arXiv subjects

Shuang Wu

Publications and source records attributed to Shuang Wu.

At least 55 records · Page 3Linked to original sources

arXiv2025

Sync-TVA: A Graph-Attention Framework for Multimodal Emotion Recognition with Cross-Modal Fusion

Multimodal emotion recognition (MER) is crucial for enabling emotionally intelligent systems that perceive and respond to human emotions. However, existing methods suffer from limited cross-modal interaction and imbalanced contributions across modalities. To address these issues, we propose Sync-TVA, an end-to-end graph-attention framework featuring modality-specific dynamic enhancement and structured cross-modal fusion. Our design incorporates a dynamic enhancement module for each modality and constructs heterogeneous cross-modal graphs to model semantic relations across text, audio, and visual features. A cross-attention fusion mechanism further aligns multimodal cues for robust emotion inference. Experiments on MELD and IEMOCAP demonstrate consistent improvements over state-of-the-art models in both accuracy and weighted F1 score, especially under class-imbalanced conditions.

cs.MM↗

arXiv2025

Fast and Provable Hankel Tensor Completion for Multi-measurement Spectral Compressed Sensing

In this paper, we introduce a novel low-rank Hankel tensor completion approach to address the problem of multi-measurement spectral compressed sensing. By lifting the multiple signals to a Hankel tensor, we reformulate this problem into a low-rank Hankel tensor completion task, exploiting the spectral sparsity via the low multilinear rankness of the tensor. Furthermore, we design a scaled gradient descent algorithm for Hankel tensor completion (ScalHT), which integrates the low-rank Tucker decomposition with the Hankel structure. Crucially, we derive novel fast computational formulations that leverage the interaction between these two structures, achieving up to an $O(\min\{s,n\})$-fold improvement in storage and computational efficiency compared to the existing algorithms, where $n$ is the length of signal, $s$ is the number of measurement vectors. Beyond its practical efficiency, ScalHT is backed by rigorous theoretical guarantees: we establish both recovery and linear convergence guarantees, which, to the best of our knowledge, are the first of their kind for low-rank Hankel tensor completion. Numerical simulations show that our method exhibits significantly lower computational and storage costs while delivering superior recovery performance compared to prior arts.

cs.IT↗

arXiv2025

Quantized Topological States and Parity Anomaly in Intrinsic Quantum Anomalous Hall Insulator MnBi2Te4

When thinned down to just a few atomic layers, the layered magnetic topological insulator MnBi2Te4 offers an exceptional platform for exploring a wide range of topological phenomena. In this work, we overcome longstanding challenges in synthesizing high-purity MnBi2Te4 crystals and report the observation of a myriad of quantized topological states in high-quality five-septuple-layer (5-SL) samples under magnetic fields up to 45 Tesla. We show that the nontrivial topology of 5-SL MnBi2Te4, in the presence of Landau quantization, is governed by a generalized topological index rooted in the parity anomaly of Dirac fermions in (2+1) dimensions. The anomaly manifests as an anomalous Landau level, giving rise to gate-tunable helical edge transport. Our results establish high-quality MnBi2Te4 as a robust platform for exploring emergent topological states and for advancing novel quantum device applications.

cond-mat.mes-hall↗

arXiv2025

On-chip photon entanglement-assisted topology loading and transfer

Topological protection offers a robust solution to the challenges of noise and loss in physical systems. By integrating topological physics into optics, loading and encoding quantum states into topological invariants can provide resilience to information systems in the face of environmental disruptions. Here, we demonstrate on-chip loading and entanglement-assisted transfer of photon topology, where the topological structure is coherently encoded in a single-photon spin-textured quantum state, which can be transferred, through entanglement distribution, into a non-local quantum-correlated topology shared between two entangled photons. Throughout the transfer process, the topology remains protected against substantial background noise as well as isotropic and anisotropic disturbances, while quantum correlations persist. Our framework for loading and transferring topology is compatible with quantum teleportation when ancillary photons are introduced, thereby promising the development of distributed quantum systems with inherently secure and protected information channels. This approach serves as a step toward building robust quantum interconnects and advancing distributed quantum information technology mediated by topology.

quant-ph↗

arXiv2025

Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

Generating high-resolution 3D shapes using volumetric representations such as Signed Distance Functions (SDFs) presents substantial computational and memory challenges. We introduce Direct3D-S2, a scalable 3D generation framework based on sparse volumes that achieves superior output quality with dramatically reduced training costs. Our key innovation is the Spatial Sparse Attention (SSA) mechanism, which greatly enhances the efficiency of Diffusion Transformer (DiT) computations on sparse volumetric data. SSA allows the model to effectively process large token sets within sparse volumes, substantially reducing computational overhead and achieving a 3.9x speedup in the forward pass and a 9.6x speedup in the backward pass. Our framework also includes a variational autoencoder (VAE) that maintains a consistent sparse volumetric format across input, latent, and output stages. Compared to previous methods with heterogeneous representations in 3D VAE, this unified design significantly improves training efficiency and stability. Our model is trained on public available datasets, and experiments demonstrate that Direct3D-S2 not only surpasses state-of-the-art methods in generation quality and efficiency, but also enables training at 1024 resolution using only 8 GPUs, a task typically requiring at least 32 GPUs for volumetric representations at 256 resolution, thus making gigascale 3D generation both practical and accessible. Project page: https://www.neural4d.com/research/direct3d-s2.

cs.CV↗

arXiv2025

LengthLogD: A Length-Stratified Ensemble Framework for Enhanced Peptide Lipophilicity Prediction via Multi-Scale Feature Integration

Peptide compounds demonstrate considerable potential as therapeutic agents due to their high target affinity and low toxicity, yet their drug development is constrained by their low membrane permeability. Molecular weight and peptide length have significant effects on the logD of peptides, which in turn influences their ability to cross biological membranes. However, accurate prediction of peptide logD remains challenging due to the complex interplay between sequence, structure, and ionization states. This study introduces LengthLogD, a predictive framework that establishes specialized models through molecular length stratification while innovatively integrating multi-scale molecular representations. We constructed feature spaces across three hierarchical levels: atomic (10 molecular descriptors), structural (1024-bit Morgan fingerprints), and topological (3 graph-based features including Wiener index), optimized through stratified ensemble learning. An adaptive weight allocation mechanism specifically developed for long peptides significantly enhances model generalizability. Experimental results demonstrate superior performance across all categories: short peptides (R^2=0.855), medium peptides (R^2=0.816), and long peptides (R^2=0.882), with a 34.7% reduction in prediction error for long peptides compared to conventional single-model approaches. Ablation studies confirm: 1) The length-stratified strategy contributes 41.2% to performance improvement; 2) Topological features account for 28.5% of predictive importance. Compared to state-of-the-art models, our method maintains short peptide prediction accuracy while achieving a 25.7% increase in the coefficient of determination (R^2) for long peptides. This research provides a precise logD prediction tool for peptide drug development, particularly demonstrating unique value in optimizing long peptide lead compounds.

cs.LG↗

arXiv2025

Evaluating Menu OCR and Translation: A Benchmark for Aligning Human and Automated Evaluations in Large Vision-Language Models

The rapid advancement of large vision-language models (LVLMs) has significantly propelled applications in document understanding, particularly in optical character recognition (OCR) and multilingual translation. However, current evaluations of LVLMs, like the widely used OCRBench, mainly focus on verifying the correctness of their short-text responses and long-text responses with simple layout, while the evaluation of their ability to understand long texts with complex layout design is highly significant but largely overlooked. In this paper, we propose Menu OCR and Translation Benchmark (MOTBench), a specialized evaluation framework emphasizing the pivotal role of menu translation in cross-cultural communication. MOTBench requires LVLMs to accurately recognize and translate each dish, along with its price and unit items on a menu, providing a comprehensive assessment of their visual understanding and language processing capabilities. Our benchmark is comprised of a collection of Chinese and English menus, characterized by intricate layouts, a variety of fonts, and culturally specific elements across different languages, along with precise human annotations. Experiments show that our automatic evaluation results are highly consistent with professional human evaluation. We evaluate a range of publicly available state-of-the-art LVLMs, and through analyzing their output to identify the strengths and weaknesses in their performance, offering valuable insights to guide future advancements in LVLM development. MOTBench is available at https://github.com/gitwzl/MOTBench.

cs.LG↗

arXiv2025

Research of the Variational Shadow Quantum Circuit Based on the Whale Optimization Algorithm in Image Classification

In order to explore the possibility of cross-fertilization between quantum computing and neural networks as well as to improve the classification performance of quantum neural networks, this paper proposes an improved Variable Split Shadow Quantum Circuit (VSQC-WOA) model based on the Whale Optimization Algorithm. In this model, we design a strongly entangled local shadow circuit to achieve efficient characterization of global features through local shadow feature extraction and a sliding mechanism, which provides a rich quantum feature representation for the classification task. The gradient is then computed by the parameter-shifting method, and finally the features processed by the shadow circuit are passed to the classical fully connected neural network (FCNN) for processing and classification. The model also introduces the Whale Optimization Algorithm (WOA) to further optimize the weights and biases of the fully connected neural network, which improves the expressive power and classification accuracy of the model. In this paper, we firstly use different localized shadow circuit VSQC models to achieve the binary classification task on the MNIST dataset, and our design of strongly entangled shadow circuits performs the best in terms of classification accuracy. The VSQC-WOA model is then used to multi-classify the MNIST dataset (three classifications as an example), and the effectiveness of the proposed VSQC-WOA model as well as the robustness and generalization ability of the model are verified through various comparison experiments.

quant-ph↗

arXiv2025

Disentangling Complex Systems: IdopNetwork Meets GLMY Homology Theory

The study of complex systems has captured widespread attention in recent years, emphasizing the exploration of interactions and emergent properties among system units. Network analysis based on graph theory has emerged as a powerful approach for analyzing network topology and functions, making them widely adopted in complex systems. IdopNetwork is an advanced statistical physics framework that constructs the interaction within complex systems by integrating large-scale omics data. By combining GLMY theory, the structural characteristics of the network topology can be traced, providing deeper insights into the dynamic evolution of the network. This combination not only offers a novel perspective for dissecting the internal regulation of complex systems from a holistic standpoint but also provides significant support for applied fields such as data science, complex disease, and materials science.

stat.AP↗

arXiv2025

DIMT25@ICDAR2025: HW-TSC's End-to-End Document Image Machine Translation System Leveraging Large Vision-Language Model

This paper presents the technical solution proposed by Huawei Translation Service Center (HW-TSC) for the "End-to-End Document Image Machine Translation for Complex Layouts" competition at the 19th International Conference on Document Analysis and Recognition (DIMT25@ICDAR2025). Leveraging state-of-the-art open-source large vision-language model (LVLM), we introduce a training framework that combines multi-task learning with perceptual chain-of-thought to develop a comprehensive end-to-end document translation system. During the inference phase, we apply minimum Bayesian decoding and post-processing strategies to further enhance the system's translation capabilities. Our solution uniquely addresses both OCR-based and OCR-free document image translation tasks within a unified framework. This paper systematically details the training methods, inference strategies, LVLM base models, training data, experimental setups, and results, demonstrating an effective approach to document image machine translation.

cs.CV↗

arXiv2025

MindFlow: A Network Traffic Anomaly Detection Model Based on MindSpore

With the wide application of IoT and industrial IoT technologies, the network structure is becoming more and more complex, and the traffic scale is growing rapidly, which makes the traditional security protection mechanism face serious challenges in dealing with high-frequency, diversified, and stealthy cyber-attacks. To address this problem, this study proposes MindFlow, a multi-dimensional dynamic traffic prediction and anomaly detection system combining convolutional neural network (CNN) and bi-directional long and short-term memory network (BiLSTM) architectures based on the MindSpore framework, and conducts systematic experiments on the NF-BoT-IoT dataset. The experimental results show that the proposed model achieves 99% in key metrics such as accuracy, precision, recall and F1 score, effectively verifying its accuracy and robustness in network intrusion detection.

cs.CY↗

arXiv2025

Frequency-Aware Attention-LSTM for PM$_{2.5}$ Time Series Forecasting

To enhance the accuracy and robustness of PM$_{2.5}$ concentration forecasting, this paper introduces FALNet, a Frequency-Aware LSTM Network that integrates frequency-domain decomposition, temporal modeling, and attention-based refinement. The model first applies STL and FFT to extract trend, seasonal, and denoised residual components, effectively filtering out high-frequency noise. The filtered residuals are then fed into a stacked LSTM to capture long-term dependencies, followed by a multi-head attention mechanism that dynamically focuses on key time steps. Experiments conducted on real-world urban air quality datasets demonstrate that FALNet consistently outperforms conventional models across standard metrics such as MAE, RMSE, and $R^2$. The model shows strong adaptability in capturing sharp fluctuations during pollution peaks and non-stationary conditions. These results validate the effectiveness and generalizability of FALNet for real-time air pollution prediction, environmental risk assessment, and decision-making support.

cs.LG↗

arXiv2025

Research on CNN-BiLSTM Network Traffic Anomaly Detection Model Based on MindSpore

With the widespread adoption of the Internet of Things (IoT) and Industrial IoT (IIoT) technologies, network architectures have become increasingly complex, and the volume of traffic has grown substantially. This evolution poses significant challenges to traditional security mechanisms, particularly in detecting high-frequency, diverse, and highly covert network attacks. To address these challenges, this study proposes a novel network traffic anomaly detection model that integrates a Convolutional Neural Network (CNN) with a Bidirectional Long Short-Term Memory (BiLSTM) network, implemented on the MindSpore framework. Comprehensive experiments were conducted using the NF-BoT-IoT dataset. The results demonstrate that the proposed model achieves 99% across accuracy, precision, recall, and F1-score, indicating its strong performance and robustness in network intrusion detection tasks.

cs.CR↗

arXiv2025

Policy Optimization Algorithms in a Unified Framework

Policy optimization algorithms are crucial in many fields but challenging to grasp and implement, often due to complex calculations related to Markov decision processes and varying use of discount and average reward setups. This paper presents a unified framework that applies generalized ergodicity theory and perturbation analysis to clarify and enhance the application of these algorithms. Generalized ergodicity theory sheds light on the steady-state behavior of stochastic processes, aiding understanding of both discounted and average rewards. Perturbation analysis provides in-depth insights into the fundamental principles of policy optimization algorithms. We use this framework to identify common implementation errors and demonstrate the correct approaches. Through a case study on Linear Quadratic Regulator problems, we illustrate how slight variations in algorithm design affect implementation outcomes. We aim to make policy optimization algorithms more accessible and reduce their misuse in practice.

eess.SY↗

arXiv2025

Heavy fermions, mass renormalization and local moments in magic-angle twisted bilayer graphene via planar tunneling spectroscopy

Topological heavy fermion models[1-5] describe the flat bands in magic-angle twisted bilayer graphene (MATBG) as arising from the hybridization between localized flat-band orbitals (f-electrons) and nearly-free conduction bands (c-electrons). The interplay between these f-electrons and c-electrons is theorized to give rise to emergent phenomena, including unconventional superconductivity[6-8], non-Fermi liquid behavior[9-11], and topologically nontrivial phases[12-14]. However, the fundamental properties of f- and c-electrons, such as their respective heavy and light effective mass and their properties under strain, need experimental verification. Here we report on the electronic inverse compressibility, effective mass, and entropy of MATBG, obtained from planar tunneling spectroscopy. Our results include the observation of electron mass renormalization, found to be consistent with the topological heavy fermion model prediction of heavy charge-one excitations away from integer fillings. Importantly, we present entropic evidence for 4-fold and 8-fold degenerate isospin local moment states emerging at temperatures of 10K and 20K, respectively, consistent with the entropy of 8 heavy-fermions flavors energetically split by the sample strain.

cond-mat.mes-hall↗

arXiv2025

Cavity-enhanced solid-state nuclear spin gyroscope

Solid-state quantum sensors based on ensembles of nitrogen-vacancy (NV) centers in diamond have emerged as powerful tools for precise sensing applications. Nuclear spin sensors are particularly well-suited for applications requiring long coherence times, such as inertial sensing, but remain underexplored due to control complexity and limited optical readout efficiency. In this work, we propose cooperative cavity quantum electrodynamic (cQED) coupling to achieve efficient nuclear spin readout. Unlike previous cQED methods used to enhance electron spin readout, here we employ two-field interference in the NV hyperfine subspace to directly probe the nuclear spin transitions. We model the nuclear spin NV-cQED system (nNV-cQED) and observe several distinct regimes, including electromagnetically induced transparency, masing without inversion, and oscillatory behavior. We then evaluate the nNV-cQED system as an inertial sensor, indicating a rotation sensitivity improved by three orders of magnitude compared to previous solid-state spin demonstrations. Furthermore, we show that the NV electron spin can be simultaneously used as a comagnetometer, and the four crystallographic axes of NVs can be employed for vector resolution in a single nNV-cQED system. These results showcase the applications of two-field interference using the nNV-cQED platform, providing critical insights into the manipulation and control of quantum states in hybrid NV systems and unlocking new possibilities for high-performance quantum sensing.

quant-ph↗

arXiv2025

SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning

Spatial reasoning is an essential problem in embodied AI research. Efforts to enhance spatial reasoning abilities through supplementary spatial data and fine-tuning have proven limited and ineffective when addressing complex embodied tasks, largely due to their dependence on language-based outputs. While some approaches have introduced a point-based action space to mitigate this issue, they fall short in managing more intricate tasks within complex environments. This deficiency arises from their failure to fully exploit the inherent thinking and reasoning capabilities that are fundamental strengths of Vision-Language Models (VLMs). To address these limitations, we propose a novel approach named SpatialCoT, specifically designed to bolster the spatial reasoning capabilities of VLMs. Our approach comprises two stages: spatial coordinate bi-directional alignment, which aligns vision-language inputs with spatial coordinates, and chain-of-thought spatial grounding, which harnesses the reasoning capabilities of language models for advanced spatial reasoning. We evaluate SpatialCoT on challenging navigation and manipulation tasks, both in simulation and real-world settings. Experimental results demonstrate that our method significantly outperforms previous state-of-the-art approaches in both tasks.

cs.RO↗

arXiv2024

Vertically Graded Fe-Ni Alloys with Low Damping and a Sizeable Spin-Orbit Torque

Energy-efficient spintronic devices require a large spin-orbit torque (SOT) and low damping to excite magnetic precession. In conventional devices with heavy-metal/ferromagnet bilayers, reducing the ferromagnet thickness to $\sim$1 nm enhances the SOT but dramatically increases damping. Here, we investigate an alternative approach based on a 10 nm thick single-layer ferromagnet to attain both low damping and a sizable SOT. Instead of relying on a single interface, we continuously break the bulk inversion symmetry with a vertical compositional gradient of two ferromagnetic elements: Fe with low intrinsic damping and Ni with sizable spin-orbit coupling. We find low effective damping parameters of $α_\mathrm{eff} < 5\times10^{-3}$ in the FeNi alloy films, despite the steep compositional gradients. Moreover, we reveal a sizable anti-damping SOT efficiency of $|θ_\mathrm{DL}| \approx 0.05$, even without an intentional compositional gradient. Through depth-resolved x-ray diffraction, we identify a lattice strain gradient as crucial symmetry breaking that underpins the SOT. Our findings provide fresh insights into damping and SOTs in single-layer ferromagnets for power-efficient spintronic devices.

cond-mat.mtrl-sci↗