arXiv subjects

Xun Zhang

Publications and source records attributed to Xun Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

PIS: A Generalized Physical Inversion Solver for Arbitrary Sparse Observations via Set Conditioned Flow Matching

The estimation of high-dimensional physical parameters constrained by partial differential equations (PDEs) from limited and indirect measurements is a highly ill-posed problem. Traditional methods face significant accuracy and efficiency bottlenecks, particularly when observations are sparse, irregularly sampled, and constrained by real-world sensor placement. We propose the Physical Inversion Solver (PIS), a unified framework that couples Set-Conditioned Flow Matching with a Cosine-Annealed Sparsity Curriculum (CASC) to enable stable inversion from arbitrary, off-grid sensors even under minimal guidance. By leveraging straight-path transport, PIS achieves instantaneous inference (50 NFEs), offering orders-of-magnitude speedup over iterative baselines. Extensive experiments demonstrate that PIS reduces error by up to 88.7% under extreme sparsity (<1%) across subsurface characterization, wave-based characterization, and structural health monitoring, while providing robust uncertainty quantification for optimal sensor placement.

cs.LG↗

arXiv2025

TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Search

Diffusion Transformers (DiTs) have emerged as a highly scalable and effective backbone for image generation, outperforming U-Net architectures in both scalability and performance. However, their real-world deployment remains challenging due to high computational and memory demands. Mixed-Precision Quantization (MPQ), designed to push the limits of quantization, has demonstrated remarkable success in advancing U-Net quantization to sub-4bit settings while significantly reducing computational and memory overhead. Nevertheless, its application to DiT architectures remains limited and underexplored. In this work, we propose TreeQ, a unified framework addressing key challenges in DiT quantization. First, to tackle inefficient search and proxy misalignment, we introduce Tree Structured Search (TSS). This DiT-specific approach leverages the architecture's linear properties to traverse the solution space in O(n) time while improving objective accuracy through comparison-based pruning. Second, to unify optimization objectives, we propose Environmental Noise Guidance (ENG), which aligns Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) configurations using a single hyperparameter. Third, to mitigate information bottlenecks in ultra-low-bit regimes, we design the General Monarch Branch (GMB). This structured sparse branch prevents irreversible information loss, enabling finer detail generation. Through extensive experiments, our TreeQ framework demonstrates state-of-the-art performance on DiT-XL/2 under W3A3 and W4A4 PTQ/PEFT settings. Notably, our work is the first to achieve near-lossless 4-bit PTQ performance on DiT models. The code and models will be available at https://github.com/racoonykc/TreeQ

cs.CV↗

arXiv2025

Diffusion-Inversion-Net (DIN): An End-to-End Direct Probabilistic Framework for Characterizing Hydraulic Conductivities and Quantifying Uncertainty

We propose the Diffusion-Inversion-Net (DIN) framework for inverse modeling of groundwater flow and solute transport processes. DIN utilizes an offline-trained Denoising Diffusion Probabilistic Model (DDPM) as a powerful prior leaner, which flexibly incorporates sparse, multi-source observational data, including hydraulic head, solute concentration, and hard conductivity data, through conditional injection mechanisms. These conditioning inputs subsequently guide the generative inversion process during sampling. Bypassing iterative forward simulations, DIN leverages stochastic sampling and probabilistic modeling mechanisms to directly generate ensembles of posterior parameter fields by repeatedly executing the reverse denoising process. Two representative posterior scenarios, Gaussian and non-Gaussian, are investigated. The results demonstrate that DIN can produce multiple constraint-satisfying realizations under identical observational conditions, accurately estimate hydraulic-conductivity fields, and achieve reliable uncertainty quantification. The framework exhibits strong generalization capability across diverse data distributions, offering a robust and unified alternative to conventional multi-stage inversion methodologies.

physics.geo-ph↗

arXiv2025

Ultrafast Reconfigurable Topological Photonic Processing Accelerator

The rise of artificial intelligence has triggered exponential growth in data volume, demanding rapid and efficient processing. High-speed, energy-efficient, and parallel-scalable computing hardware is thus increasingly critical. We demonstrate a wafer-scale non-volatile topological photonic computing chip using topological modulators. Leveraging the GHz-speed electro-optic response and nonvolatility of ferroelectric lead zirconate titanate (PZT) thin films via topological photonic confinement, Our chip enables thousand-fold faster reconfiguration, zero-static-power operation, and a computational density of 266 trillion operations per second per square millimeter . This density surpasses that of silicon photonic reconfigurable computing chips by two orders of magnitude and thin-film lithium niobate platforms by four orders of magnitude. A 16-channel wavelength-space multiplexed chip delivers 1.92 TOPS throughput with 95.64% digit-recognition accuracy and 94.5% precision for solving time-varying partial differential equations. Additionally, the chip supports functional reconfiguration for high bandwidth density optical I/O. This work establishes ferroelectric topological photonics for efficient high-speed photonic tensor processing.

physics.optics↗

arXiv2025

ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Model

The limited capacity for fine-grained visual perception presents a critical bottleneck for Vision-Language Models (VLMs) in real-world applications. Addressing this is challenging due to the scarcity of high-quality data and the limitations of existing methods: supervised fine-tuning (SFT) often compromises general capabilities, while reinforcement fine-tuning (RFT) prioritizes textual reasoning over visual perception. To bridge this gap, we propose a novel two-stage task that structures visual perception learning as a coarse-to-fine progressive process. Based on this task formulation, we develop ViPER, a self-bootstrapping framework specifically designed to enable iterative evolution through self-critiquing and self-prediction. By synergistically integrating image-level and instance-level reconstruction with a two-stage reinforcement learning strategy, ViPER establishes a closed-loop training paradigm, where internally synthesized data directly fuel the enhancement of perceptual ability. Applied to the Qwen2.5-VL family, ViPER produces the Qwen-Viper series. With an average gain of 1.7% on seven comprehensive benchmarks spanning various tasks and up to 6.0% on fine-grained perception, Qwen-Viper consistently demonstrates superior performance across different vision-language scenarios while maintaining generalizability. Beyond enabling self-improvement in perceptual capabilities, ViPER provides concrete evidence for the reciprocal relationship between generation and understanding, a breakthrough to developing more autonomous and capable VLMs.

cs.CV↗

arXiv2025

Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems

Evaluating and iterating upon recommender systems is crucial, yet traditional A/B testing is resource-intensive, and offline methods struggle with dynamic user-platform interactions. While agent-based simulation is promising, existing platforms often lack a mechanism for user actions to dynamically reshape the environment. To bridge this gap, we introduce RecInter, a novel agent-based simulation platform for recommender systems featuring a robust interaction mechanism. In RecInter platform, simulated user actions (e.g., likes, reviews, purchases) dynamically update item attributes in real-time, and introduced Merchant Agents can reply, fostering a more realistic and evolving ecosystem. High-fidelity simulation is ensured through Multidimensional User Profiling module, Advanced Agent Architecture, and LLM fine-tuned on Chain-of-Thought (CoT) enriched interaction data. Our platform achieves significantly improved simulation credibility and successfully replicates emergent phenomena like Brand Loyalty and the Matthew Effect. Experiments demonstrate that this interaction mechanism is pivotal for simulating realistic system evolution, establishing our platform as a credible testbed for recommender systems research. Our codes are available at https://github.com/jinsong8/RecInter.

cs.CL↗

arXiv2025

A Privacy-Preserving Indoor Localization System based on Hierarchical Federated Learning

Location information serves as the fundamental element for numerous Internet of Things (IoT) applications. Traditional indoor localization techniques often produce significant errors and raise privacy concerns due to centralized data collection. In response, Machine Learning (ML) techniques offer promising solutions by capturing indoor environment variations. However, they typically require central data aggregation, leading to privacy, bandwidth, and server reliability issues. To overcome these challenges, in this paper, we propose a Federated Learning (FL)-based approach for dynamic indoor localization using a Deep Neural Network (DNN) model. Experimental results show that FL has the nearby performance to Centralized Model (CL) while keeping the data privacy, bandwidth efficiency and server reliability. This research demonstrates that our proposed FL approach provides a viable solution for privacy-enhanced indoor localization, paving the way for advancements in secure and efficient indoor localization systems.

cs.LG↗

arXiv2025

Transfer Learning for VLC-based indoor Localization: Addressing Environmental Variability

Accurate indoor localization is crucial in industrial environments. Visible Light Communication (VLC) has emerged as a promising solution, offering high accuracy, energy efficiency, and minimal electromagnetic interference. However, VLC-based indoor localization faces challenges due to environmental variability, such as lighting fluctuations and obstacles. To address these challenges, we propose a Transfer Learning (TL)-based approach for VLC-based indoor localization. Using real-world data collected at a BOSCH factory, the TL framework integrates a deep neural network (DNN) to improve localization accuracy by 47\%, reduce energy consumption by 32\%, and decrease computational time by 40\% compared to the conventional models. The proposed solution is highly adaptable under varying environmental conditions and achieves similar accuracy with only 30\% of the dataset, making it a cost-efficient and scalable option for industrial applications in Industry 4.0.

eess.SP↗

arXiv2025

Filtrations on the derived category of twisted K3 surfaces

We introduce and study the Shen-Yin-Zhao filtration on derived categories of twisted K3 surfaces. A main contribution is the construction of a twisted Beauville-Voisin class $\mathfrak{o}_{\mathscr{X}} \in \operatorname{CH}_0(X)$ that extends fundamental results of O'Grady and Shen-Yin-Zhao \cite{OG13, SYZ20} to twisted settings. This class enables: 1. A derived equivalence-invariant filtration $\mathbf{S}_\bullet(\mathrm{D}^{(1)}(\mathscr{X}))$ preserved under Fourier-Mukai transforms, 2. A birational invariant filtration $\mathbf{S}^{\mathrm{SYZ}}_\bullet \operatorname{CH}_0$ on Bridgeland moduli spaces. We prove $\mathbf{S}^{\mathrm{SYZ}}_\bullet \operatorname{CH}_0$ coincides with Voisin's filtration $\mathbf{S}^{\mathrm{BV}}_\bullet\operatorname{CH}_0$ (Theorem 1.4), providing a canonical candidate for the conjectural Beauville-Voisin filtration. Applications include Bloch's conjecture for (anti)-symplectic automorphisms and existence of algebraically coisotropic subvarieties.

math.AG↗

arXiv2025

Optic Fingerprint(OFP): Enhancing Security in Li-Fi Networks

We present a hardware-integrated security framework for LiFi networks through device fingerprint extraction within the IEEE 802.15.7 protocol. Our Optic Fingerprint (OFP) model utilizes inherent LED nonlinearities to generate amplitude-based feature vectors in time and frequency domains, specifically designed for optical wireless systems. Experimental results with 39 commercial LEDs demonstrate 90.36% classification accuracy across SNR 10-30 dB while maintaining standard compliance, offering a practical physical-layer authentication solution for visible light communication.

eess.SP↗

arXiv2025

Extremely Simple Out-of-distribution Detection for Audio-visual Generalized Zero-shot Learning

Zero-shot Learning(ZSL) attains knowledge transfer from seen classes to unseen classes by exploring auxiliary category information, which is a promising yet difficult research topic. In this field, Audio-Visual Generalized Zero-Shot Learning~(AV-GZSL) has aroused researchers' great interest in which intricate relations within triple modalities~(audio, video, and natural language) render this task quite challenging but highly research-worthy. However, both existing embedding-based and generative-based AV-GZSL methods tend to suffer from domain shift problem a lot and we propose an extremely simple Out-of-distribution~(OOD) detection based AV-GZSL method~(EZ-AVOOD) to further mitigate bias problem by differentiating seen and unseen samples at the initial beginning. EZ-AVOOD accomplishes effective seen-unseen separation by exploiting the intrinsic discriminative information held in class-specific logits and class-agnostic feature subspace without training an extra OOD detector network. Followed by seen-unseen binary classification, we employ two expert models to classify seen samples and unseen samples separately. Compared to existing state-of-the-art methods, our model achieves superior ZSL and GZSL performances on three audio-visual datasets and becomes the new SOTA, which comprehensively demonstrates the effectiveness of the proposed EZ-AVOOD.

cs.CV↗

arXiv2025

Exact Fit Attention in Node-Holistic Graph Convolutional Network for Improved EEG-Based Driver Fatigue Detection

EEG-based fatigue monitoring can effectively reduce the incidence of related traffic accidents. In the past decade, with the advancement of deep learning, convolutional neural networks (CNN) have been increasingly used for EEG signal processing. However, due to the data's non-Euclidean characteristics, existing CNNs may lose important spatial information from EEG, specifically channel correlation. Thus, we propose the node-holistic graph convolutional network (NHGNet), a model that uses graphic convolution to dynamically learn each channel's features. With exact fit attention optimization, the network captures inter-channel correlations through a trainable adjacency matrix. The interpretability is enhanced by revealing critical areas of brain activity and their interrelations in various mental states. In validations on two public datasets, NHGNet outperforms the SOTAs. Specifically, in the intra-subject, NHGNet improved detection accuracy by at least 2.34% and 3.42%, and in the inter-subjects, it improved by at least 2.09% and 15.06%. Visualization research on the model revealed that the central parietal area plays an important role in detecting fatigue levels, whereas the frontal and temporal lobes are essential for maintaining vigilance.

cs.LG↗

arXiv2024

Semantic Convergence: Harmonizing Recommender Systems via Two-Stage Alignment and Behavioral Semantic Tokenization

Large language models (LLMs), endowed with exceptional reasoning capabilities, are adept at discerning profound user interests from historical behaviors, thereby presenting a promising avenue for the advancement of recommendation systems. However, a notable discrepancy persists between the sparse collaborative semantics typically found in recommendation systems and the dense token representations within LLMs. In our study, we propose a novel framework that harmoniously merges traditional recommendation models with the prowess of LLMs. We initiate this integration by transforming ItemIDs into sequences that align semantically with the LLMs space, through the proposed Alignment Tokenization module. Additionally, we design a series of specialized supervised learning tasks aimed at aligning collaborative signals with the subtleties of natural language semantics. To ensure practical applicability, we optimize online inference by pre-caching the top-K results for each user, reducing latency and improving effciency. Extensive experimental evidence indicates that our model markedly improves recall metrics and displays remarkable scalability of recommendation systems.

cs.IR↗

arXiv2024

Explainable Data-driven Share-of-choice Product Line Design Optimization

The share-of-choice (SOC) problem is a widely studied problem for product line design (PLD) where representative customers are sampled from a target population and the percentage of the ones who choose the offered products over outside options over the sample is maximized. The utility maximization framework captures individual choices. A significant challenge is that these utilities are not directly observable and must be estimated from other primitive data. Conjoint analysis is a commonly applied technique for generating such data, where sampled customers rate, rank, or choose between different product alternatives. With the responses, various methods, such as the hierarchical Bayesian method and polyhedral estimation, are employed to estimate the utilities. However, this " estimate-then-optimize" procedure disconnects the decision-making process from the primitive data and thus cannot attribute the PLD decision to the unresolved survey data. To fill the gap, we integrate the polyhedral estimation method into the PLD optimization, which constructs a polyhedron set containing all utilities consistent with the responses. Specifically, we proposed a robust model that maximizes the share-of-choice calculated by the worst-case utility over the polyhedron. The model brings threefold explainability to the PLD problem. First, it enables us to explore the influence of both estimation error and the number of sampled customers through an out-of-sample performance guarantee of the proposed model. Secondly, the linearly tractable equivalent reformulation constructed by the duality allows us to attribute the optimal product line to the survey data through the dual variables. Third, inspired by the fact that the survey questions are associated with columns in the dual reformulation, we propose a column generation approach to identify new questions that most effectively improve the model's objective.

math.OC↗

arXiv2024

Energy Efficiency Optimization Method of WDM Visible Light Communication System for Indoor Broadcasting Networks

This paper introduces a novel approach to optimize energy efficiency in wavelength division multiplexing (WDM) Visible Light Communication (VLC) systems designed for indoor broadcasting networks. A physics-based LED model is integrated into system energy efficiency optimization, enabling quantitative analysis of the critical issue of VLC energy efficiency: the nonlinear interplay between illumination and communication performance. The optimization jointly incorporates constraints on communication quality of each channel, and illumination performance, standardized by the International Commission on Illumination (CIE). The formulated nonlinear optimization problem is solved by the Sequential Quadratic Programming (SQP) algorithm in an experiment-based simulation. An integrated Red-Green-Blue-Yellow Light Emitting Diode (RGBY-LED) is measured for model calibration and three different scenarios are simulated to evaluate the generality of the proposed method. Results demonstrate a double enhancement in performance and a high versatility in accommodating various scenarios. Furthermore, it highlights the importance of balancing communication and illumination imperatives in VLC systems, challenging conventional perceptions focused solely on minimizing power consumption.

eess.SY↗

arXiv2024

Phase transition like behaviors of Propagation of Passenger Stranding phenomena in Subway Networks

The subway as the most important transportation for daily urban commuting is a typical non-equilibrium complex system, composed of 2 types of basic units with service relationship. One challenge to operate it is passengers be stranded at stations, which arise from the spatiotemporal mismatch of supply scale and demand scale. More seriously, there is a special phenomenon of the propagation of passenger stranding (PPS) by forming stranded stations clusters, which significantly reduces the service efficiency. In this study, Beijing subway as an example is studied to reveal the nature of PPS phenomena from a view point of statistical physics. The simulation results demonstrate phase-transition-like behaviors depending on the ratio of service supply scale and demand scale. The transition point can quantitatively characterize the resilience failure threshold of service. The eigen microstate method is used to extracting the fundamental patterns of PPS phenomena. Moreover, this study offers a theoretical foundation for strategies to improve service, such as topological planning and train timetable optimization. The methodology developed in present work has significant implications for study of other service systems.

physics.soc-ph↗

arXiv2024

A Data-Driven Bayesian Nonparametric Approach for Black-Box Optimization

We present a data-driven Bayesian nonparametric approach for global optimization (DaBNO) of stochastic black-box function. The function value depends on the distribution of a random vector. However, this distribution is usually complex and hardly known in practice, and is often inferred from data (realizations of random vectors). The DaBNO accounts for the finite-data error that arises when estimating the distribution and relaxes the commonly-used parametric assumption to reduce the distribution-misspecified error. We show that the DaBNO objective formulation can converge to the true objective asymptotically. We further develop a surrogate-assisted algorithm DaBNO-K to efficiently optimize the proposed objective function based on a carefully designed kernel. Numerical experiments are conducted with several synthetic and practical problems, demonstrating the empirical global convergence of this algorithm and its finite-sample performance.

math.OC↗

arXiv2024

Evaluate and Guard the Wisdom of Crowds: Zero Knowledge Proofs for Crowdsourcing Truth Inference

Crowdsourcing has emerged as a prevalent method for mitigating the risks of correctness and security in outsourced cloud computing. This process involves an aggregator distributing tasks, collecting responses, and aggregating outcomes from multiple data sources. Such an approach harnesses the wisdom of crowds to accomplish complex tasks, enhancing the accuracy of task completion while diminishing the risks associated with the malicious actions of any single entity. However, a critical question arises: How can we ensure that the aggregator performs its role honestly and each contributor's input is fairly evaluated? In response to this challenge, we introduce a novel protocol termed $\mathsf{zkTI}. This scheme guarantees both the honest execution of the aggregation process by the aggregator and the fair evaluation of each data source. It innovatively integrates a cryptographic construct known as zero-knowledge proof with a category of truth inference algorithms for the first time. Under this protocol, the aggregation operates with both correctness and verifiability, while ensuring fair assessment of data source reliability. Experimental results demonstrate the protocol's efficiency and robustness, making it a viable and effective solution in crowdsourcing and cloud computing.

cs.CR↗