their ability to produce structure-aware and task-discriminative representations. To address this challenge, we propose ABG-NAS, a novel framework for automated graph neural network architecture search tailored for efficient graph representation learning. ABG-NAS encompasses three key components: a Comprehensive Architecture Search Space (CASS), an Adaptive Genetic Optimization Strategy (AGOS), and a Bayesian-Guided Tuning Module (BGTM). CASS systematically explores diverse propagation (P) and transformation (T) operations, enabling the discovery of GNN architectures capable of capturing intricate graph characteristics. AGOS dynamically balances exploration and exploitation, ensuring search efficiency and preserving solution diversity. BGTM further optimizes hyperparameters periodically, enhancing the scalability and robustness of the resulting architectures. Empirical evaluations on benchmark datasets (Cora, PubMed, Citeseer, and CoraFull) demonstrate that ABG-NAS consistently outperforms both manually designed GNNs and state-of-the-art neural architecture search (NAS) methods. These results highlight the potential of ABG-NAS to advance graph representation learning by providing scalable and adaptive solutions for diverse graph structures. Our code is publicly available at https://github.com/sserranw/ABG-NAS.

cs.LG↗