arXiv subjects

Xuhui Wang

Publications and source records attributed to Xuhui Wang.

At least 19 recordsLinked to original sources

arXiv2026

LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing

Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency, and reproducibility under strict enterprise constraints. In practice, documents arrive with heterogeneous layouts and formats, semantically rich and context-dependent content, and embedded business rules that current pipelines struggle to process reliably. We introduce LAVA (Logic-Aware Validation and Augmentation), a modular, backbone-agnostic pipeline built on multimodal large language models, that integrates a four-stage design: document-rule retrieval, layout-preserving information extraction, auxiliary metadata enrichment, and auditable symbolic/arithmetic verification. LAVA supports robust rule grounding, fine-grained error attribution, and consistent, traceable end-to-end execution, capabilities essential for high-stakes deployment. Evaluated on a large real-world benchmark with diverse financial documents and dozens of expert-curated validation rules, LAVA outperforms baselines in hallucination control and edge-case handling while maintaining efficient token usage, demonstrating practicality for high-volume, time-critical validation.

cs.AI↗

arXiv2026

FRAMES: Guarded and Dual-Objective Skill Evolution for Agents in Policy-Governed Enterprise Workflows

LLM agents increasingly run policy-bound enterprise workflows such as document auditing, where they must apply rules consistently, ground every value, and stay auditable. Improving these agents is hard: operational feedback is sparse and unlabeled, edits to one rule can regress unrelated cases, and accuracy must improve without inflating inference cost or losing auditability. We present FRAMES, a closed-loop framework that cold-starts deployable skills from existing assets and then evolves them through consensus-based mutation, Pareto selection over accuracy and cost, and an anti-regression guarantee, all while preserving auditability. Deployed on our internal production system, FRAMES attains the best accuracy-cost trade-off among baselines, with the same gains reproduced on tau-bench.

cs.AI↗

arXiv2024

Identifying Influential nodes in Brain Networks via Self-Supervised Graph-Transformer

Studying influential nodes (I-nodes) in brain networks is of great significance in the field of brain imaging. Most existing studies consider brain connectivity hubs as I-nodes. However, this approach relies heavily on prior knowledge from graph theory, which may overlook the intrinsic characteristics of the brain network, especially when its architecture is not fully understood. In contrast, self-supervised deep learning can learn meaningful representations directly from the data. This approach enables the exploration of I-nodes for brain networks, which is also lacking in current studies. This paper proposes a Self-Supervised Graph Reconstruction framework based on Graph-Transformer (SSGR-GT) to identify I-nodes, which has three main characteristics. First, as a self-supervised model, SSGR-GT extracts the importance of brain nodes to the reconstruction. Second, SSGR-GT uses Graph-Transformer, which is well-suited for extracting features from brain graphs, combining both local and global characteristics. Third, multimodal analysis of I-nodes uses graph-based fusion technology, combining functional and structural brain information. The I-nodes we obtained are distributed in critical areas such as the superior frontal lobe, lateral parietal lobe, and lateral occipital lobe, with a total of 56 identified across different experiments. These I-nodes are involved in more brain networks than other regions, have longer fiber connections, and occupy more central positions in structural connectivity. They also exhibit strong connectivity and high node efficiency in both functional and structural networks. Furthermore, there is a significant overlap between the I-nodes and both the structural and functional rich-club. These findings enhance our understanding of the I-nodes within the brain network, and provide new insights for future research in further understanding the brain working mechanisms.

q-bio.NC↗

arXiv2024

Large Language Models for Robotics: Opportunities, Challenges, and Perspectives

Large language models (LLMs) have undergone significant expansion and have been increasingly integrated across various domains. Notably, in the realm of robot task planning, LLMs harness their advanced reasoning and language comprehension capabilities to formulate precise and efficient action plans based on natural language instructions. However, for embodied tasks, where robots interact with complex environments, text-only LLMs often face challenges due to a lack of compatibility with robotic visual perception. This study provides a comprehensive overview of the emerging integration of LLMs and multimodal LLMs into various robotic tasks. Additionally, we propose a framework that utilizes multimodal GPT-4V to enhance embodied task planning through the combination of natural language instructions and robot visual perceptions. Our results, based on diverse datasets, indicate that GPT-4V effectively enhances robot performance in embodied tasks. This extensive survey and evaluation of LLMs and multimodal LLMs across a variety of robotic tasks enriches the understanding of LLM-centric embodied intelligence and provides forward-looking insights toward bridging the gap in Human-Robot-Environment interaction.

cs.RO↗

arXiv2023

Structure, physical properties, and magnetically tunable topological phases in topological semimetal EuCuBi

A single material achieving multiple topological phases can provide potential application for topological spintronics, whereas the candidate materials are very limited. Here, we report the structure, physical properties, and possible emergence of multiple topological phases in the newly discovered, air-stable EuCuBi single crystal. EuCuBi crystallizes in a hexagonal space group P63/mmc (No. 194) in ZrBeSi-type structure with an antiferromagnetic (AFM) ground state below TN = 11.2 K. There is a competition between AFM and ferromagnetic (FM) interactions below TN revealed by electrical resistivity and magnetic susceptibility measurements. With the increasing magnetic field, EuCuBi evolves from the AFM ground state with a small amount of FM component, going through two possible metamagnetic phases, finally reaches the field-induced FM phase. Based on the first-principles calculations, we demonstrate that the Dirac, Weyl, and possible mirror Chern insulator can be achieved in EuCuBi by tuning the temperature and applying magnetic field, making EuCuBi a promising candidate for exploring multiple topological phases.

cond-mat.mtrl-sci↗

arXiv2019

Modified PHT-splines

The local refinement of PHT-splines (polynomial splines over hierarchical T-meshes) is achieved by a simple cross insertion, which may introduce superfluous control points or coefficients. By allowing split-in-half in mesh refinement, modified hierarchical T-meshes are defined. Using this approach, polynomial splines defined over the modified hierarchical T-meshes (modified PHT-splines) are introduced to increase the flexibility of PHT-splines. Numerical examples demonstrate the advantages of our new splines when applied to surface fitting and isogeometric analysis problems with anisotropic features.

math.NA↗

arXiv2016

Scaling of anomalous Hall effect in ferromagnetic thin films

We propose a new scaling law for anomalous Hall effect in ferromagnetic thin films by distinguishing three scattering sources, namely, bulk impurity, phonon, and more importantly a rough surface. This new scaling law fits the recent experimental data excellently with constant coefficients that are independent of temperature and film thickness. This is in stark constrast with previous scaling laws that use temperature/thickness dependent fitting coefficients, and is a strong indicator that this law captures the essential physics. By intepretating the experiments for Fe, Co, and Ni with this new law, we conclude that (i) the phonon-induced skew scattering is unimportant as expected; (ii) contribution from the impurity-induced skew scattering is negative; (iii) the intrinsic (extrinsic) mechanism dominates in Fe (Co), and both the extrinsic and the intrinsic contribution are important in Ni.

cond-mat.mes-hall↗

arXiv2015

Valley-dependent spin-orbit torques in two dimensional hexagonal crystals

We study spin-orbit torques in two dimensional hexagonal crystals such as graphene, silicene, germanene and stanene. The torque possesses two components, a field-like term due to inverse spin galvanic effect and an antidamping torque originating from Berry curvature in mixed spin-$k$ space. In the presence of staggered potential and exchange field, the valley degeneracy can be lifted and we obtain a valley-dependent Berry curvature, leading to a tunable antidamping torque by controlling the valley degree of freedom. The valley imbalance can be as high as 100\% by tuning the bias voltage or magnetization angle. These findings open new venues for the development of current-driven spin-orbit torques by structural design.

cond-mat.mes-hall↗

arXiv2015

Spin Polarization Inversion at Benzene-Absorbed Fe4N Surface

We report a first-principle study on electronic structure and simulation of the spin-polarized scanning tunneling microscopy graphic of a benzene/Fe4N interface. Fe4N is a compound ferromagnet suitable for many spintronic applications. We found that, depending on the particular termination schemes and interface configurations, the spin polarization on the benzene surface shows a rich variety of properties ranging from cosine-type oscillation to polarization inversion. Spin-polarization inversion above benzene is resulting from the hybridizations between C pz and the out-of-plane d orbitals of Fe atom.

cond-mat.mtrl-sci↗

arXiv2015

Geometrically Enhanced Quantum Oscillatory Signal and Nonzero Berry's Phase in Indium Arsenide Surface

In a system accommodating both surface and bulk conduction channels, a long-standing challenge is to extract weak Shubnikov-de Haas oscillation signal in the surface from a large background stemming from the bulk. Conventional methods to suppress the bulk conduction often involve doping, an intrusive approach, to reduce the bulk carrier density. Here we propose a geometric method, i.e. attaching a metal shunt to the indium arsenide epilayer, to redistribute current and thus enhance the oscillation-to-background ratio. This allows us, for the first time, to observe clear quantum oscillations and nonzero Berry's phase at the surface of indium arsenide. We also identify the existence of a Rashba type spin-orbit interaction, on the InAs surface, with a large coupling constant ~ 1 eVA. We anticipate wide applicability of this non-intrusive architecture in similar systems such as topological insulators.

cond-mat.mes-hall↗

arXiv2015

Intraband and interband spin-orbit torques in non-centrosymmetric ferromagnets

Intraband and interband contributions to the current-driven spin-orbit torque in magnetic materials lacking inversion symmetry are theoretically studied using Kubo formula. In addition to the current-driven field-like torque ${\bf T}_{\rm FL}= τ_{\rm FL}{\bf m}\times{\bf u}_{\rm so}$ (${\bf u}_{\rm so}$ being a unit vector determined by the symmetry of the spin-orbit coupling), we explore the intrinsic contribution arising from impurity-independent interband transitions and producing an anti-damping-like torque of the form ${\bf T}_{\rm DL}= τ_{\rm DL}{\bf m}\times({\bf u}_{\rm so}\times{\bf m})$. Analytical expressions are obtained in the model case of a magnetic Rashba two-dimensional electron gas, while numerical calculations have been performed on a dilute magnetic semiconductor (Ga,Mn)As modeled by the Kohn-Luttinger Hamiltonian exchanged coupled to the Mn moments. Parametric dependences of the different torque components and similarities to the analytical results of the Rashba two-dimensional electron gas in the weak disorder limit are described.

cond-mat.mes-hall↗

arXiv2014

Scaling Law of Confined Spin-Hall Effect

We incorporate quantum size effect to investigate the extrinsic spin-Hall effect in ultrathin metal films. A Lippmann-Schwinger formalism based theoretical method, accounting for quantum confinement and surface roughness scattering, is developed to calculate both spin-Hall and longitudinal resistivities and spin-Hall angle. The presence of quantum confinement gives rise to a linear relation $ρ_{sH}=αρ+β$ between the extrinsic spin-Hall resistivity $ρ_{sH}$ and longitudinal charge resistivity $ρ$. The linear term $αρ$ originates from side jump, and the constant $β$ is due to skew scattering. This deviates significantly from the commonly accepted scaling law $ρ_{sH}=aρ^2+bρ$ in a bulk conductor. Thus we call for cautious interpretation of experimental data when applying the scaling law.

cond-mat.mes-hall↗

arXiv2014

Spin Hall effect by surface roughness

The spin Hall effect and its inverse effect, caused by the spin orbit interaction, provide the interconversion between spin current and charge current. Since the effects make it possible to generate and manipulate spin current electrically, how to realize the large effects is an important issue in both physics and applications. To do so, materials with heavy elements, which have strong spin orbit interaction, have been examined so far. Here, we propose a new mechanism to enhance the spin Hall effect without heavy elements, \ie surface roughness in metallic thin films. We examine Cu and Al thin films with surface roughness and find that they give the spin Hall effect comparable to that in bulk Au. We demonstrate that the spin Hall effect induced by surface roughness has the side jump contribution but not skew scattering.

cond-mat.mtrl-sci↗

arXiv2014

Spin-orbit coupled transport and spin torque in a ferromagnetic heterostructure

Ferromagnetic heterostructures provide an ideal platform to explore the nature of spin-orbit torques arising from the interplay mediated by itinerant electrons between a Rashba-type spin-orbit coupling and a ferromagnetic exchange interaction. For such a prototypic system, we develop a set of coupled diffusion equations to describe the diffusive spin dynamics and spin-orbit torques. We characterize the spin torque and its two prominent--out-of-plane and in-plane--components for a wide range of relative strength between the Rashba coupling and ferromagnetic exchange. The symmetry and angular dependence of the spin torque emerging from our simple Rashba model is in an agreement with experiments. The spin diffusion equation can be generalized to incorporate dynamic effect such as spin pumping and magnetic damping.

cond-mat.mes-hall↗

arXiv2013

Tailoring spin-orbit torque in diluted magnetic semiconductors

We study the spin orbit torque arising from an intrinsic linear Dresselhaus spin-orbit coupling in a single layer III-V diluted magnetic semiconductor. We investigate the transport properties and spin torque using the linear response theory and we report here : (1) a strong correlation exists between the angular dependence of the torque and the anisotropy of the Fermi surface; (2) the spin orbit torque depends nonlinearly on the exchange coupling. Our findings suggest the possibility to tailor the spin orbit torque magnitude and angular dependence by structural design.

cond-mat.mes-hall↗

arXiv2013

Angular dependence and symmetry of Rashba spin torque in ferromagnetic heterostructures

In a ferromagnetic heterostructure, the interplay between a Rashba spin-orbit coupling and an exchange field gives rise to a current-driven spin torque. In a realistic device setup, we investigate the Rashba spin torque in the diffusive regime and report two major findings: (i) a nonvanishing torque exists at the edges of the device even when the magnetization and effective Rashba field are aligned; (ii) anisotropic spin relaxation rates driven by the Rashba spin-orbit coupling assign the spin torque a general expression ${\bm T}=T^y_{\para}(θ){\bm m}\times(\hat{\bm y}\times{\bm m})+T^y_{\bot}(θ)\hat{\bm y}\times{\bm m}+T^z_{\para}(θ){\bm m}\times(\hat{\bm z}\times{\bm m})+T^z_{\bot}(θ)\hat{\bm z}\times{\bm m}$, where the coefficients $T_{\para,\bot}^{y,z}$ depend on the magnetization direction. Our results agree with recent experiments.

cond-mat.mes-hall↗

arXiv2013

Pauli spin blockade and the ultrasmall magnetic field effect

Based on the spin-blockade model for organic magnetoresistance we present an analytic expression for the polaron-bipolaron transition rate, taking into account the effective nuclear fields on the sites. We reveal the physics producing qualitatively different magnetoconductance line shapes as well as the ultrasmall magnetic field effect, and we study the role of the ratio between the intersite hopping rate and the typical magnitude of the nuclear fields. Our findings are in agreement with recent experiments and numerical simulations.

cond-mat.mes-hall↗

arXiv2013

Peculiarities of Spin Polarization Inversion at a Thiophene/Cobalt Interface

We perform ab-initio calculations to investigate the spin polarization at the interface between a thiophene molecule and cobalt substrate. We find that the reduced symmetry in the presence of a sulfur atom (in the thiophene molecule) leads to a strong spatial dependence of the spin polarization of the molecule: The two carbon atoms far from the sulfur acquire a polarization opposite to that of the substrate, while the carbon atoms bonded directly to sulfur possess the same polarization as the substrate. We determine the origin of this peculiar spin interface property as well as its impact on the spin transport.

cond-mat.mtrl-sci↗