arXiv subjects

Xinyue Zhang

Publications and source records attributed to Xinyue Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Beyond Flatlands: Unlocking Spatial Intelligence by Decoupling 3D Reasoning from Numerical Regression

Existing Vision Language Models (VLMs) architecturally rooted in "flatland" perception, fundamentally struggle to comprehend real-world 3D spatial intelligence. This failure stems from a dual-bottleneck: input-stage conflict between computationally exorbitant geometric-aware encoders and superficial 2D-only features, and output-stage misalignment where discrete tokenizers are structurally incapable of producing precise, continuous numerical values. To break this impasse, we introduce GEODE (Geometric-Output and Decoupled-Input Engine), a novel architecture that resolves this dual-bottleneck by decoupling 3D reasoning from numerical generation. GEODE augments main VLM with two specialized, plug-and-play modules: Decoupled Rationale Module (DRM) that acts as spatial co-processor, aligning explicit 3D data with 2D visual features via cross-attention and distilling spatial Chain-of-Thought (CoT) logic into injectable Rationale Tokens; and Direct Regression Head (DRH), an "Embedding-as-Value" paradigm which routes specialized control tokens to a lightweight MLP for precise, continuous regression of scalars and 3D bounding boxes. The synergy of these modules allows our 1.5B parameter model to function as a high-level semantic dispatcher, achieving state-of-the-art spatial reasoning performance that rivals 7B+ models.

cs.CV↗

arXiv2025

Stroke Modeling Enables Vectorized Character Generation with Large Vectorized Glyph Model

Vectorized glyphs are widely used in poster design, network animation, art display, and various other fields due to their scalability and flexibility. In typography, they are often seen as special sequences composed of ordered strokes. This concept extends to the token sequence prediction abilities of large language models (LLMs), enabling vectorized character generation through stroke modeling. In this paper, we propose a novel Large Vectorized Glyph Model (LVGM) designed to generate vectorized Chinese glyphs by predicting the next stroke. Initially, we encode strokes into discrete latent variables called stroke embeddings. Subsequently, we train our LVGM via fine-tuning DeepSeek LLM by predicting the next stroke embedding. With limited strokes given, it can generate complete characters, semantically elegant words, and even unseen verses in vectorized form. Moreover, we release a new large-scale Chinese SVG dataset containing 907,267 samples based on strokes for dynamically vectorized glyph generation. Experimental results show that our model has scaling behaviors on data scales. Our generated vectorized glyphs have been validated by experts and relevant individuals.

cs.CV↗

arXiv2025

PE-TSFM: Self-Supervised Time-Series Learning for Generalizable Power Converter Health Monitoring under Unseen Conditions

Data-driven health monitoring of power converters remains limited by poor generalization to unseen operating conditions. This work addresses this out-of-distribution (OOD) challenge by building a domain-specific time-series foundation model (PE-TSFM) that learns representations directly from large-scale unlabeled converter data. Unlike generic TSFMs trained on broad time-series datasets, the proposed PE-TSFM is pre-trained entirely on domain data, enabling it to learn the physical relationships unique to power electronics. To further tailor the model to this domain, we introduce a dual-attention mechanism that captures both temporal patterns and inter-channel dependencies. While generic TSFMs primarily model temporal dependencies, the added channel attention captures inter-sensor physical relationships essential for converter degradation analysis. A dataset containing 141 million unlabeled timestamps from an operating power converter is used for pre-training. Experiments show that PE-TSFM achieves 92% accuracy under unseen operating conditions. In contrast, generic TSFMs achieve around 60% and conventional time-series models achieve around 40% accuracy. This result confirms the strong OOD generalization of the proposed PE-TSFM. Ablation studies further verify that the introduced channel attention mechanism significantly improves model performance. In addition, we conduct detailed studies on model scalability, hyperparameter sensitivity, and interpretability to provide a comprehensive understanding of the proposed approach.

eess.SY↗

arXiv2025

Learning from Disagreement: A Group Decision Simulation Framework for Robust Medical Image Segmentation

Medical image segmentation annotation suffers from inter-rater variability (IRV) due to differences in annotators' expertise and the inherent blurriness of medical images. Standard approaches that simply average expert labels are flawed, as they discard the valuable clinical uncertainty revealed in disagreements. We introduce a fundamentally new approach with our group decision simulation framework, which works by mimicking the collaborative decision-making process of a clinical panel. Under this framework, an Expert Signature Generator (ESG) learns to represent individual annotator styles in a unique latent space. A Simulated Consultation Module (SCM) then intelligently generates the final segmentation by sampling from this space. This method achieved state-of-the-art results on challenging CBCT and MRI datasets (92.11% and 90.72% Dice scores). By treating expert disagreement as a useful signal instead of noise, our work provides a clear path toward more robust and trustworthy AI systems for healthcare.

cs.CV↗

arXiv2025

Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems

Multi-agent systems powered by Large Language Models (LLM-MAS) have demonstrated remarkable capabilities in collaborative problem-solving. However, their deployment also introduces new security risks. Existing research on LLM-based agents has primarily examined single-agent scenarios, while the security of multi-agent systems remains largely unexplored. To address this gap, we present a systematic study of intention-hiding threats in LLM-MAS. We design four representative attack paradigms that subtly disrupt task completion while maintaining a high degree of stealth, and evaluate them under centralized, decentralized, and layered communication structures. Experimental results show that these attacks are highly disruptive and can easily evade existing defense mechanisms. To counter these threats, we propose AgentXposed, a psychology-inspired detection framework. AgentXposed draws on the HEXACO personality model, which characterizes agents through psychological trait dimensions, and the Reid interrogation technique, a structured method for eliciting concealed intentions. By combining progressive questionnaire probing with behavior-based inter-agent monitoring, the framework enables the proactive identification of malicious agents before harmful actions are carried out. Extensive experiments across six datasets against both our proposed attacks and two baseline threats demonstrate that AgentXposed effectively detects diverse forms of malicious behavior, achieving strong robustness across multiple communication settings.

cs.MA↗

arXiv2025

Physics-Constrained Inc-GAN for Tunnel Propagation Modeling from Sparse Line Measurements

High-speed railway tunnel communication systems require reliable radio wave propagation prediction to ensure operational safety. However, conventional simulation methods face challenges of high computational complexity and inability to effectively process sparse measurement data collected during actual railway operations. This letter proposes an inception-enhanced generative adversarial network (Inc-GAN) that can reconstruct complete electric field distributions across tunnel cross-sections using sparse value lines measured during actual train operations as input. This directly addresses practical railway measurement constraints. Through an inception-based generator architecture and progressive training strategy, the method achieves robust reconstruction from single measurement signal lines to complete field distributions. Numerical simulation validation demonstrates that Inc-GAN can accurately predict electric fields based on measured data collected during actual train operations, with significantly improved computational efficiency compared to traditional methods, providing a novel solution for railway communication system optimization based on real operational data.

eess.SP↗

arXiv2025

A new minimax principle and application to the p-Laplace equation

We introduce a new minimax principle to prove the existence of multi-peak solutions to the Neumann problem of the $p$-Laplace equation $$ -\varepsilon^p Δ_p u = u^{q-1} - u^{p-1} \ \ \text{in}\ Ω,$$ where $\Om$ is a bounded domain in $\mathbb{R}^n$ with smooth boundary, $1<p<n$ and $p<q< \frac{np}{n-p}$. The minimax principle will be applied to the set of peak functions, which is a subset of the Sobolev space $W^{1,p} (Ω)$. The argument is based on a combination of variational method, topological degree theory, and gradient flow.

math.AP↗

arXiv2025

YuE: Scaling Open Foundation Models for Long-Form Music Generation

We tackle the task of long-form music generation--particularly the challenging \textbf{lyrics-to-song} problem--by introducing YuE, a family of open foundation models based on the LLaMA2 architecture. Specifically, YuE scales to trillions of tokens and generates up to five minutes of music while maintaining lyrical alignment, coherent musical structure, and engaging vocal melodies with appropriate accompaniment. It achieves this through (1) track-decoupled next-token prediction to overcome dense mixture signals, (2) structural progressive conditioning for long-context lyrical alignment, and (3) a multitask, multiphase pre-training recipe to converge and generalize. In addition, we redesign the in-context learning technique for music generation, enabling versatile style transfer (e.g., converting Japanese city pop into an English rap while preserving the original accompaniment) and bidirectional generation. Through extensive evaluation, we demonstrate that YuE matches or even surpasses some of the proprietary systems in musicality and vocal agility. In addition, fine-tuning YuE enables additional controls and enhanced support for tail languages. Furthermore, beyond generation, we show that YuE's learned representations can perform well on music understanding tasks, where the results of YuE match or exceed state-of-the-art methods on the MARBLE benchmark. Keywords: lyrics2song, song generation, long-form, foundation model, music generation

eess.AS↗

arXiv2025

Uncovering the network geometry of green bonds

With the rapid growth of the green bond market amid increasing emphasis on sustainable development, understanding its structural properties and potential systemic risks has become essential. This study applies Minimum Spanning Tree (MST) and Hierarchical Tree (HT) methods introduced by Mantegna, which gives a minimum spanning tree of bonds whose mutual distance corresponds to the correlation coefficient of the synchronous time evolution of the difference of the logarithm of their monthly price. Our analysis reveals that green bonds exhibit tighter ultrametric distances on average compared to stocks and conventional bonds, indicating a highly interconnected market structure. We also identify strong sectorial clustering, with green bonds in the utilities sector emerging as the most central nodes by average total betweenness centrality, suggesting their critical role in potential risk propagation. These findings highlight both the opportunities and vulnerabilities inherent in the green bond market, offering insights for investors and policymakers on monitoring concentration, enhancing transparency, and mitigating systemic risks as the market continues to evolve.

physics.soc-ph↗

arXiv2025

A Sparsity Predicting Approach for Large Language Models via Activation Pattern Clustering

Large Language Models (LLMs) exhibit significant activation sparsity, where only a subset of neurons are active for a given input. Although this sparsity presents opportunities to reduce computational cost, efficiently utilizing it requires predicting activation patterns in a scalable manner. However, direct prediction at the neuron level is computationally expensive due to the vast number of neurons in modern LLMs. To enable efficient prediction and utilization of activation sparsity, we propose a clustering-based activation pattern compression framework. Instead of treating each neuron independently, we group similar activation patterns into a small set of representative clusters. Our method achieves up to 79.34% clustering precision, outperforming standard binary clustering approaches while maintaining minimal degradation in perplexity (PPL) scores. With a sufficiently large number of clusters, our approach attains a PPL score as low as 12.49, demonstrating its effectiveness in preserving model quality while reducing computational overhead. By predicting cluster assignments rather than individual neuron states, future models can efficiently infer activation patterns from pre-computed centroids. We detail the clustering algorithm, analyze its effectiveness in capturing meaningful activation structures, and demonstrate its potential to improve sparse computation efficiency. This clustering-based formulation serves as a foundation for future work on activation pattern prediction, paving the way for efficient inference in large-scale language models.

cs.LG↗

arXiv2025

Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale Dataset

Human communication involves a complex interplay of verbal and nonverbal signals, essential for conveying meaning and achieving interpersonal goals. To develop socially intelligent AI technologies, it is crucial to develop models that can both comprehend and generate dyadic behavioral dynamics. To this end, we introduce the Seamless Interaction Dataset, a large-scale collection of over 4,000 hours of face-to-face interaction footage from over 4,000 participants in diverse contexts. This dataset enables the development of AI technologies that understand dyadic embodied dynamics, unlocking breakthroughs in virtual agents, telepresence experiences, and multimodal content analysis tools. We also develop a suite of models that utilize the dataset to generate dyadic motion gestures and facial expressions aligned with human speech. These models can take as input both the speech and visual behavior of their interlocutors. We present a variant with speech from an LLM model and integrations with 2D and 3D rendering methods, bringing us closer to interactive virtual agents. Additionally, we describe controllable variants of our motion models that can adapt emotional responses and expressivity levels, as well as generating more semantically-relevant gestures. Finally, we discuss methods for assessing the quality of these dyadic motion models, which are demonstrating the potential for more intuitive and responsive human-AI interactions.

cs.CV↗

arXiv2025

Genetic Algorithm-Accelerated Computational Discovery of Liquid Crystal Polymers with Enhanced Optical Properties

Liquid crystal polymers with exceptional optical properties are highly promising for next-generation virtual, augmented, and mixed reality (VR/AR/MR) technologies, serving as high-performance, compact, lightweight, and cost-effective optical components. However, the growing demands for optical transparency and high refractive index in advanced optical devices present a challenge for material discovery. In this study, we develop a novel approach that integrates first-principles calculations with genetic algorithms to accelerate the discovery of liquid crystal polymers with low visible absorption and high refractive index. By iterating within a predefined space of molecular building blocks, our approach rapidly identifies reactive mesogens that meet target specifications. Additionally, it provides valuable insights into the relationships between molecular structure and properties. This strategy not only accelerates material screening but also uncovers key molecular design principles, offering a systematic and scalable alternative to traditional trial-and-error methods.

cond-mat.soft↗

arXiv2025

Slow, Nanometer Light Confinement Observed in Atomically Thin TaS2

Extreme light confinement down to the atomic scale has been theoretically predicted for ultrathin, Ta-based transition metal dichalcogenides (TMDs). In this work, we experimentally demonstrate in 2H-TaS$_2$ monolayers and bilayers a lateral confinement ratio up to 300 at large wave vectors of $q = 0.15 \, Å^{-1}$, and slow light behaviour with a group velocity $\sim 10^{-4}c$. Quantitative momentum-resolved electron energy loss spectroscopy (q-EELS) with a momentum resolution of $0.0056 \, Å^{-1}$ was used as a platform for the nanoscale optical measurements. With it, momentum-dispersed, two-dimensional (2D) plasmon resonances were experimentally observed, showing a transition from 2D to 3D Coulomb interaction in the high-momentum regime, equivalent to light confinement volumes of $1\text{-}2 \, \text{nm}^3$. Remarkably, the resonant modes do not enter the electron-hole continuum, predicting even further enhanced optical field confinements for this material at cryogenic temperatures.

cond-mat.mtrl-sci↗

arXiv2025

The positivity-preserving high-order semi-Lagrangian spectral volume method for Vlasov-Poisson equations

In this paper, a novel high order semi-Lagrangian (SL) spectral volume (SV) method is proposed and studied for nonlinear Vlasov-Poisson (VP) simulations via operator splitting. The proposed algorithm combines both advantages of semi-Lagrangian and spectral volume approaches, exhibiting strong stability, robustness under large time steps, arbitrary high-order accuracy in space, local mass conservation, and positivity preservation. Numerical study of the SLSV method applied to the one-dimensional and two-dimensional transport equations, the Vlasov-Poisson system, the classical benchmark problems including Landau damping and two-stream instabilities is conducted, confirming the effectiveness, accuracy, and robustness of our algorithm in addressing complex nonlinear phenomena.

math.NA↗

arXiv2025

Simulator HC: Regression-based Online Simulation of Starting Problem-Solution Pairs for Homotopy Continuation in Geometric Vision

While automatically generated polynomial elimination templates have sparked great progress in the field of 3D computer vision, there remain many problems for which the degree of the constraints or the number of unknowns leads to intractability. In recent years, homotopy continuation has been introduced as a plausible alternative. However, the method currently depends on expensive parallel tracking of all possible solutions in the complex domain, or a classification network for starting problem-solution pairs trained over a limited set of real-world examples. Our innovation lies in a novel approach to finding solution-problem pairs, where we only need to predict a rough initial solution, with the corresponding problem generated by an online simulator. Subsequently, homotopy continuation is applied to track that single solution back to the original problem. We apply this elegant combination to generalized camera resectioning, and also introduce a new solution to the challenging generalized relative pose and scale problem. As demonstrated, the proposed method successfully compensates the raw error committed by the regressor alone, and leads to state-of-the-art efficiency and success rates.

cs.CV↗

arXiv2025

Semantic Web and Creative AI -- A Technical Report from ISWS 2023

The International Semantic Web Research School (ISWS) is a week-long intensive program designed to immerse participants in the field. This document reports a collaborative effort performed by ten teams of students, each guided by a senior researcher as their mentor, attending ISWS 2023. Each team provided a different perspective to the topic of creative AI, substantiated by a set of research questions as the main subject of their investigation. The 2023 edition of ISWS focuses on the intersection of Semantic Web technologies and Creative AI. ISWS 2023 explored various intersections between Semantic Web technologies and creative AI. A key area of focus was the potential of LLMs as support tools for knowledge engineering. Participants also delved into the multifaceted applications of LLMs, including legal aspects of creative content production, humans in the loop, decentralised approaches to multimodal generative AI models, nanopublications and AI for personal scientific knowledge graphs, commonsense knowledge in automatic story and narrative completion, generative AI for art critique, prompt engineering, automatic music composition, commonsense prototyping and conceptual blending, and elicitation of tacit knowledge. As Large Language Models and semantic technologies continue to evolve, new exciting prospects are emerging: a future where the boundaries between creative expression and factual knowledge become increasingly permeable and porous, leading to a world of knowledge that is both informative and inspiring.

cs.AI↗

arXiv2025

The Influence of Initial Connectivity on Biologically Plausible Learning

Understanding how the brain learns can be advanced by investigating biologically plausible learning rules -- those that obey known biological constraints, such as locality, to serve as valid brain learning models. Yet, many studies overlook the role of architecture and initial synaptic connectivity in such models. Building on insights from deep learning, where initialization profoundly affects learning dynamics, we ask a key but underexplored neuroscience question: how does initial synaptic connectivity shape learning in neural circuits? To investigate this, we train recurrent neural networks (RNNs), which are widely used for brain modeling, with biologically plausible learning rules. Our findings reveal that initial weight magnitude significantly influences the learning performance of such rules, mirroring effects previously observed in training with backpropagation through time (BPTT). By examining the maximum Lyapunov exponent before and after training, we uncovered the greater demands that certain initialization schemes place on training to achieve desired information propagation properties. Consequently, we extended the recently proposed gradient flossing method, which regularizes the Lyapunov exponents, to biologically plausible learning and observed an improvement in learning performance. To our knowledge, we are the first to examine the impact of initialization on biologically plausible learning rules for RNNs and to subsequently propose a biologically plausible remedy. Such an investigation can lead to neuroscientific predictions about the influence of initial connectivity on learning dynamics and performance, as well as guide neuromorphic design.

cs.NE↗

arXiv2025

Differential Privacy Preserving Distributed Quantum Computing

Existing quantum computers can only operate with hundreds of qubits in the Noisy Intermediate-Scale Quantum (NISQ) state, while quantum distributed computing (QDC) is regarded as a reliable way to address this limitation, allowing quantum computers to achieve their full computational potential. However, similar to classical distributed computing, QDC also faces the problem of privacy leakage. Existing research has introduced quantum differential privacy (QDP) for privacy protection in central quantum computing, but there is no dedicated privacy protection mechanisms for QDC. To fill this research gap, our paper introduces a novel concept called quantum Rényi differential privacy (QRDP), which incorporates the advantages of classical Rényi DP and is applicable in the QDC domain. Based on the new quantum Rényi divergence, QRDP provides delicate and flexible privacy protection by introducing parameter $α$. In particular, the QRDP composition is well suited for QDC, since it allows for more precise control of the total privacy budget in scenarios requiring multiple quantum operations. We analyze a variety of noise mechanisms that can implement QRDP, and derive the lowest privacy budget provided by these mechanisms. Finally, we investigate the impact of different quantum parameters on QRDP. Through our simulations, we also find that adding noise will make the data less usable, but increase the level of privacy protection.

quant-ph↗