arXiv subjects

Xin Wang

Publications and source records attributed to Xin Wang.

At least 613 records · Page 34Linked to original sources

arXiv2025

LENS-DF: Deepfake Detection and Temporal Localization for Long-Form Noisy Speech

This study introduces LENS-DF, a novel and comprehensive recipe for training and evaluating audio deepfake detection and temporal localization under complicated and realistic audio conditions. The generation part of the recipe outputs audios from the input dataset with several critical characteristics, such as longer duration, noisy conditions, and containing multiple speakers, in a controllable fashion. The corresponding detection and localization protocol uses models. We conduct experiments based on self-supervised learning front-end and simple back-end. The results indicate that models trained using data generated with LENS-DF consistently outperform those trained via conventional recipes, demonstrating the effectiveness and usefulness of LENS-DF for robust audio deepfake detection and localization. We also conduct ablation studies on the variations introduced, investigating their impact on and relevance to realistic challenges in the field.

cs.SD↗

arXiv2025

THE-Tree: Can Tracing Historical Evolution Enhance Scientific Verification and Reasoning?

Large Language Models (LLMs) are accelerating scientific idea generation, but rigorously evaluating these numerous, often superficial, AI-generated propositions for novelty and factual accuracy is a critical bottleneck; manual verification is too slow. Existing validation methods are inadequate: LLMs as standalone verifiers may hallucinate and lack domain knowledge (our findings show 60% unawareness of relevant papers in specific domains), while traditional citation networks lack explicit causality and narrative surveys are unstructured. This underscores a core challenge: the absence of structured, verifiable, and causally-linked historical data of scientific evolution.To address this,we introduce \textbf{THE-Tree} (\textbf{T}echnology \textbf{H}istory \textbf{E}volution Tree), a computational framework that constructs such domain-specific evolution trees from scientific literature. THE-Tree employs a search algorithm to explore evolutionary paths. During its node expansion, it utilizes a novel "Think-Verbalize-Cite-Verify" process: an LLM proposes potential advancements and cites supporting literature. Critically, each proposed evolutionary link is then validated for logical coherence and evidential support by a recovered natural language inference mechanism that interrogates the cited literature, ensuring that each step is grounded. We construct and validate 88 THE-Trees across diverse domains and release a benchmark dataset including up to 71k fact verifications covering 27k papers to foster further research. Experiments demonstrate that i) in graph completion, our THE-Tree improves hit@1 by 8% to 14% across multiple models compared to traditional citation networks; ii) for predicting future scientific developments, it improves hit@1 metric by nearly 10%; and iii) when combined with other methods, it boosts the performance of evaluating important scientific papers by almost 100%.

cs.AI↗

arXiv2025

Nakayama automorphisms of graded double Ore extensions of Koszul Artin-Schelter regular algebras with nontrivial skew derivations

Let $A$ be a Koszul Artin-Schelter regular algebra and $B=A_P[y_1,y_2;ς,ν]$ be a graded double Ore extension of $A$ where $ς:A\to M_{2\times 2}(A)$ is a graded algebra homomorphism and $ν:A\to A^{\oplus 2}$ is a degree one $ς$-derivation. We construct a minimal free resolution for the trivial module of $B$, and it implies that $B$ is still Koszul. We introduce a homological invariant called $ς$-divergence of $ν$, and with its aid, we obtain a precise description of the Nakayama automorphism of $B$. A twisted superpotential $\hatω$ for $B$ with respect to the Nakayama automorphism is constructed so that $B$ is isomorphic to the derivation quotient algebra of $\hatω$.

math.RA↗

arXiv2025

A Comprehensive Survey of Synthetic Tabular Data Generation

Tabular data is one of the most prevalent and important data formats in real-world applications such as healthcare, finance, and education. However, its effective use in machine learning is often constrained by data scarcity, privacy concerns, and class imbalance. Synthetic tabular data generation has emerged as a powerful solution, leveraging generative models to learn underlying data distributions and produce realistic, privacy-preserving samples. Although this area has seen growing attention, most existing surveys focus narrowly on specific methods (e.g., GANs or privacy-enhancing techniques), lacking a unified and comprehensive view that integrates recent advances such as diffusion models and large language models (LLMs). In this survey, we present a structured and in-depth review of synthetic tabular data generation methods. Specifically, the survey is organized into three core components: (1) Background, which covers the overall generation pipeline, including problem definitions, synthetic tabular data generation methods, post processing, and evaluation; (2) Generation Methods, where we categorize existing approaches into traditional generation methods, diffusion model methods, and LLM-based methods, and compare them in terms of architecture, generation quality, and applicability; and (3) Applications and Challenges, which summarizes practical use cases, highlights common datasets, and discusses open challenges such as heterogeneity, data fidelity, and privacy protection. This survey aims to provide researchers and practitioners with a holistic understanding of the field and to highlight key directions for future work in synthetic tabular data generation.

cs.LG↗

arXiv2025

USIS16K: High-Quality Dataset for Underwater Salient Instance Segmentation

Inspired by the biological visual system that selectively allocates attention to efficiently identify salient objects or regions, underwater salient instance segmentation (USIS) aims to jointly address the problems of where to look (saliency prediction) and what is there (instance segmentation) in underwater scenarios. However, USIS remains an underexplored challenge due to the inaccessibility and dynamic nature of underwater environments, as well as the scarcity of large-scale, high-quality annotated datasets. In this paper, we introduce USIS16K, a large-scale dataset comprising 16,151 high-resolution underwater images collected from diverse environmental settings and covering 158 categories of underwater objects. Each image is annotated with high-quality instance-level salient object masks, representing a significant advance in terms of diversity, complexity, and scalability. Furthermore, we provide benchmark evaluations on underwater object detection and USIS tasks using USIS16K. To facilitate future research in this domain, the dataset and benchmark models are publicly available.

cs.CV↗

arXiv2025

Robust Beamforming Design for Secure Near-Field ISAC Systems

This letter investigates the robust beamforming design for a near-field secure integrated sensing and communication (ISAC) system with multiple communication users (CUs) and targets, as well as multiple eavesdroppers. Taking into account the channel uncertainty constraints, we maximize the minimum sensing beampattern gain for targets, subject to the minimum signal-to-interference-plus-noise ratio (SINR) constraint for each CU and the maximum SINR constraint for each eavesdropper, as well as the ISAC transmit power constraint. The formulated design problem is non-convex. As a low-complexity suboptimal solution, we first apply the S-Procedure to convert semi-infinite channel uncertainty constraints into linear matrix inequalities (LMIs) and then use the state-of-the-art sequential rank-one constraint relaxation (SROCR) method to address the rank-one constraints. The numerical results show that the proposed ISAC beamforming design scheme outperforms the existing semidefinite relaxation (SDR) and other baseline schemes, and it significantly enhances security and robustness for near-field ISAC systems.

cs.IT↗

arXiv2025

GS-I$^{3}$: Gaussian Splatting for Surface Reconstruction from Illumination-Inconsistent Images

Accurate geometric surface reconstruction, providing essential environmental information for navigation and manipulation tasks, is critical for enabling robotic self-exploration and interaction. Recently, 3D Gaussian Splatting (3DGS) has gained significant attention in the field of surface reconstruction due to its impressive geometric quality and computational efficiency. While recent relevant advancements in novel view synthesis under inconsistent illumination using 3DGS have shown promise, the challenge of robust surface reconstruction under such conditions is still being explored. To address this challenge, we propose a method called GS-3I. Specifically, to mitigate 3D Gaussian optimization bias caused by underexposed regions in single-view images, based on Convolutional Neural Network (CNN), a tone mapping correction framework is introduced. Furthermore, inconsistent lighting across multi-view images, resulting from variations in camera settings and complex scene illumination, often leads to geometric constraint mismatches and deviations in the reconstructed surface. To overcome this, we propose a normal compensation mechanism that integrates reference normals extracted from single-view image with normals computed from multi-view observations to effectively constrain geometric inconsistencies. Extensive experimental evaluations demonstrate that GS-3I can achieve robust and accurate surface reconstruction across complex illumination scenarios, highlighting its effectiveness and versatility in this critical challenge. https://github.com/TFwang-9527/GS-3I

cs.CV↗

arXiv2025

EmbRACE-3K: Embodied Reasoning and Action in Complex Environments

Recent advanced vision-language models(VLMs) have demonstrated strong performance on passive, offline image and video understanding tasks. However, their effectiveness in embodied settings, which require online interaction and active scene understanding remains limited. In such scenarios, an agent perceives the environment from a first-person perspective, with each action dynamically shaping subsequent observations. Even state-of-the-art models such as GPT-4o, Claude 3.5 Sonnet, and Gemini 2.5 Pro struggle in open-environment interactions, exhibiting clear limitations in spatial reasoning and long-horizon planning. To address this gap, we introduce EmRACE-3K, a dataset of over 3,000 language-guided tasks situated in diverse, photorealistic environments constructed using Unreal Engine and the UnrealCV-Zoo framework. The tasks encompass a wide range of embodied challenges, including navigation, object manipulation, and multi-stage goal execution. Each task unfolds as a multi-step trajectory, pairing first-person visual observations with high-level instructions, grounded actions, and natural language rationales that express the agent's intent at every step. Using EmRACE-3K, we establish a benchmark to evaluate the embodied reasoning capabilities of VLMs across three key dimensions: Exploration, Dynamic Spatial-Semantic Reasoning, and Multi-stage Goal Execution. In zero-shot settings, all models achieve success rates below 20%, underscoring the challenge posed by our benchmark and the current limitations of VLMs in interactive environments. To demonstrate the utility of EmRACE-3K, we further fine-tune Qwen2.5-VL-7B using supervised learning followed by reinforcement learning. This approach yields substantial improvements across all three challenge categories, highlighting the dataset's effectiveness in enabling the development of embodied reasoning capabilities.

cs.CV↗

arXiv2025

A Model Aware AIGC Task Offloading Algorithm in IIoT Edge Computing

The integration of the Industrial Internet of Things (IIoT) with Artificial Intelligence-Generated Content (AIGC) offers new opportunities for smart manufacturing, but it also introduces challenges related to computation-intensive tasks and low-latency demands. Traditional generative models based on cloud computing are difficult to meet the real-time requirements of AIGC tasks in IIoT environments, and edge computing can effectively reduce latency through task offloading. However, the dynamic nature of AIGC tasks, model switching delays, and resource constraints impose higher demands on edge computing environments. To address these challenges, this paper proposes an AIGC task offloading framework tailored for IIoT edge computing environments, considering the latency and energy consumption caused by AIGC model switching for the first time. IIoT devices acted as multi-agent collaboratively offload their dynamic AIGC tasks to the most appropriate edge servers deployed with different generative models. A model aware AIGC task offloading algorithm based on Multi-Agent Deep Deterministic Policy Gradient (MADDPG-MATO) is devised to minimize the latency and energy. Experimental results show that MADDPG-MATO outperforms baseline algorithms, achieving an average reduction of 6.98% in latency, 7.12% in energy consumption, and a 3.72% increase in task completion rate across four sets of experiments with model numbers ranging from 3 to 6, it is demonstrated that the proposed algorithm is robust and efficient in dynamic, high-load IIoT environments.

cs.DC↗

arXiv2025

MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling

Generating expressive audio performances from music scores requires models to capture both instrument acoustics and human interpretation. Traditional music performance synthesis pipelines follow a two-stage approach, first generating expressive performance MIDI from a score, then synthesising the MIDI into audio. However, the synthesis models often struggle to generalise across diverse MIDI sources, musical styles, and recording environments. To address these challenges, we propose MIDI-VALLE, a neural codec language model adapted from the VALLE framework, which was originally designed for zero-shot personalised text-to-speech (TTS) synthesis. For performance MIDI-to-audio synthesis, we improve the architecture to condition on a reference audio performance and its corresponding MIDI. Unlike previous TTS-based systems that rely on piano rolls, MIDI-VALLE encodes both MIDI and audio as discrete tokens, facilitating a more consistent and robust modelling of piano performances. Furthermore, the model's generalisation ability is enhanced by training on an extensive and diverse piano performance dataset. Evaluation results show that MIDI-VALLE significantly outperforms a state-of-the-art baseline, achieving over 75% lower Frechet Audio Distance on the ATEPP and Maestro datasets. In the listening test, MIDI-VALLE received 202 votes compared to 58 for the baseline, demonstrating improved synthesis quality and generalisation across diverse performance MIDI inputs.

cs.SD↗

arXiv2025

Towards the ultimate limits of quantum channel discrimination and quantum communication

Distinguishability is fundamental to information theory and extends naturally to quantum systems. While quantum state discrimination is well understood, quantum channel discrimination remains challenging due to the dynamic nature of channels and the variety of discrimination strategies. This work advances the understanding of quantum channel discrimination and its fundamental limits. We develop new tools for quantum divergences, including sharper bounds on the quantum hypothesis testing relative entropy and additivity results for channel divergences. We establish a quantum Stein's lemma for memoryless channel discrimination, and link the strong converse property to the asymptotic equipartition property and continuity of divergences. Notably, we prove the equivalence of exponentially strong converse properties under coherent and sequential strategies. We further explore the interplay among operational regimes, discrimination strategies, and channel divergences, deriving exponents in various settings and contributing to a unified framework for channel discrimination. Finally, we recast quantum communication tasks as discrimination problems, uncovering deep connections between channel capacities, channel discrimination, and the mathematical structure of channel divergences. These results bridge two core areas of quantum information theory and offer new insights for future exploration.

quant-ph↗

arXiv2025

Chiral-Extended Photon-Emitter Dressed States in Non-Hermitian Topological Baths

The interplay of quantum emitters and non-Hermitian structured baths has received increasing attention in recent years. Here, we predict unconventional quantum optical behaviors of quantum emitters coupled to a non-Hermitian topological bath, which is realized in a 1D Su-Schrieffer-Heeger photonic chain subjected to nonlocal dissipation. In addition to the Hermitian-like chiral bound states in the middle line gap and skin-mode-like hidden bound states inside the point gap, we identify peculiar in-gap chiral and extended photon-emitter dressed states. This is due to the competition of topological-edge localization and non-Hermitian skin-mode localization in combination with the non-Bloch bulk-boundary correspondence. Strikingly, dissipation can shape the wavefunction profile of the dressed state. Furthermore, when two emitters are coupled to the same bath, such in-gap dressed states can mediate the nonreciprocal long-range emitter-emitter interactions, with the interaction range limited only by the dissipation of the bath. Our work opens the door to further study rich quantum optical phenomena and exotic many-body physics utilizing quantum emitters coupled to non-Hermitian baths.

quant-ph↗

arXiv2025

SecureSpeech: Prompt-based Speaker and Content Protection

Given the increasing privacy concerns from identity theft and the re-identification of speakers through content in the speech field, this paper proposes a prompt-based speech generation pipeline that ensures dual anonymization of both speaker identity and spoken content. This is addressed through 1) generating a speaker identity unlinkable to the source speaker, controlled by descriptors, and 2) replacing sensitive content within the original text using a name entity recognition model and a large language model. The pipeline utilizes the anonymized speaker identity and text to generate high-fidelity, privacy-friendly speech via a text-to-speech synthesis model. Experimental results demonstrate an achievement of significant privacy protection while maintaining a decent level of content retention and audio quality. This paper also investigates the impact of varying speaker descriptions on the utility and privacy of generated speech to determine potential biases.

cs.SD↗

arXiv2025

Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS

Test-time scaling has emerged as a promising paradigm in language modeling, leveraging additional computational resources at inference time to enhance model performance. In this work, we introduce R2-LLMs, a novel and versatile hierarchical retrieval-augmented reasoning framework designed to improve test-time scaling in large language models (LLMs) without requiring distillation from more advanced models to obtain chain-of-thought (CoT) training data. R2-LLMs enhances inference-time generalization by integrating dual-level retrieval-based in-context learning: (1) At the coarse level, our approach extracts abstract templates from complex reasoning problems and retrieves similar problem-answer pairs to facilitate high-level in-context learning; (2) At the fine level, during Monte Carlo Tree Search (MCTS), R2-LLMs efficiently retrieves analogous intermediate solution steps from reference mathematical problem datasets, refining step-wise reasoning with the aid of a process reward model (PRM) for scoring. R2-LLMs is a robust hierarchical reasoning-augmentation method that enhances in-context-level reasoning while seamlessly integrating with step-level tree search methods. Utilizing PRM, it refines both candidate generation and decision-making for improved reasoning accuracy. Empirical evaluations on the MATH500, GSM8K, and OlympiadBench-TO datasets achieve substantial relative improvement with an increase of up to 16% using LLaMA-3.1-8B compared to the baselines, showcasing the effectiveness of our approach in complex reasoning tasks.

cs.CL↗

arXiv2025

Quantum Latin squares with all possible cardinalities

A quantum Latin square of order $n$ (denoted as QLS$(n)$) is an $n\times n$ array whose entries are unit column vectors from the $n$-dimensional Hilbert space $\mathcal{H}_n$, such that each row and column forms an orthonormal basis. Two unit vectors $|u\rangle, |v\rangle\in \mathcal{H}_n$ are regarded as identical if there exists a real number $θ$ such that $|u\rangle=e^{iθ}|v\rangle$; otherwise, they are considered distinct. The cardinality $c$ of a QLS$(n)$ is the number of distinct vectors in the array. In this paper, we use sub-QLS$(4)$s to prove that for any integer $m\geq 2$ and any integer $c\in [4m,16m^2]\setminus \{4m+1\}$, there is a QLS$(4m)$ with cardinality $c$.

quant-ph↗

arXiv2025

DpDNet: An Dual-Prompt-Driven Network for Universal PET-CT Segmentation

PET-CT lesion segmentation is challenging due to noise sensitivity, small and variable lesion morphology, and interference from physiological high-metabolic signals. Current mainstream approaches follow the practice of one network solving the segmentation of multiple cancer lesions by treating all cancers as a single task. However, this overlooks the unique characteristics of different cancer types. Considering the specificity and similarity of different cancers in terms of metastatic patterns, organ preferences, and FDG uptake intensity, we propose DpDNet, a Dual-Prompt-Driven network that incorporates specific prompts to capture cancer-specific features and common prompts to retain shared knowledge. Additionally, to mitigate information forgetting caused by the early introduction of prompts, prompt-aware heads are employed after the decoder to adaptively handle multiple segmentation tasks. Experiments on a PET-CT dataset with four cancer types show that DpDNet outperforms state-of-the-art models. Finally, based on the segmentation results, we calculated MTV, TLG, and SUVmax for breast cancer survival analysis. The results suggest that DpDNet has the potential to serve as a valuable tool for personalized risk stratification, supporting clinicians in optimizing treatment strategies and improving outcomes. Code is available at https://github.com/XinglongLiang08/DpDNet.

eess.IV↗

arXiv2025

MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation

Electrocardiogram (ECG) is the primary non-invasive diagnostic tool for monitoring cardiac conditions and is crucial in assisting clinicians. Recent studies have concentrated on classifying cardiac conditions using ECG data but have overlooked ECG report generation, which is time-consuming and requires clinical expertise. To automate ECG report generation and ensure its versatility, we propose the Multimodal ECG Instruction Tuning (MEIT) framework, the first attempt to tackle ECG report generation with LLMs and multimodal instructions. To facilitate future research, we establish a benchmark to evaluate MEIT with various LLMs backbones across two large-scale ECG datasets. Our approach uniquely aligns the representations of the ECG signal and the report, and we conduct extensive experiments to benchmark MEIT with nine open-source LLMs using more than 800,000 ECG reports. MEIT's results underscore the superior performance of instruction-tuned LLMs, showcasing their proficiency in quality report generation, zero-shot capabilities, resilience to signal perturbation, and alignment with human expert evaluation. These findings emphasize the efficacy of MEIT and its potential for real-world clinical application.

cs.CL↗

arXiv2025

Topological defects govern plasticity and shear band formation in two-dimensional amorphous solids

Understanding the fundamental mechanisms behind plastic instabilities and shear band formation in amorphous media under applied deformation remains a long-standing challenge. Leveraging on the mathematical concept of topology, we revisit this problem using two-dimensional experimental amorphous granular packings subjected to pure shear. We demonstrate that topological defects (TDs) in the displacement vector field act as carriers of plasticity, enabling the prediction of both the onset of plastic flow and the global mechanical response of the system. At the microscopic level, we show that these TDs are responsible for the dynamical breakdown of local orientational order, thereby linking topological excitations to short-range structural changes. Finally, we establish that the spatial localization and cooperative alignment of TDs underlie the formation of macroscopic shear bands, which drive plastic flow under large shear loads. This process is mediated by the quasi-periodic annihilation of large defect clusters and their geometric transformation from an approximately isotropic to a strongly anisotropic shape. Our results provide a unified framework for understanding plastic deformation and shear band formation in two-dimensional amorphous systems by connecting topology, short-range order, and mechanical response.

cond-mat.soft↗