arXiv subjects

Xin Wang

Publications and source records attributed to Xin Wang.

At least 469 records · Page 26Linked to original sources

arXiv2025

A unified framework for identifying influential nodes in hypergraphs

Identifying influential nodes plays a pivotal role in understanding, controlling, and optimizing the behavior of complex systems, ranging from social to biological and technological domains. Yet most centrality-based approaches rely on pairwise topology and are purely structural, neglecting the higher-order interactions and the coupling between structure and dynamics. Consequently, the practical effectiveness of existing approaches remains uncertain when applied to complex spreading processes. To bridge this gap, we propose a unified framework, Initial Propagation Score (IPS), to directly embed propagation dynamics into influence assessment on higher-order networks. We analytically derive mechanism-aware influence measures by relating the early-stage dynamics and local topological characteristics to long-term outbreak sizes, and such explicit physical context endows IPS with robustness, transferability, and interpretability. Extensive experiments across multiple dynamics and more than 20 real-world hypergraphs show that IPS consistently outperforms other leading baseline centralities. Furthermore, IPS estimates node influence with only local neighborhood information, yielding computational efficiency and scalability to large-scale networks. This work underscores the necessity of considering dynamics for reliable identification of influential nodes and provides a concise principled basis for optimizing interventions in epidemiology, information diffusion, and collective intelligence.

physics.soc-ph↗

arXiv2025

Human perception of audio deepfakes: the role of language and speaking style

Audio deepfakes have reached a level of realism that makes it increasingly difficult to distinguish between human and artificial voices, which poses risks such as identity theft or spread of disinformation. Despite these concerns, research on humans' ability to identify deepfakes is limited, with most studies focusing on English and very few exploring the reasons behind listeners' perceptual decisions. This study addresses this gap through a perceptual experiment in which 54 listeners (28 native Spanish speakers and 26 native Japanese speakers) classified voices as natural or synthetic, and justified their choices. The experiment included 80 stimuli (50% artificial), organized according to three variables: language (Spanish/Japanese), speech style (audiobooks/interviews), and familiarity with the voice (familiar/unfamiliar). The goal was to examine how these variables influence detection and to analyze qualitatively the reasoning behind listeners' perceptual decisions. Results indicate an average accuracy of 59.11%, with higher performance on authentic samples. Judgments of vocal naturalness rely on a combination of linguistic and non-linguistic cues. Comparing Japanese and Spanish listeners, our qualitative analysis further reveals both shared cues and notable cross-linguistic differences in how listeners conceptualize the "humanness" of speech. Overall, participants relied primarily on suprasegmental and higher-level or extralinguistic characteristics - such as intonation, rhythm, fluency, pauses, speed, breathing, and laughter - over segmental features. These findings underscore the complexity of human perceptual strategies in distinguishing natural from artificial speech and align partly with prior research emphasizing the importance of prosody and phenomena typical of spontaneous speech, such as disfluencies.

eess.AS↗

arXiv2025

Dynamic Facial Expressions Analysis Based Parkinson's Disease Auxiliary Diagnosis

Parkinson's disease (PD), a prevalent neurodegenerative disorder, significantly affects patients' daily functioning and social interactions. To facilitate a more efficient and accessible diagnostic approach for PD, we propose a dynamic facial expression analysis-based PD auxiliary diagnosis method. This method targets hypomimia, a characteristic clinical symptom of PD, by analyzing two manifestations: reduced facial expressivity and facial rigidity, thereby facilitating the diagnosis process. We develop a multimodal facial expression analysis network to extract expression intensity features during patients' performance of various facial expressions. This network leverages the CLIP architecture to integrate visual and textual features while preserving the temporal dynamics of facial expressions. Subsequently, the expression intensity features are processed and input into an LSTM-based classification network for PD diagnosis. Our method achieves an accuracy of 93.1%, outperforming other in-vitro PD diagnostic approaches. This technique offers a more convenient detection method for potential PD patients, improving their diagnostic experience.

cs.CV↗

arXiv2025

Programmable Open Quantum Systems

Programmability is a unifying paradigm for enacting families of quantum transformations via fixed processors and program states, with a fundamental role and broad impact in quantum computation and control. While there has been a shift from viewing open systems solely as a source of error to treating them as a computational resource, their programmability remains largely unexplored. In this work, we develop a framework that characterizes and quantifies the programmability of Lindbladian semigroups by combining physically implementable retrieval maps with time varying program states. Within this framework, we identify quantum programmable classes enabled by symmetry and stochastic structure, including covariant semigroups and fully dissipative Pauli Lindbladians with finite program dimension. We further provide a necessary condition for physical programmability that rules out coherent generators and typical dissipators generating amplitude damping. For such nonphysically programmable cases, we construct explicit protocols with finite resources. Finally, we introduce an operational programming cost, defined via the number of samples required to program the Lindbladian, and establish its core structural properties, such as continuity and faithfulness. These results provide a notion of programming cost for Lindbladians, bridge programmable channel theory and open system dynamics, and yield symmetry driven compression schemes and actionable resource estimates for semigroup simulation and control in noisy quantum technologies.

quant-ph↗

arXiv2025

RL-I2IT: Image-to-Image Translation with Deep Reinforcement Learning

Most existing Image-to-Image Translation (I2IT) methods generate images in a single run of a deep learning (DL) model. However, designing such a single-step model is always challenging, requiring a huge number of parameters and easily falling into bad global minimums and overfitting. In this work, we reformulate I2IT as a step-wise decision-making problem via deep reinforcement learning (DRL) and propose a novel framework that performs RL-based I2IT (RL-I2IT). The key feature in the RL-I2IT framework is to decompose a monolithic learning process into small steps with a lightweight model to progressively transform a source image successively to a target image. Considering that it is challenging to handle high dimensional continuous state and action spaces in the conventional RL framework, we introduce meta policy with a new concept Plan to the standard Actor-Critic model, which is of a lower dimension than the original image and can facilitate the actor to generate a tractable high dimensional action. In the RL-I2IT framework, we also employ a task-specific auxiliary learning strategy to stabilize the training process and improve the performance of the corresponding task. Experiments on several I2IT tasks demonstrate the effectiveness and robustness of the proposed method when facing high-dimensional continuous action space problems. Our implementation of the RL-I2IT framework is available at https://github.com/Algolzw/SPAC-Deformable-Registration.

cs.CV↗

arXiv2025

PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention

The Vision-Language-Action (VLA) models have demonstrated remarkable performance on embodied tasks and shown promising potential for real-world applications. However, current VLAs still struggle to produce consistent and precise target-oriented actions, as they often generate redundant or unstable motions along trajectories, limiting their applicability in time-sensitive scenarios.In this work, we attribute these redundant actions to the spatially uniform perception field of existing VLAs, which causes them to be distracted by target-irrelevant objects, especially in complex environments.To address this issue, we propose an efficient PosA-VLA framework that anchors visual attention via pose-conditioned supervision, consistently guiding the model's perception toward task-relevant regions. The pose-conditioned anchor attention mechanism enables the model to better align instruction semantics with actionable visual cues, thereby improving action generation precision and efficiency. Moreover, our framework adopts a lightweight architecture and requires no auxiliary perception modules (e.g., segmentation or grounding networks), ensuring efficient inference. Extensive experiments verify that our method executes embodied tasks with precise and time-efficient behavior across diverse robotic manipulation benchmarks and shows robust generalization in a variety of challenging environments.

cs.CV↗

arXiv2025

Cross-platform Product Matching Based on Entity Alignment of Knowledge Graph with RAEA model

Product matching aims to identify identical or similar products sold on different platforms. By building knowledge graphs (KGs), the product matching problem can be converted to the Entity Alignment (EA) task, which aims to discover the equivalent entities from diverse KGs. The existing EA methods inadequately utilize both attribute triples and relation triples simultaneously, especially the interactions between them. This paper introduces a two-stage pipeline consisting of rough filter and fine filter to match products from eBay and Amazon. For fine filtering, a new framework for Entity Alignment, Relation-aware and Attribute-aware Graph Attention Networks for Entity Alignment (RAEA), is employed. RAEA focuses on the interactions between attribute triples and relation triples, where the entity representation aggregates the alignment signals from attributes and relations with Attribute-aware Entity Encoder and Relation-aware Graph Attention Networks. The experimental results indicate that the RAEA model achieves significant improvements over 12 baselines on EA task in the cross-lingual dataset DBP15K (6.59% on average Hits@1) and delivers competitive results in the monolingual dataset DWY100K. The source code for experiments on DBP15K and DWY100K is available at github (https://github.com/Mockingjay-liu/RAEA-model-for-Entity-Alignment).

cs.AI↗

arXiv2025

Non-Orthogonal Multiple-Access for Coherent-State Optical Quantum Communications Under Lossy Photon Channels

Coherent states have been increasingly considered in optical quantum communications (OQCs). With the inherent non-orthogonality of coherent states, non-orthogonal multiple-access (NOMA) naturally lends itself to the implementation of multi-user OQC. However, this remains unexplored in the literature. This paper proposes a novel successive interference cancellation (SIC)-based Kennedy receiver for uplink NOMA-OQC systems, along with a new approach for power allocation of the coherent states emitted by users. The key idea is to rigorously derive the asymptotic sum-rate of the considered systems, taking into account the impact of atmospheric turbulence, background noise, and lossy photon channel. With the asymptotic sum-rate, we optimize the average number of photons (or powers) of the coherent states emitted by the users. Variable substitution and successive convex approximation (SCA) are employed to convexify and maximize the asymptotic sum-rate iteratively. A new coherent-state power allocation algorithm is developed for a small-to-medium number of users. We further develop its low-complexity variant using adaptive importance sampling, which is suitable for scenarios with a medium-to-large number of users. Simulations demonstrate that our algorithms significantly enhance the sum-rate of uplink NOMA-OQC systems using coherent states by over 20\%, compared to their alternatives.

quant-ph↗

arXiv2025

Non-Orthogonal Multiple Access-Based Continuous-Variable Quantum Key Distribution: Secret Key Rate Analysis and Power Allocation

We address the multi-user quantum key distribution (QKD) problem under malicious quantum attacks, which is critical for realizing a large-scale quantum Internet. This paper maximizes the sum secret key rate (SKR) of a novel uplink non-orthogonal multiple access based continuous-variable QKD (NOMA-CVQKD) system under collective attacks. The proposed system uses Gaussian-modulated coherent states and a quantum successive interference cancellation based heterodyne receiver. We derive closed-form asymptotic bounds for the legitimate users' achievable key rates via the entropy power inequality and maximum entropy principle, as well as for the eavesdropper's intercepted information based on Holevo information. A successive convex approximation based power allocation algorithm is developed to maximize the asymptotic sum SKR of the NOMA-CVQKD system under collective attacks, with guaranteed convergence to a locally optimal Karush-Kuhn-Tucker solution. Simulation results show that the proposed NOMA-CVQKD system with the power allocation algorithm achieves up to 23% higher sum SKR than quantum-orthogonal multiple access, supports 16 users at excess noise variance 0.1, and remains robust under varying turbulence intensities and transmission distances.

quant-ph↗

arXiv2025

Dressed Interference in Giant Superatoms: Entanglement Generation and Transfer

We introduce the concept of giant superatoms (GSAs), where two or more interacting atoms are nonlocally coupled to a waveguide through one of them, and explore their unconventional quantum dynamics. For braided GSAs, this setup enables decoherence-free transfer and swapping of their internal entangled states. For separate GSAs, engineering coupling phases leads to state-dependent chiral emission, which enables selective, directional quantum information transfer. This mechanism further facilitates remote generation of W-class entangled states. Our results thereby open exciting possibilities for quantum networks and quantum information processing.

quant-ph↗

arXiv2025

BiTAgent: A Task-Aware Modular Framework for Bidirectional Coupling between Multimodal Large Language Models and World Models

Building generalist embodied agents requires a unified system that can interpret multimodal goals, model environment dynamics, and execute reliable actions across diverse real-world tasks. Multimodal large language models (MLLMs) offer strong semantic priors and cross-modal generalization, while world models (WMs) provide actionable latent dynamics for prediction and control. Their combination holds promise for open-ended embodied intelligence, yet introduces two key challenges: (1) establishing a tight coupling between the semantic intent from MLLMs and the dynamic state representations within the WM's latent space, and (2) achieving task-aware adaptability that supports multi-task learning and cross-environment generalization. To address these limitations, we propose BiTAgent, a task-aware dynamic joint framework that enables bidirectional coupling between MLLMs and WMs. BiTAgent establishes two complementary pathways: a forward path that injects MLLM representations into the WM's latent space for semantically guided imagination, and a backward path where WM-generated feedback refines the MLLM's semantic space via dense text-conditioned rewards. This bidirectional interaction is realized through three synergistic components: Task-Aware Dynamic Joint Learning, Task-Aware Behavior Learning, and MLLM-WM Joint Optimization, which together harmonize semantic reasoning and dynamic prediction. Extensive experiments across multi-task and cross-environment settings demonstrate superior stability and generalization over state-of-the-art baselines, marking a step toward open-ended embodied learning.

cs.AI↗

arXiv2025

PhyVLLM: Physics-Guided Video Language Model with Motion-Appearance Disentanglement

Video Large Language Models (Video LLMs) have shown impressive performance across a wide range of video-language tasks. However, they often fail in scenarios requiring a deeper understanding of physical dynamics. This limitation primarily arises from their reliance on appearance-based matching. Incorporating physical motion modeling is crucial for deeper video understanding, but presents three key challenges: (1) motion signals are often entangled with appearance variations, making it difficult to extract clean physical cues; (2) effective motion modeling requires not only continuous-time motion representations but also capturing physical dynamics; and (3) collecting accurate annotations for physical attributes is costly and often impractical. To address these issues, we propose PhyVLLM, a physical-guided video-language framework that explicitly incorporates physical motion into Video LLMs. Specifically, PhyVLLM disentangles visual appearance and object motion through a dual-branch encoder. To model physical dynamics over time, we incorporate a Neural Ordinary Differential Equation (Neural ODE) module, which generates differentiable physical dynamic representations. The resulting motion-aware representations are projected into the token space of a pretrained LLM, enabling physics reasoning without compromising the model's original multimodal capabilities. To circumvent the need for explicit physical labels, PhyVLLM employs a self-supervised manner to model the continuous evolution of object motion. Experimental results demonstrate that PhyVLLM significantly outperforms state-of-the-art Video LLMs on both physical reasoning and general video understanding tasks, highlighting the advantages of incorporating explicit physical modeling.

cs.CV↗

arXiv2025

On-the-fly Feedback SfM: Online Explore-and-Exploit UAV Photogrammetry with Incremental Mesh Quality-Aware Indicator and Predictive Path Planning

Compared with conventional offline UAV photogrammetry, real-time UAV photogrammetry is essential for time-critical geospatial applications such as disaster response and active digital-twin maintenance. However, most existing methods focus on processing captured images or sequential frames in real time, without explicitly evaluating the quality of the on-the-go 3D reconstruction or providing guided feedback to enhance image acquisition in the target area. This work presents On-the-fly Feedback SfM, an explore-and-exploit framework for real-time UAV photogrammetry, enabling iterative exploration of unseen regions and exploitation of already observed and reconstructed areas in near real time. Built upon SfM on-the-fly , the proposed method integrates three modules: (1) online incremental coarse-mesh generation for dynamically expanding sparse 3D point cloud; (2) online mesh quality assessment with actionable indicators; and (3) predictive path planning for on-the-fly trajectory refinement. Comprehensive experiments demonstrate that our method achieves in-situ reconstruction and evaluation in near real time while providing actionable feedback that markedly reduces coverage gaps and re-flight costs. Via the integration of data collection, processing, 3D reconstruction and assessment, and online feedback, our on the-fly feedback SfM could be an alternative for the transition from traditional passive working mode to a more intelligent and adaptive exploration workflow. Code is now available at https://github.com/IRIS-LAB-whu/OntheflySfMFeedback.

cs.CV↗

arXiv2025

ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning

Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors into simplified reasoning with latent embeddings, rendering the reasoning chain opaque and essentially intractable. We therefore adopt an explicit decomposition perspective and introduce ReVSeg, which executes reasoning as sequential decisions in the native interface of pretrained vision language models (VLMs). Rather than folding all reasoning into a single-step prediction, ReVSeg executes three explicit operations -- semantics interpretation, temporal evidence selection, and spatial grounding -- aligning pretrained capabilities. We further employ reinforcement learning to optimize the multi-step reasoning chain, enabling the model to self-refine its decision quality from outcome-driven signals. Experimental results demonstrate that ReVSeg attains state-of-the-art performances on standard video object segmentation benchmarks and yields interpretable reasoning trajectories. Project page is available at https://clementine24.github.io/ReVSeg/ .

cs.CV↗

arXiv2025

CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generation

Despite major advances brought by diffusion-based models, current 3D texture generation systems remain hindered by cross-view inconsistency -- textures that appear convincing from one viewpoint often fail to align across others. We find that this issue arises from attention ambiguity, where unstructured full attention is applied indiscriminately across tokens and modalities, causing geometric confusion and unstable appearance-structure coupling. To address this, we introduce CaliTex, a framework of geometry-calibrated attention that explicitly aligns attention with 3D structure. It introduces two modules: Part-Aligned Attention that enforces spatial alignment across semantically matched parts, and Condition-Routed Attention which routes appearance information through geometry-conditioned pathways to maintain spatial fidelity. Coupled with a two-stage diffusion transformer, CaliTex makes geometric coherence an inherent behavior of the network rather than a byproduct of optimization. Empirically, CaliTex produces seamless and view-consistent textures and outperforms both open-source and commercial baselines.

cs.CV↗

arXiv2025

Generative Editing in the Joint Vision-Language Space for Zero-Shot Composed Image Retrieval

Composed Image Retrieval (CIR) enables fine-grained visual search by combining a reference image with a textual modification. While supervised CIR methods achieve high accuracy, their reliance on costly triplet annotations motivates zero-shot solutions. The core challenge in zero-shot CIR (ZS-CIR) stems from a fundamental dilemma: existing text-centric or diffusion-based approaches struggle to effectively bridge the vision-language modality gap. To address this, we propose Fusion-Diff, a novel generative editing framework with high effectiveness and data efficiency designed for multimodal alignment. First, it introduces a multimodal fusion feature editing strategy within a joint vision-language (VL) space, substantially narrowing the modality gap. Second, to maximize data efficiency, the framework incorporates a lightweight Control-Adapter, enabling state-of-the-art performance through fine-tuning on only a limited-scale synthetic dataset of 200K samples. Extensive experiments on standard CIR benchmarks (CIRR, FashionIQ, and CIRCO) demonstrate that Fusion-Diff significantly outperforms prior zero-shot approaches. We further enhance the interpretability of our model by visualizing the fused multimodal representations.

cs.CV↗

arXiv2025

A homoclinic route to chaos in omnivore communities

Omnivory, where species feed across multiple trophic levels, is a widespread feature of ecological networks. A key mechanism underlying such complexity is intraguild predation (IGP), in which a top predator consumes both an intermediate predator and a shared resource. Here, we show that Shilnikov homoclinic orbits emerge in a minimal intraguild predation model, triggering a cascade of homoclinic bifurcations near a saddle-focus equilibrium that culminates in chaos. Numerical simulations and Lyapunov spectrum analysis reveal multiple coexistence modes, ranging from regular oscillations to Shilnikov homoclinic orbits and chaos. Our model quantitatively reproduces patterns observed in natural omnivore networks, providing mechanistic insights into complex population fluctuations in ecological systems.

nlin.CD↗

arXiv2025

Machine Unlearning of Traffic State Estimation and Prediction

Data-driven traffic state estimation and prediction (TSEP) relies heavily on data sources that contain sensitive information. While the abundance of data has fueled significant breakthroughs, particularly in machine learning-based methods, it also raises concerns regarding privacy, cybersecurity, and data freshness. These issues can erode public trust in intelligent transportation systems. Recently, regulations have introduced the "right to be forgotten", allowing users to request the removal of their private data from models. As machine learning models can remember old data, simply removing it from back-end databases is insufficient in such systems. To address these challenges, this study introduces a novel learning paradigm for TSEP-Machine Unlearning TSEP-which enables a trained TSEP model to selectively forget privacy-sensitive, poisoned, or outdated data. By empowering models to "unlearn," we aim to enhance the trustworthiness and reliability of data-driven traffic TSEP.

cs.LG↗