arXiv subjects

Hui Liu

Publications and source records attributed to Hui Liu.

At least 181 records · Page 10Linked to original sources

arXiv2025

UPRPRC: Unified Pipeline for Reproducing Parallel Resources -- Corpus from the United Nations

The quality and accessibility of multilingual datasets are crucial for advancing machine translation. However, previous corpora built from United Nations documents have suffered from issues such as opaque process, difficulty of reproduction, and limited scale. To address these challenges, we introduce a complete end-to-end solution, from data acquisition via web scraping to text alignment. The entire process is fully reproducible, with a minimalist single-machine example and optional distributed computing steps for scalability. At its core, we propose a new Graph-Aided Paragraph Alignment (GAPA) algorithm for efficient and flexible paragraph-level alignment. The resulting corpus contains over 713 million English tokens, more than doubling the scale of prior work. To the best of our knowledge, this represents the largest publicly available parallel corpus composed entirely of human-translated, non-AI-generated content. Our code and corpus are accessible under the MIT License.

cs.CL↗

arXiv2025

Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis

Recent advances in audio-driven avatar video generation have significantly enhanced audio-visual realism. However, existing methods treat instruction conditioning merely as low-level tracking driven by acoustic or visual cues, without modeling the communicative purpose conveyed by the instructions. This limitation compromises their narrative coherence and character expressiveness. To bridge this gap, we introduce Kling-Avatar, a novel cascaded framework that unifies multimodal instruction understanding with photorealistic portrait generation. Our approach adopts a two-stage pipeline. In the first stage, we design a multimodal large language model (MLLM) director that produces a blueprint video conditioned on diverse instruction signals, thereby governing high-level semantics such as character motion and emotions. In the second stage, guided by blueprint keyframes, we generate multiple sub-clips in parallel using a first-last frame strategy. This global-to-local framework preserves fine-grained details while faithfully encoding the high-level intent behind multimodal instructions. Our parallel architecture also enables fast and stable generation of long-duration videos, making it suitable for real-world applications such as digital human livestreaming and vlogging. To comprehensively evaluate our method, we construct a benchmark of 375 curated samples covering diverse instructions and challenging scenarios. Extensive experiments demonstrate that Kling-Avatar is capable of generating vivid, fluent, long-duration videos at up to 1080p and 48 fps, achieving superior performance in lip synchronization accuracy, emotion and dynamic expressiveness, instruction controllability, identity preservation, and cross-domain generalization. These results establish Kling-Avatar as a new benchmark for semantically grounded, high-fidelity audio-driven avatar synthesis.

cs.CV↗

arXiv2025

GSTBench: A Benchmark Study on the Transferability of Graph Self-Supervised Learning

Self-supervised learning (SSL) has shown great promise in graph representation learning. However, most existing graph SSL methods are developed and evaluated under a single-dataset setting, leaving their cross-dataset transferability largely unexplored and limiting their ability to leverage knowledge transfer and large-scale pretraining, factors that are critical for developing generalized intelligence beyond fitting training data. To address this gap and advance foundation model research for graphs, we present GSTBench, the first systematic benchmark for evaluating the transferability of graph SSL methods. We conduct large-scale pretraining on ogbn-papers100M and evaluate five representative SSL methods across a diverse set of target graphs. Our standardized experimental setup decouples confounding factors such as model architecture, dataset characteristics, and adaptation protocols, enabling rigorous comparisons focused solely on pretraining objectives. Surprisingly, we observe that most graph SSL methods struggle to generalize, with some performing worse than random initialization. In contrast, GraphMAE, a masked autoencoder approach, consistently improves transfer performance. We analyze the underlying factors that drive these differences and offer insights to guide future research on transferable graph SSL, laying a solid foundation for the "pretrain-then-transfer" paradigm in graph learning. Our code is available at https://github.com/SongYYYY/GSTBench.

cs.LG↗

arXiv2025

MonoRelief V2: Leveraging Real Data for High-Fidelity Monocular Relief Recovery

This paper presents MonoRelief V2, an end-to-end model designed for directly recovering 2.5D reliefs from single images under complex material and illumination variations. In contrast to its predecessor, MonoRelief V1 [1], which was solely trained on synthetic data, MonoRelief V2 incorporates real data to achieve improved robustness, accuracy and efficiency. To overcome the challenge of acquiring large-scale real-world dataset, we generate approximately 15,000 pseudo real images using a text-to-image generative model, and derive corresponding depth pseudo-labels through fusion of depth and normal predictions. Furthermore, we construct a small-scale real-world dataset (800 samples) via multi-view reconstruction and detail refinement. MonoRelief V2 is then progressively trained on the pseudo-real and real-world datasets. Comprehensive experiments demonstrate its state-of-the-art performance both in depth and normal predictions, highlighting its strong potential for a range of downstream applications. Code is at: https://github.com/glp1001/MonoreliefV2.

cs.CV↗

arXiv2025

$(H,H^2)$-smoothing effect of Navier-Stokes equations with additive white noise on two-dimensional torus

This paper is devoted to the regularity of Navier-Stokes (NS) equations with additive white noise on two-dimensional torus $\mathbb T^2$. Under the conditions that the external force $f(x)$ belongs to the phase space $ H$ and the noise intensity function $h(x)$ satisfies $\|\nabla h\|_{L^\infty} \leq \sqrt πνλ_1$, where $ ν$ is the kinematic viscosity of the fluid and $λ_1$ is the first eigenvalue of the Stokes operator, it was proved that the random NS equations possess a tempered $(H,H^2)$-random attractor whose (box-counting) fractal dimension in $H^2$ is finite. This was achieved by establishing, first, an $H^2$ bounded absorbing set and, second, an $(H,H^2)$-smoothing effect of the system which lifts the compactness and finite-dimensionality of the attractor in $H$ to that in $H^2$. Since the force $f$ belongs only to $H$, the $H^2$-regularity of solutions as well as the $H^2$-bounded absorbing set was constructed by an indirect approach of estimating the $H^2$-distance between the solution of the random NS equations and that of the corresponding deterministic equations.

math.AP↗

arXiv2025

Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization

The increasing sophistication of image manipulation techniques demands robust forensic solutions that can both reliably detect alterations and precisely localize tampered regions. Recent Multimodal Large Language Models (MLLMs) show promise by leveraging world knowledge and semantic understanding for context-aware detection, yet they struggle with perceiving subtle, low-level forensic artifacts crucial for accurate manipulation localization. This paper presents a novel Propose-Rectify framework that effectively bridges semantic reasoning with forensic-specific analysis. In the proposal stage, our approach utilizes a forensic-adapted LLaVA model to generate initial manipulation analysis and preliminary localization of suspicious regions based on semantic understanding and contextual reasoning. In the rectification stage, we introduce a Forensics Rectification Module that systematically validates and refines these initial proposals through multi-scale forensic feature analysis, integrating technical evidence from several specialized filters. Additionally, we present an Enhanced Segmentation Module that incorporates critical forensic cues into SAM's encoded image embeddings, thereby overcoming inherent semantic biases to achieve precise delineation of manipulated regions. By synergistically combining advanced multimodal reasoning with established forensic methodologies, our framework ensures that initial semantic proposals are systematically validated and enhanced through concrete technical evidence, resulting in comprehensive detection accuracy and localization precision. Extensive experimental validation demonstrates state-of-the-art performance across diverse datasets with exceptional robustness and generalization capabilities.

cs.CV↗

arXiv2025

S2Sent: Nested Selectivity Aware Sentence Representation Learning

The combination of Transformer-based encoders with contrastive learning represents the current mainstream paradigm for sentence representation learning. This paradigm is typically based on the hidden states of the last Transformer block of the encoder. However, within Transformer-based encoders, different blocks exhibit varying degrees of semantic perception ability. From the perspective of interpretability, the semantic perception potential of knowledge neurons is modulated by stimuli, thus rational cross-block representation fusion is a direction worth optimizing. To balance the semantic redundancy and loss across block fusion, we propose a sentence representation selection mechanism S\textsuperscript{2}Sent, which integrates a parameterized nested selector downstream of the Transformer-based encoder. This selector performs spatial selection (SS) and nested frequency selection (FS) from a modular perspective. The SS innovatively employs a spatial squeeze based self-gating mechanism to obtain adaptive weights, which not only achieves fusion with low information redundancy but also captures the dependencies between embedding features. The nested FS replaces GAP with different DCT basis functions to achieve spatial squeeze with low semantic loss. Extensive experiments have demonstrated that S\textsuperscript{2}Sent achieves significant improvements over baseline methods with negligible additional parameters and inference latency, while highlighting high integrability and scalability.

cs.CL↗

arXiv2025

$(H,H^3)$-smoothing effect and convergence of solutions of stochastic two-dimensional anisotropic Navier-Stokes equations driven by colored noise

This paper is devoted to the higher regularity and convergence of solutions of anisotropic Navier-Stokes (NS) equations with additive colored noise and white noise on two-dimensional torus $\mathbb T^2$. Under the conditions that the external force $f(\textbf{x})$ belongs to the phase space $ H$ and the noise intensity function $h(\textbf{x})$ satisfies $\|\nabla h\|_{L^\infty} \leq \sqrt{πδ} \frac{νλ_1}{2}$, it was proved that the random anisotropic NS equations possess a tempered $(H,H^2)$-random attractor whose (box-counting) fractal dimension in $H^2$ is finite. This was achieved by establishing, first, an $H^2$ bounded absorbing set and, second, an $(H,H^2)$-smoothing effect of the system which lifts the compactness and finite-dimensionality of the attractor in $H$ to that in $H^2$. Since the force $f$ belongs only to $H$, the $H^2$-regularity of solutions as well as the $H^2$-bounded absorbing set was constructed by an indirect approach of estimating the $H^2$-distance between the solution of the random anisotropic NS equations and that of the corresponding deterministic anisotropic NS equations. When the external force $f(\textbf{x})$ belongs to $H^2$ and the noise intensity function $h(\textbf{x})$ satisfies the Assumption 2, it was proved that the random anisotropic NS equations possess a tempered $(H,H^3)$-random attractor whose (box-counting) fractal dimension in $H^3$ is finite. Finally, we prove the upper semi-continuity of random attractors and the convergence of solutions of (8.3) as $δ\rightarrow0$ in the spaces $(H,H)$, $(H,H^1)$, $(H^1,H^2)$ and $(H^2,H^3)$, respectively.

math.AP↗

arXiv2025

Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models

Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. However, the advancement of T2I diffusion models presents significant risks, as the models could be exploited for malicious purposes, such as generating images with violence or nudity, or creating unauthorized portraits of public figures in inappropriate contexts. To mitigate these risks, concept removal methods have been proposed. These methods aim to modify diffusion models to prevent the generation of malicious and unwanted concepts. Despite these efforts, existing research faces several challenges: (1) a lack of consistent comparisons on a comprehensive dataset, (2) ineffective prompts in harmful and nudity concepts, (3) overlooked evaluation of the ability to generate the benign part within prompts containing malicious concepts. To address these gaps, we propose to benchmark the concept removal methods by introducing a new dataset, Six-CD, along with a novel evaluation metric. In this benchmark, we conduct a thorough evaluation of concept removals, with the experimental observations and discussions offering valuable insights in the field.

cs.CV↗

arXiv2025

Efficient high-quality photon pair generation in modal phase-matched thin-film lithium niobate micro-ring resonators

Efficient generation of high-quality photon pairs is essential for modern quantum technologies. Micro-ring resonator is an ideal platform for studying on-chip photon sources due to strong nonlinear effect, resonant-enhanced optical fields, and high integration. Thin-film lithium niobate (TFLN) micro-ring resonators with periodically poled quasi-phase matching have shown high-quality photon pair generation. However, periodic poling technology remains expensive and requires complex fabrication hindering its scalability and capability for practical application in nonlinear photonic devices. To address this, we propose a scalable approach using TFLN micro-ring resonators based on modal phase matching to achieve cost-effective, efficient high-quality photon-pair generation, significantly simplifying fabrication. We achieved pair generation rates up to 40.2 MHz/mW through spontaneous parametric down-conversion, with coincidence-to-accidental ratios exceeding 1200. By combining micro-ring resonance enhancement with modal phase matching, our approach reduces device size and fabrication cost while maintaining high nonlinear efficiency. These results advance the development of compact, efficient on-chip photon sources for next-generation nonlinear and quantum photonic applications.

physics.optics↗

arXiv2025

A Scalable Pretraining Framework for Link Prediction with Efficient Adaptation

Link Prediction (LP) is a critical task in graph machine learning. While Graph Neural Networks (GNNs) have significantly advanced LP performance recently, existing methods face key challenges including limited supervision from sparse connectivity, sensitivity to initialization, and poor generalization under distribution shifts. We explore pretraining as a solution to address these challenges. Unlike node classification, LP is inherently a pairwise task, which requires the integration of both node- and edge-level information. In this work, we present the first systematic study on the transferability of these distinct modules and propose a late fusion strategy to effectively combine their outputs for improved performance. To handle the diversity of pretraining data and avoid negative transfer, we introduce a Mixture-of-Experts (MoE) framework that captures distinct patterns in separate experts, facilitating seamless application of the pretrained model on diverse downstream datasets. For fast adaptation, we develop a parameter-efficient tuning strategy that allows the pretrained model to adapt to unseen datasets with minimal computational overhead. Experiments on 16 datasets across two domains demonstrate the effectiveness of our approach, achieving state-of-the-art performance on low-resource link prediction while obtaining competitive results compared to end-to-end trained methods, with over 10,000x lower computational overhead.

cs.LG↗

arXiv2025

A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models

With the advancement of web techniques, they have significantly revolutionized various aspects of people's lives. Despite the importance of the web, many tasks performed on it are repetitive and time-consuming, negatively impacting overall quality of life. To efficiently handle these tedious daily tasks, one of the most promising approaches is to advance autonomous agents based on Artificial Intelligence (AI) techniques, referred to as AI Agents, as they can operate continuously without fatigue or performance degradation. In the context of the web, leveraging AI Agents -- termed WebAgents -- to automatically assist people in handling tedious daily tasks can dramatically enhance productivity and efficiency. Recently, Large Foundation Models (LFMs) containing billions of parameters have exhibited human-like language understanding and reasoning capabilities, showing proficiency in performing various complex tasks. This naturally raises the question: `Can LFMs be utilized to develop powerful AI Agents that automatically handle web tasks, providing significant convenience to users?' To fully explore the potential of LFMs, extensive research has emerged on WebAgents designed to complete daily web tasks according to user instructions, significantly enhancing the convenience of daily human life. In this survey, we comprehensively review existing research studies on WebAgents across three key aspects: architectures, training, and trustworthiness. Additionally, several promising directions for future research are explored to provide deeper insights.

cs.AI↗

arXiv2025

Two-spinon effects on the thermal Tonks-Girardeau gas

We study the effects of the two-spinon excitations on the field-field correlator of the Tonks-Girardeau gas. While these excitations have been previously examined in the ground state of the system, their role at finite temperatures remains unexplored. Here, we extend the analysis to the one-dimensional interacting Bose gas at thermal equilibrium, focusing on the one-body correlation function of the infinitely repulsive Lieb-Liniger model. We demonstrate that two-spinon excitations, characterized by two holes within the rapidity distribution, constitute the dominant contribution to the field-field correlator at low temperatures. Furthermore, we analytically show that incorporating additional particle-hole excitations diminishes their contribution, highlighting the efficacy of the two-spinon framework in capturing the essential physics of the system. Numerical evaluations of both the Fredholm determinant and the spectral sum stemming from the two-spinon program, with the addition of particle-hole excitations, reveal convergence at low temperatures.

cond-mat.quant-gas↗

arXiv2025

Examining the Effects of Human-Likeness of Avatars on Emotion Perception and Emotion Elicitation

An increasing number of online interaction settings now provide the possibility to visually represent oneself via an animated avatar instead of a video stream. Benefits include protecting the communicator's privacy while still providing a means to express their individuality. In consequence, there has been a surge in means for avatar-based personalization, ranging from classic human representations to animals, food items, and more. However, using avatars also has drawbacks. Depending on the human-likeness of the avatar and the corresponding disparities between the avatar and the original expresser, avatars may elicit discomfort or even hinder effective nonverbal communication by distorting emotion perception. This study examines the relationship between the human-likeness of virtual avatars and emotion perception for Ekman's six "basic emotions". Research reveals that avatars with varying degrees of human-likeness have distinct effects on emotion perception. High human-likeness avatars, such as human avatars, tend to elicit more negative emotional responses from users, a phenomenon that is consistent with the concept of Uncanny Valley in aesthetics, which suggests that closely resembling humans can provoke negative emotional responses. Conversely, a raccoon avatar and a shark avatar, known as cuteness, which exhibit moderate human similarity in this study, demonstrate a positive influence on emotion perception. Our initial results suggest that the human-likeness of avatars is an important factor for emotion perception. The results from the follow-up study further suggest that the cuteness of avatars and their natural facial status may also play a significant role in emotion perception and elicitation. We discuss practical implications for strategically conveying specific human behavioral messages through avatars in multiple applications, such as business and counseling.

cs.HC↗

arXiv2025

LIDAR: Lightweight Adaptive Cue-Aware Fusion Vision Mamba for Multimodal Segmentation of Structural Cracks

Achieving pixel-level segmentation with low computational cost using multimodal data remains a key challenge in crack segmentation tasks. Existing methods lack the capability for adaptive perception and efficient interactive fusion of cross-modal features. To address these challenges, we propose a Lightweight Adaptive Cue-Aware Vision Mamba network (LIDAR), which efficiently perceives and integrates morphological and textural cues from different modalities under multimodal crack scenarios, generating clear pixel-level crack segmentation maps. Specifically, LIDAR is composed of a Lightweight Adaptive Cue-Aware Visual State Space module (LacaVSS) and a Lightweight Dual Domain Dynamic Collaborative Fusion module (LD3CF). LacaVSS adaptively models crack cues through the proposed mask-guided Efficient Dynamic Guided Scanning Strategy (EDG-SS), while LD3CF leverages an Adaptive Frequency Domain Perceptron (AFDP) and a dual-pooling fusion strategy to effectively capture spatial and frequency-domain cues across modalities. Moreover, we design a Lightweight Dynamically Modulated Multi-Kernel convolution (LDMK) to perceive complex morphological structures with minimal computational overhead, replacing most convolutional operations in LIDAR. Experiments on three datasets demonstrate that our method outperforms other state-of-the-art (SOTA) methods. On the light-field depth dataset, our method achieves 0.8204 in F1 and 0.8465 in mIoU with only 5.35M parameters. Code and datasets are available at https://github.com/Karl1109/LIDAR-Mamba.

cs.CV↗

arXiv2025

Cardiac-CLIP: A Vision-Language Foundation Model for 3D Cardiac CT Images

Foundation models have demonstrated remarkable potential in medical domain. However, their application to complex cardiovascular diagnostics remains underexplored. In this paper, we present Cardiac-CLIP, a multi-modal foundation model designed for 3D cardiac CT images. Cardiac-CLIP is developed through a two-stage pre-training strategy. The first stage employs a 3D masked autoencoder (MAE) to perform self-supervised representation learning from large-scale unlabeled volumetric data, enabling the visual encoder to capture rich anatomical and contextual features. In the second stage, contrastive learning is introduced to align visual and textual representations, facilitating cross-modal understanding. To support the pre-training, we collect 16641 real clinical CT scans, supplemented by 114k publicly available data. Meanwhile, we standardize free-text radiology reports into unified templates and construct the pathology vectors according to diagnostic attributes, based on which the soft-label matrix is generated to supervise the contrastive learning process. On the other hand, to comprehensively evaluate the effectiveness of Cardiac-CLIP, we collect 6,722 real-clinical data from 12 independent institutions, along with the open-source data to construct the evaluation dataset. Specifically, Cardiac-CLIP is comprehensively evaluated across multiple tasks, including cardiovascular abnormality classification, information retrieval and clinical analysis. Experimental results demonstrate that Cardiac-CLIP achieves state-of-the-art performance across various downstream tasks in both internal and external data. Particularly, Cardiac-CLIP exhibits great effectiveness in supporting complex clinical tasks such as the prospective prediction of acute coronary syndrome, which is notoriously difficult in real-world scenarios.

eess.IV↗

arXiv2025

Quantum anomalous Hall crystals in moiré bands with higher Chern number

The realization of fractional Chern insulators in moiré materials has sparked the search for further novel phases of matter in this platform. In particular, recent works have demonstrated the possibility of realizing quantum anomalous Hall crystals (QAHCs), which combine the zero-field quantum Hall effect with spontaneously broken discrete translation symmetry. Here, we employ exact diagonalization to demonstrate the existence of stable QAHCs arising from $\frac{2}{3}$-filled moiré bands with Chern number $C=2$. Our calculations show that these topological crystals, which are characterized by a quantized Hall conductivity of $1$ (in units of $e^2/h$) and a tripled unit cell, are robust in an ideal model of twisted bilayer-trilayer graphene -- providing a novel explanation for experimental observations in this heterostructure. Furthermore, we predict that the QAHC remains robust in a realistic model of twisted double bilayer graphene and, in addition, we provide a range of optimal tuning parameters, namely twist angle and electric field, for experimentally realizing this phase. Overall, our work demonstrates the stability of QAHCs at odd-denominator filling of $C=2$ bands, provides specific guidelines for future experiments, and establishes chiral multilayer graphene as a theoretical platform for studying topological phases beyond the Landau-level paradigm.

cond-mat.mes-hall↗

arXiv2025

An Extended Soliton's Zero Modes

Quantum field theory in the presence of localized solitons is more complicated than vacuum sector quantum field theory, largely as a result of the soliton's zero modes. In the present work, we try to understand to what extent this situation carries over to extended solitons. To this end, we explicitly construct the quantum state corresponding to a domain wall string or membrane, treating the zero modes carefully. This is done both for compact and also infinitely extended solitons. As an application, we calculate the differential probability for a domain wall string's translation mode, with a given momentum, to be excited by a single quantum of incoming radiation.

hep-th↗