arXiv subjects

Yongwei Zhang

Publications and source records attributed to Yongwei Zhang.

10 recordsLinked to original sources

arXiv2026

Tangut Word Segmentation under Extreme Resource Scarcity: Integrating Traditional Lexicons and Unlabeled Text

Tangut is an extinct language whose script does not explicitly mark word boundaries. We present the first systematic study of Tangut word segmentation using 2,750 expert-annotated segments(31,893 tokens), traditional lexicons, and unlabeled text. Our framework combines a reliability-calibrated lexicon-lattice representation, explicit distributional statistics, and a lightweight character encoder pretrained with MLM. Segment-level five-fold cross-validation shows that lexical and statistical features raise CRF F1 to approximately 0.91. The full TangutEncoder reaches the highest mean F1 (0.911) and improves recall beyond the labeled training vocabulary. These results demonstrate generalization beyond the limited supervised vocabulary across thematically diverse held-out passages, while document-level transfer remains to be evaluated.

cs.CL↗

arXiv2026

In-depth Analysis of Graph-based RAG in a Unified Framework

Graph-based Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs), improving their factual accuracy, adaptability, interpretability, and trustworthiness. A number of graph-based RAG methods have been proposed in the literature. However, these methods have not been systematically and comprehensively compared under the same experimental settings. In this paper, we first summarize a unified framework to incorporate all graph-based RAG methods from a high-level perspective. We then extensively compare representative graph-based RAG methods over a range of questing-answering (QA) datasets -- from specific questions to abstract questions -- and examine the effectiveness of all methods, providing a thorough analysis of graph-based RAG approaches. As a byproduct of our experimental analysis, we are also able to identify new variants of the graph-based RAG methods over specific QA and abstract QA tasks respectively, by combining existing techniques, which outperform the state-of-the-art methods. Finally, based on these findings, we offer promising research opportunities. We believe that a deeper understanding of the behavior of existing methods can provide new valuable insights for future research.

cs.IR↗

arXiv2026

MSACL: Multi-Step Actor-Critic Learning with Lyapunov Certificates for Exponentially Stabilizing Control

For stabilizing control tasks, model-free reinforcement learning (RL) approaches face numerous challenges, particularly regarding the issues of effectiveness and efficiency in complex high-dimensional environments with limited training data. To address these challenges, we propose Multi-Step Actor-Critic Learning with Lyapunov Certificates (MSACL), a novel approach that integrates exponential stability into off-policy maximum entropy reinforcement learning (MERL). In contrast to existing RL-based approaches that depend on elaborate reward engineering and single-step constraints, MSACL adopts intuitive reward design and exploits multi-step samples to enable exploratory actor-critic learning. Specifically, we first introduce Exponential Stability Labels (ESLs) to categorize training samples and propose a $λ$-weighted aggregation mechanism to learn Lyapunov certificates. Based on these certificates, we further design a stability-aware advantage function to guide policy optimization, thereby promoting rapid Lyapunov descent and robust state convergence. We evaluate MSACL across six benchmarks, comprising four stabilizing and two high-dimensional tracking tasks. Experimental results demonstrate its consistent performance improvements over both standard RL baselines and state-of-the-art Lyapunov-based RL algorithms. Beyond rapid convergence, MSACL exhibits robustness against environmental uncertainties and generalization to unseen reference signals. The source code and benchmarking environments are available at \href{https://github.com/YuanZhe-Xing/MSACL}{https://github.com/YuanZhe-Xing/MSACL}.

cs.LG↗

arXiv2025

Deep Learning-based Techniques for Integrated Sensing and Communication Systems: State-of-the-Art, Challenges, and Opportunities

This article comprehensively reviews recent developments and research on deep learning-based (DL-based) techniques for integrated sensing and communication (ISAC) systems. ISAC, which combines sensing and communication functionalities, is regarded as a key enabler for 6G and beyond networks, as many emerging applications, such as vehicular networks and industrial robotics, necessitate both sensing and communication capabilities for effective operation. A unified platform that provides both functions can reduce hardware complexity, alleviate frequency spectrum congestion, and improve energy efficiency. However, integrating these functionalities on the same hardware requires highly optimized signal processing and system design, introducing significant computational complexity when relying on conventional iterative or optimization-based techniques. As an alternative to conventional techniques, DL-based techniques offer efficient and near-optimal solutions with reduced computational complexity. Hence, such techniques are well-suited for operating under limited computational resources and low latency requirements in real-time systems. DL-based techniques can swiftly and effectively yield near-optimal solutions for a wide range of sophisticated ISAC-related tasks, including waveform design, channel estimation, sensing signal processing, data demodulation, and interference mitigation. Therefore, motivated by these advantages, recent studies have proposed various DL-based approaches for ISAC system design. After briefly introducing DL architectures and ISAC fundamentals, this survey presents a comprehensive and categorized review of state-of-the-art DL-based techniques for ISAC, highlights their key advantages and major challenges, and outlines potential directions for future research.

eess.SP↗

arXiv2025

Navigating Robot Swarm Through a Virtual Tube with Flow-Adaptive Distribution Control

With the rapid development of robot swarm technology and its diverse applications, navigating robot swarms through complex environments has emerged as a critical research direction. To ensure safe navigation and avoid potential collisions with obstacles, the concept of virtual tubes has been introduced to define safe and navigable regions. However, current control methods in virtual tubes face the congestion issues, particularly in narrow ones with low throughput. To address these challenges, we first propose a novel control method that combines a modified artificial potential field (APF) for swarm navigation and density feedback control for distribution regulation. Then we generate a global velocity field that not only ensures collision-free navigation but also achieves locally input-to-state stability (LISS) for density tracking. Finally, numerical simulations and realistic applications validate the effectiveness and advantages of the proposed method in navigating robot swarms through narrow virtual tubes.

cs.RO↗

arXiv2025

Multiscale model reduction and two-level Schwarz preconditioner for H(curl) elliptic problems

This paper addresses the efficient solution of linear systems arising from curl-conforming finite element discretizations of $H(\mathrm{curl})$ elliptic problems with heterogeneous coefficients. We first employ the discrete form of a multiscale spectral generalized finite element method (MS-GFEM) for model reduction and prove that the method exhibits exponential convergence with respect to the number of local degrees of freedom. The proposed method and its convergence analysis are applicable in broad settings, including general heterogeneous ($L^{\infty}$) coefficients, domains and subdomains with nontrivial topology, irregular subdomain geometries, and high-order finite element discretizations. Furthermore, we formulate the method as an iterative solver, yielding a two-level restricted additive Schwarz type preconditioner based on the MS-GFEM coarse space. The GMRES algorithm, applied to the preconditioned system, is shown to converge at a rate of at least $Λ$, where $Λ$ denotes the error bound of the discrete MS-GFEM approximation. Numerical experiments in both two and three dimensions demonstrate the superior performance of the proposed methods in terms of dimensionality reduction.

math.NA↗

arXiv2025

Two-level Restricted Additive Schwarz preconditioner based on Multiscale Spectral Generalized FEM for Heterogeneous Helmholtz Problems

We present and analyze a two-level restricted additive Schwarz (RAS) preconditioner for heterogeneous Helmholtz problems, based on a multiscale spectral generalized finite element method (MS-GFEM) proposed in [C. Ma, C. Alber, and R. Scheichl, SIAM. J. Numer. Anal., 61 (2023), pp. 1546--1584]. The preconditioner uses local solves with impedance boundary conditions, and a global coarse solve based on the MS-GFEM approximation space constructed from local eigenproblems. It is derived by first formulating MS-GFEM as a Richardson iterative method, and without using an oversampling technique, reduces to the preconditioner recently proposed and analyzed in [Q. Hu and Z.Li, arXiv 2402.06905]. We prove that both the Richardson iterative method and the preconditioner used within GMRES converge at a rate of $Λ$ under some reasonable conditions, where $Λ$ denotes the error of the underlying MS-GFEM \rs{approximation}. Notably, the convergence proof of GMRES does not rely on the `Elman theory'. An exponential convergence property of MS-GFEM, resulting from oversampling, ensures that only a few iterations are needed for convergence with a small coarse space. Moreover, the convergence rate $Λ$ is not only independent of the fine-mesh size $h$ and the number of subdomains, but decays with increasing wavenumber $k$. In particular, in the constant-coefficient case, with $h\sim k^{-1-γ}$ for some $γ\in (0,1]$, it holds that $Λ\sim k^{-1+\fracγ{2}}$. We present extensive numerical experiments to illustrate the performance of the preconditioner, including 2D and 3D benchmark geophysics tests, and a high-contrast coefficient example arising in applications.

math.NA↗

arXiv2024

Self-reconfiguration Strategies for Space-distributed Spacecraft

This paper proposes a distributed on-orbit spacecraft assembly algorithm, where future spacecraft can assemble modules with different functions on orbit to form a spacecraft structure with specific functions. This form of spacecraft organization has the advantages of reconfigurability, fast mission response and easy maintenance. Reasonable and efficient on-orbit self-reconfiguration algorithms play a crucial role in realizing the benefits of distributed spacecraft. This paper adopts the framework of imitation learning combined with reinforcement learning for strategy learning of module handling order. A robot arm motion algorithm is then designed to execute the handling sequence. We achieve the self-reconfiguration handling task by creating a map on the surface of the module, completing the path point planning of the robotic arm using A*. The joint planning of the robotic arm is then accomplished through forward and reverse kinematics. Finally, the results are presented in Unity3D.

cs.RO↗

arXiv2020

Efficient multiscale algorithms for simulating nonlocal optical response of metallic nanostructure arrays

In this paper, we consider numerical simulations of the nonlocal optical response of metallic nanostructure arrays inside a dielectric host, which is of particular interest to the nanoplasmonics community due to many unusual properties and potential applications. Mathematically, it is described by Maxwell's equations with discontinuous coefficients coupled with a set of Helmholtz-type equations defined only on the domains of metallic nanostructures. To solve this challenging problem, we develop an efficient multiscale method consisting of three steps. First, we extend the system into the domain occupied by the dielectric medium in a novel way and result in a coupled system with rapidly oscillating coefficients. A rigorous analysis of the error between the solutions of the original system and the extended system is given. Second, we derive the homogenized system and define the multiscale approximate solution for the extended system by using the multiscale asymptotic method. Third, to fix the inaccuracy of the multiscale asymptotic method inside the metallic nanostructures, we solve the original system in each metallic nanostructure separately with boundary conditions given by the multiscale approximate solution. A fast algorithm based on the $LU$ decomposition is proposed for solving the resulting linear systems. By applying the multiscale method, we obtain the results that are in good agreement with those obtained by solving the original system directly at a much lower computational cost. Numerical examples are provided to validate the efficiency and accuracy of the proposed method.

math.NA↗

arXiv2019

Mathematical and numerical analysis of a nonlocal Drude model in nanoplasmonics

In this paper, we consider the frequency-domain Maxwell's equations coupled to a nonlocal Drude model which describes the nonlocal optical response in metallic nanostructures. We prove the existence and uniqueness of weak solutions to the coupled equations. A Galerkin finite element method based on the Raviart--Thomas and Nédélec elements is proposed to solve the equations and the associated error estimates are given. This is the first work on the mathematical and numerical analysis of this model. Numerical examples are presented to verify our theoretical analysis.

math.NA↗