arXiv subjects

Xinyue Liu

Publications and source records attributed to Xinyue Liu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Boosting Meta-Learning for Few-Shot Text Classification via Label-guided Distance Scaling

Few-shot text classification aims to recognize unseen classes with limited labeled text samples. Existing approaches focus on boosting meta-learners by developing complex algorithms in the training stage. However, the labeled samples are randomly selected during the testing stage, so they may not provide effective supervision signals, leading to misclassification. To address this issue, we propose a \textbf{L}abel-guided \textbf{D}istance \textbf{S}caling (LDS) strategy. The core of our method is exploiting label semantics as supervision signals in both the training and testing stages. Specifically, in the training stage, we design a label-guided loss to inject label semantic information, pulling closer the sample representations and corresponding label representations. In the testing stage, we propose a Label-guided Scaler which scales sample representations with label semantics to provide additional supervision signals. Thus, even if labeled sample representations are far from class centers, our Label-guided Scaler pulls them closer to their class centers, thereby mitigating the misclassification. We combine two common meta-learners to verify the effectiveness of the method. Extensive experimental results demonstrate that our approach significantly outperforms state-of-the-art models. All datasets and codes are available at https://anonymous.4open.science/r/Label-guided-Text-Classification.

cs.LG↗

arXiv2026

Interplay between antiferromagnetic spin fluctuation and electron-phonon coupling and the origin of the peak-dip-hump structure in the anti-nodal spectrum of high-$T_{c}$ cuprate superconductors

Electron-phonon coupling is believed to be responsible for many spectral anomalies in the cuprate superconductors. In particular, the $B_{1g}$ buckling mode of the oxygen ion in the $CuO_{2}$ plane has been proposed to be responsible for the dramatic peak-dip-hump(PDH) structure in the anti-nodal spectrum. The recent observation of the exceptional flat quasiparticle dispersion in the anti-nodal region and the sudden suppression of the PDH structure around the pseudogap end point cast doubts on such a scenario. Instead, a scenario involving the coupling to the antiferromagnetic spin fluctuation seems to resolve both puzzles naturally. Here we present a systematic study on the interplay between antiferromagnetic spin fluctuation and electron-phonon coupling in the cuprate superconductors. We show that the coupling strength to the $B_{1g}$ buckling mode is strongly suppressed by the vertex correction caused by the antiferromagnetic spin fluctuation in the $\mathbf{q}\rightarrow 0$ limit as a result of the destructive interference between electron-phonon coupling at electron momentum differ by the antiferromagnetic wave vector. Counterintuitively, we find that the same vertex correction enhances the phonon contribution to the PDH structure. We also find that while the coupling to either the antiferromagnetic spin fluctuation or the $B_{1g}$ buckling mode can generate a PDH structure in the anti-nodal spectrum with similar phenomenologies, the sudden suppression of such a structure around the pseudogap end point should be mainly attributed to the dramatic change in the nature of the spin fluctuation at such a critical doping. We suggest to take the PDH structure in the anti-nodal spectrum as a spectral signature for the emergence of fluctuating local moment in the pseudogap phase and the entrance of a doped Mott insulating state.

cond-mat.str-el↗

arXiv2026

Optical and Hall conductivity of the two dimensional Hubbard model: effective theory description, sign-problem-free Monte Carlo simulation and applications to the cuprate superconductors

Exact formulas for the optical conductivity and the Hall conductivity of the two dimensional Hubbard model are derived in terms of an effective theory description of the local moment fluctuation in the system. In this framework, the quantum Monte Carlo simulation of the electromagnetic response of such a strongly correlated electron system becomes sign-problem-free in many physically relevant cases. In particular, it is sign-problem-free when we assume the widely used Millis-Monien-Pines form for the phenomenological susceptibility in the effective action of the fluctuating local moment, even though these local moments are now subjected to Landau damping as a result of their coupling to the itinerant quasiparticle on the fermi surface. This is true more generally when a $φ^{4}$ term is included in the effective action and is thus not restricted to the Gaussian limit. Here we demonstrate the power of this framework by studying the effect of thermal fluctuation of the local moment on the optical conductivity $σ^{xx}(ω)$ and the Hall conductivity $σ^{xy}(ω)$ of the cuprate superconductors. Both $σ^{xx}(ω)$ and $σ^{xy}(ω)$ calculated are found to exhibit a two-component structure, with a Drude component at low energy and a mid-infrared component at higher energy. Depending on the relative importance of the hole pocket and the electron pocket on the reconstructed fermi surface and the coupling strength to the local moment, the Drude component in $\mathrm{Im}σ^{xy}(ω)$ can be either positive or negative.(full-length abstract can be found in the main text.)

cond-mat.str-el↗

arXiv2025

From Narrative to Action: A Hierarchical LLM-Agent Framework for Human Mobility Generation

Understanding and replicating human mobility requires not only spatial-temporal accuracy but also an awareness of the cognitive hierarchy underlying real-world travel decisions. Traditional agent-based or deep learning models can reproduce statistical patterns of movement but fail to capture the semantic coherence and causal logic of human behavior. Large language models (LLMs) show potential, but struggle to balance creative reasoning with strict structural compliance. This study proposes a Hierarchical LLM-Agent Framework, termed Narrative-to-Action, that integrates high-level narrative reasoning, mid-level reflective planning, and low-level behavioral execution within a unified cognitive hierarchy. At the macro level, one agent is employed as a "creative writer" to produce diary-style narratives rich in motivation and context, then uses another agent as a "structural parser" to convert narratives into machine-readable plans. A dynamic execution module further grounds agents in geographic environments and enables adaptive behavioral adjustments guided by a novel occupation-aware metric, Mobility Entropy by Occupation (MEO), which captures heterogeneous schedule flexibility across different occupational personalities. At the micro level, the agent executes concrete actions-selecting locations, transportation modes, and time intervals-through interaction with an environmental simulation. By embedding this multi-layer cognitive process, the framework produces not only synthetic trajectories that align closely with real-world patterns but also interpretable representations of human decision logic. This research advances synthetic mobility generation from a data-driven paradigm to a cognition-driven simulation, providing a scalable pathway for understanding, predicting, and synthesizing complex urban mobility behaviors through hierarchical LLM agents.

cs.MA↗

arXiv2025

Hexagonal InOI monolayer: a 2D phase-change material combining topological insulator states and piezoelectricity

Two-dimensional (2D) phase-change materials (PCMs) with moderate transition barriers and distinctly contrasting properties are highly desirable for multifunctional devices, yet such systems remain scarce. Using first-principles calculations, we propose a hexagonal InOI monolayer as a promising 2D PCM. This material exhibits two distinct polymorphs: an energetically favorable T$^{\prime}$ phase and a metastable T phase, differentiated by iodine atom positions. The T$^{\prime}$-to-T structural phase transition features a moderate energy barrier $E_b$ of 72.1 meV per formula unit, facilitating reversible switching. Notably, strain engineering tailors the electronic transition, inducing either a metal-to-topological-insulator or a metal-to-normal-insulator transformation. Additionally, this phase transition modulates the piezoelectric response and shifts optical absorption from the infrared to the visible range. These multifunctional properties make 2D hexagonal InOI highly promising for applications in non-volatile memory, low-contact-resistance spintronics, and optical switching devices.

cond-mat.mtrl-sci↗

arXiv2025

Integration of promising piezoelectric and photocatalytic properties in Janus In$XY$ ($X$ = S, Se, Te; $Y$ = Cl, Br, I) monolayers and their heterojunctions

Two-dimensional (2D) Janus materials show great promise as piezoelectric materials and photocatalysts for water splitting. In this work, we systematically investigated the piezoelectric and photocatalytic properties of the hexagonal Janus In$XY$ ($X$ = S, Se, Te; $Y$ = Cl, Br, I) monolayers (MLs) using first-principles calculations. Except for InSeCl ML, the remaining eight In$XY$ MLs are stable and exhibit exceptionally high in-plane piezoelectric coefficients ($|d_{22}|$ = 6.07--155.27 pm/V), which exceed those of most known 2D materials. In$XY$ MLs possess band edges straddling the water redox potentials at pH = 0. Their intrinsic vertical polarization induces an intralayer polarization field $E_{\rm intra}$, leading to low exciton binding energies (0.44--0.78 eV). Moreover, their strong vertical piezoelectric responses ($|d_{32}|$ = 0.34--0.65 pm/V) suggest that in-plane stress can further enhance $E_{\rm intra}$ to facilitate the separation of photogenerated carriers. Additionally, these In$XY$ MLs exhibit high electron mobility (101--899 cm$^2$/V/s) and a pronounced anisotropy ratio in carrier mobility, which effectively suppresses charge recombination. Among them, several stand out: InSI and InSeBr MLs show high electron mobility and a large carrier mobility anisotropy ratio; InSeBr ML exhibits excellent in-plane and out-of-plane piezoelectricity; and InSeBr, InSeI, and InTe$Y$ ($Y$ = Cl, Br, I) MLs show strong visible-light absorption. To optimize performance, we constructed a van der Waals heterojunction (InSI/InSeBr), which demonstrates remarkable photocatalytic properties, including enhanced redox ability, a direct Z-scheme charge transfer pathway, strong visible-light absorption, high carrier mobility, and excellent photocorrosion resistance.

cond-mat.mtrl-sci↗

arXiv2025

NoveltyBench: Evaluating Language Models for Humanlike Diversity

Language models have demonstrated remarkable capabilities on standard benchmarks, yet they struggle increasingly from mode collapse, the inability to generate diverse and novel outputs. Our work introduces NoveltyBench, a benchmark specifically designed to evaluate the ability of language models to produce multiple distinct and high-quality outputs. NoveltyBench utilizes prompts curated to elicit diverse answers and filtered real-world user queries. Evaluating 20 leading language models, we find that current state-of-the-art systems generate significantly less diversity than human writers. Notably, larger models within a family often exhibit less diversity than their smaller counterparts, challenging the notion that capability on standard benchmarks translates directly to generative utility. While prompting strategies like in-context regeneration can elicit diversity, our findings highlight a fundamental lack of distributional diversity in current models, reducing their utility for users seeking varied responses and suggesting the need for new training and evaluation paradigms that prioritize diversity alongside quality.

cs.CL↗

arXiv2025

A fluctuating lattice Boltzmann method for viscoelastic fluid flows

This study introduces a novel fluctuating lattice Boltzmann (LB) method for simulating viscoelastic fluid flows governed by the Oldroyd-B model. In contrast to conventional LB approaches that explicitly compute the divergence of the polymer stress tensor using finite-difference schemes, the proposed method incorporates the polymer stress implicitly by introducing a polymer stress fluctuation term directly into the evolution equation. This treatment avoids the need for stress-gradient computations, and preserves the physical characteristics of viscoelastic fluid flows. The proposed method is validated against four classical benchmark problems: the simplified four-roll mill, planar Poiseuille flow, unsteady Womersley flow, and the three-dimensional Taylor-Green vortex. The numerical results show excellent agreement with analytical solutions and previous numerical results, confirming the method's reliability in viscoelastic fluid dynamics. Moreover, performance evaluations demonstrate that the present model reduces the memory occupancy and enhances computational efficiency, highlighting its potential for large-scale simulations of complex viscoelastic flows systems.

physics.flu-dyn↗

arXiv2025

Local volume-conserving lattice Boltzmann model for incompressible multiphase flows

The Cahn-Hilliard (C-H) equation, as a classical diffusion-interface method of phase-field, has been extensively employed for simulating two-phase fluid dynamics. However, it suffers from a key challenge in the simulation process, specifically the volume conservation of each phase cannot be guaranteed. To address this issue, in this paper, a modified C-H equation for two-phase flow modeling is first introduced, and the basic idea of this model lies in that it combines the profile correction method with the level-set approach, and thus, it effectively improves the deficiency of the classical C-H equation in terms of volume non-conservation of each phase. Based on this modified C-H equation, we further propose an accurate interface-capturing lattice Boltzmann (LB) model. After that, we perform a range of numerical simulations, including two stationary droplets immersed in the gas phase, single vortex, Rayleigh-Plateau fluid instability, and droplet deformation under a shear flow. These simulations illustrate that the proposed LB model has superior performance in maintaining local volume conservation and accurately capturing interfaces. More importantly, compared to the LB model derived from the classical C-H equation, it not only achieves more precise volume conservation for each phase but also provides a more consistent representation of the droplet's interface morphology more consistently, especially in dealing with small droplet problems.

physics.flu-dyn↗

arXiv2025

ONER: Online Experience Replay for Incremental Anomaly Detection

Incremental anomaly detection aims to sequentially identify defects in industrial product lines but suffers from catastrophic forgetting, primarily due to knowledge overwriting during parameter updates and feature conflicts between tasks. In this work, We propose ONER (ONline Experience Replay), an end-to-end framework that addresses these issues by synergistically integrating two types of experience: (1) decomposed prompts, which dynamically generate image-conditioned prompts from reusable modules to retain prior knowledge thus prevent knowledge overwriting, and (2) semantic prototypes, which enforce separability in latent feature spaces at pixel and image levels to mitigate cross-task feature conflicts. Extensive experiments demonstrate the superiority of ONER, achieving state-of-the-art performance with +4.4% Pixel AUROC and +28.3% Pixel AUPR improvements on the MVTec AD dataset over prior methods. Remarkably, ONER achieves this with only 0.019M parameters and 5 training epochs per task, confirming its efficiency and stability for real-world industrial deployment.

cs.CV↗

arXiv2025

Modelling anisotropic Cahn-Hilliard equation with the lattice Boltzmann method

The anisotropic Cahn-Hilliard equation is often used to model the formation of faceted pyramids on nanoscale crystal surfaces. In comparison to the isotropic Cahn-Hilliard model, the nonlinear terms associated with strong anisotropic coefficients present challenges for developing an effective numerical scheme. In this work, we propose a multiple-relaxation-time lattice Boltzmann method to solve the anisotropic Cahn-Hilliard equation. To this end, we reformulate the original equation into a nonlinear convection-diffusion equation with source terms. Then the modified equilibrium distribution function and source terms are incorporated into the computations. Through Chapman-Enskog analysis, it successfully recovers the macroscopic governing equation. To validate the proposed approach, we perform numerical simulations, including cases like droplet deformation and spinodal decomposition. These results consistent with available works, confirming the effectiveness of the proposed approach. Furthermore, the simulations demonstrate that the model adheres to the energy dissipation law, further highlighting the effectiveness of the developed lattice Boltzmann method.

physics.flu-dyn↗

arXiv2024

Hawkes based Representation Learning for Reasoning over Scale-free Community-structured Temporal Knowledge Graphs

Temporal knowledge graph (TKG) reasoning has become a hot topic due to its great value in many practical tasks. The key to TKG reasoning is modeling the structural information and evolutional patterns of the TKGs. While great efforts have been devoted to TKG reasoning, the structural and evolutional characteristics of real-world networks have not been considered. In the aspect of structure, real-world networks usually exhibit clear community structure and scale-free (long-tailed distribution) properties. In the aspect of evolution, the impact of an event decays with the time elapsing. In this paper, we propose a novel TKG reasoning model called Hawkes process-based Evolutional Representation Learning Network (HERLN), which learns structural information and evolutional patterns of a TKG simultaneously, considering the characteristics of real-world networks: community structure, scale-free and temporal decaying. First, we find communities in the input TKG to make the encoding get more similar intra-community embeddings. Second, we design a Hawkes process-based relational graph convolutional network to cope with the event impact-decaying phenomenon. Third, we design a conditional decoding method to alleviate biases towards frequent entities caused by long-tailed distribution. Experimental results show that HERLN achieves significant improvements over the state-of-the-art models.

cs.SI↗

arXiv2024

Unlocking the Potential of Reverse Distillation for Anomaly Detection

Knowledge Distillation (KD) is a promising approach for unsupervised Anomaly Detection (AD). However, the student network's over-generalization often diminishes the crucial representation differences between teacher and student in anomalous regions, leading to detection failures. To addresses this problem, the widely accepted Reverse Distillation (RD) paradigm designs the asymmetry teacher and student, using an encoder as teacher and a decoder as student. Yet, the design of RD does not ensure that the teacher encoder effectively distinguishes between normal and abnormal features or that the student decoder generates anomaly-free features. Additionally, the absence of skip connections results in a loss of fine details during feature reconstruction. To address these issues, we propose RD with Expert, which introduces a novel Expert-Teacher-Student network for simultaneous distillation of both the teacher encoder and student decoder. The added expert network enhances the student's ability to generate normal features and optimizes the teacher's differentiation between normal and abnormal features, reducing missed detections. Additionally, Guided Information Injection is designed to filter and transfer features from teacher to student, improving detail reconstruction and minimizing false positives. Experiments on several benchmarks prove that our method outperforms existing unsupervised AD methods under RD paradigm, fully unlocking RD's potential.

cs.CV↗

arXiv2024

Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection

Knowledge distillation based on student-teacher network is one of the mainstream solution paradigms for the challenging unsupervised Anomaly Detection task, utilizing the difference in representation capabilities of the teacher and student networks to implement anomaly localization. However, over-generalization of the student network to the teacher network may lead to negligible differences in representation capabilities of anomaly, thus affecting the detection effectiveness. Existing methods address the possible over-generalization by using differentiated students and teachers from the structural perspective or explicitly expanding distilled information from the content perspective, which inevitably result in an increased likelihood of underfitting of the student network and poor anomaly detection capabilities in anomaly center or edge. In this paper, we propose Dual-Modeling Decouple Distillation (DMDD) for the unsupervised anomaly detection. In DMDD, a Decouple Student-Teacher Network is proposed to decouple the initial student features into normality and abnormality features. We further introduce Dual-Modeling Distillation based on normal-anomaly image pairs, fitting normality features of anomalous image and the teacher features of the corresponding normal image, widening the distance between abnormality features and the teacher features in anomalous regions. Synthesizing these two distillation ideas, we achieve anomaly detection which focuses on both edge and center of anomaly. Finally, a Multi-perception Segmentation Network is proposed to achieve focused anomaly map fusion based on multiple attention. Experimental results on MVTec AD show that DMDD surpasses SOTA localization performance of previous knowledge distillation-based methods, reaching 98.85% on pixel-level AUC and 96.13% on PRO.

cs.CV↗

arXiv2024

Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the Tasks

Meta-learning has emerged as a prominent technology for few-shot text classification and has achieved promising performance. However, existing methods often encounter difficulties in drawing accurate class prototypes from support set samples, primarily due to probable large intra-class differences and small inter-class differences within the task. Recent approaches attempt to incorporate external knowledge or pre-trained language models to augment data, but this requires additional resources and thus does not suit many few-shot scenarios. In this paper, we propose a novel solution to address this issue by adequately leveraging the information within the task itself. Specifically, we utilize label information to construct a task-adaptive metric space, thereby adaptively reducing the intra-class differences and magnifying the inter-class differences. We further employ the optimal transport technique to estimate class prototypes with query set samples together, mitigating the problem of inaccurate and ambiguous support set samples caused by large intra-class differences. We conduct extensive experiments on eight benchmark datasets, and our approach shows obvious advantages over state-of-the-art models across all the tasks on all the datasets. For reproducibility, all the datasets and codes are available at https://github.com/YvoGao/LAQDA.

cs.CV↗

arXiv2024

Multi-UAV Enabled MEC Networks: Optimizing Delay through Intelligent 3D Trajectory Planning and Resource Allocation

Mobile Edge Computing (MEC) reduces the computational burden on terminal devices by shortening the distance between these devices and computing nodes. Integrating Unmanned Aerial Vehicles (UAVs) with enhanced MEC networks can leverage the high mobility of UAVs to flexibly adjust network topology, further expanding the applicability of MEC. However, in highly dynamic and complex real-world environments, it is crucial to balance task offloading effectiveness with algorithm performance. This paper investigates a multi-UAV communication network equipped with edge computing nodes to assist terminal users in task computation. Our goal is to reduce the task processing delay for users through the joint optimization of discrete computation modes, continuous 3D trajectories, and resource assignment. To address the challenges posed by the mixed action space, we propose a Multi-UAV Edge Computing Resource Scheduling (MUECRS) algorithm, which comprises two key components: 1) trajectory optimization, and 2) computation mode and resource management. Experimental results demonstrate our method effectively designs the 3D flight trajectories of UAVs, enabling rapid terminal coverage. Furthermore, the proposed algorithm achieves efficient resource deployment and scheduling, outperforming comparative algorithms by at least 16.7%, demonstrating superior adaptability and robustness.

cs.MA↗

arXiv2024

Customizing Large Language Model Generation Style using Parameter-Efficient Finetuning

One-size-fits-all large language models (LLMs) are increasingly being used to help people with their writing. However, the style these models are trained to write in may not suit all users or use cases. LLMs would be more useful as writing assistants if their idiolect could be customized to match each user. In this paper, we explore whether parameter-efficient finetuning (PEFT) with Low-Rank Adaptation can effectively guide the style of LLM generations. We use this method to customize LLaMA-2 to ten different authors and show that the generated text has lexical, syntactic, and surface alignment with the target author but struggles with content memorization. Our findings highlight the potential of PEFT to support efficient, user-level customization of LLMs.

cs.CL↗

arXiv2024

GNSS Interference Classification Using Federated Reservoir Computing

The expanding use of Unmanned Aerial Vehicles (UAVs) in vital areas like traffic management, surveillance, and environmental monitoring highlights the need for robust communication and navigation systems. Particularly vulnerable are Global Navigation Satellite Systems (GNSS), which face a spectrum of interference and jamming threats that can significantly undermine their performance. While traditional deep learning approaches are adept at mitigating these issues, they often fall short for UAV applications due to significant computational demands and the complexities of managing large, centralized datasets. In response, this paper introduces Federated Reservoir Computing (FedRC) as a potent and efficient solution tailored to enhance interference classification in GNSS systems used by UAVs. Our experimental results demonstrate that FedRC not only achieves faster convergence but also sustains lower loss levels than traditional models, highlighting its exceptional adaptability and operational efficiency.

eess.SP↗