arXiv subjects

Di Wu

Publications and source records attributed to Di Wu.

At least 289 records · Page 16Linked to original sources

arXiv2025

A Comprehensive Survey on Machine Learning Driven Material Defect Detection

Material defects (MD) represent a primary challenge affecting product performance and giving rise to safety issues in related products. The rapid and accurate identification and localization of MD constitute crucial research endeavors in addressing contemporary challenges associated with MD. In recent years, propelled by the swift advancement of machine learning (ML) technologies, particularly exemplified by deep learning, ML has swiftly emerged as the core technology and a prominent research direction for material defect detection (MDD). Through a comprehensive review of the latest literature, we systematically survey the ML techniques applied in MDD into five categories: unsupervised learning, supervised learning, semi-supervised learning, reinforcement learning, and generative learning. We provide a detailed analysis of the main principles and techniques used, together with the advantages and potential challenges associated with these techniques. Furthermore, the survey focuses on the techniques for defect detection in composite materials, which are important types of materials enjoying increasingly wide application in various industries such as aerospace, automotive, construction, and renewable energy. Finally, the survey explores potential future directions in MDD utilizing ML technologies. This survey consolidates ML-based MDD literature and provides a foundation for future research and practice.

cs.CV↗

arXiv2025

Deep Learning Model Inversion Attacks and Defenses: A Comprehensive Survey

The rapid adoption of deep learning in sensitive domains has brought tremendous benefits. However, this widespread adoption has also given rise to serious vulnerabilities, particularly model inversion (MI) attacks, posing a significant threat to the privacy and integrity of personal data. The increasing prevalence of these attacks in applications such as biometrics, healthcare, and finance has created an urgent need to understand their mechanisms, impacts, and defense methods. This survey aims to fill the gap in the literature by providing a structured and in-depth review of MI attacks and defense strategies. Our contributions include a systematic taxonomy of MI attacks, extensive research on attack techniques and defense mechanisms, and a discussion about the challenges and future research directions in this evolving field. By exploring the technical and ethical implications of MI attacks, this survey aims to offer insights into the impact of AI-powered systems on privacy, security, and trust. In conjunction with this survey, we have developed a comprehensive repository to support research on MI attacks and defenses. The repository includes state-of-the-art research papers, datasets, evaluation metrics, and other resources to meet the needs of both novice and experienced researchers interested in MI attacks and defenses, as well as the broader field of AI security and privacy. The repository will be continuously maintained to ensure its relevance and utility. It is accessible at https://github.com/overgter/Deep-Learning-Model-Inversion-Attacks-and-Defenses.

cs.CR↗

arXiv2025

Borodin-Kostochka conjecture for a family of $P_6$-free graphs

Borodin and Kostochka conjectured that every graph $G$ with $Δ\ge9$ satisfies $χ\le$ max $\{ω, Δ-1\}$. Gupta and Pradhan proved the Borodin-Kostochka conjecture for ($P_5$, $C_4$)-free graphs [{\em J. Appl. Math. Comp.} \textbf{65} (2021) 877-884]. In this paper, we prove the Borodin-Kostochka conjecture for ($P_6$, apple, torch)-free graphs, that is, graphs with no induced $P_6$, no induced $C_5$ with a hanging edge, and no induced $C_5$ and $C_4$ sharing exactly an induced $P_3$. This generalizes the result of Gupta and Pradhan from the perspective of allowing the existence of $P_5$.

math.CO↗

arXiv2025

Back to Fundamentals: Low-Level Visual Features Guided Progressive Token Pruning

Vision Transformers (ViTs) excel in semantic segmentation but demand significant computation, posing challenges for deployment on resource-constrained devices. Existing token pruning methods often overlook fundamental visual data characteristics. This study introduces 'LVTP', a progressive token pruning framework guided by multi-scale Tsallis entropy and low-level visual features with twice clustering. It integrates high-level semantics and basic visual attributes for precise segmentation. A novel dynamic scoring mechanism using multi-scale Tsallis entropy weighting overcomes limitations of traditional single-parameter entropy. The framework also incorporates low-level feature analysis to preserve critical edge information while optimizing computational cost. As a plug-and-play module, it requires no architectural changes or additional training. Evaluations across multiple datasets show 20%-45% computational reductions with negligible performance loss, outperforming existing methods in balancing cost and accuracy, especially in complex edge regions.

cs.CV↗

arXiv2025

Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?

Extremely low-resource (XLR) languages lack substantial corpora for training NLP models, motivating the use of all available resources such as dictionaries and grammar books. Machine Translation from One Book (Tanzer et al., 2024) suggests that prompting long-context LLMs with one grammar book enables English-Kalamang translation, an XLR language unseen by LLMs - a noteworthy case of linguistics helping an NLP task. We investigate the source of this translation ability, finding almost all improvements stem from the book's parallel examples rather than its grammatical explanations. We find similar results for Nepali and Guarani, seen low-resource languages, and we achieve performance comparable to an LLM with a grammar book by simply fine-tuning an encoder-decoder translation model. We then investigate where grammar books help by testing two linguistic tasks, grammaticality judgment and gloss prediction, and we explore what kind of grammatical knowledge helps by introducing a typological feature prompt that achieves leading results on these more relevant tasks. We thus emphasise the importance of task-appropriate data for XLR languages: parallel examples for translation, and grammatical data for linguistic tasks. As we find no evidence that long-context LLMs can make effective use of grammatical explanations for XLR translation, we conclude data collection for multilingual XLR tasks such as translation is best focused on parallel data over linguistic description.

cs.CL↗

arXiv2025

CKMDiff: A Generative Diffusion Model for CKM Construction via Inverse Problems with Learned Priors

Channel knowledge map (CKM) is a promising technology to enable environment-aware wireless communications and sensing with greatly enhanced performance, by offering location-specific channel prior information for future wireless networks. One fundamental problem for CKM-enabled wireless systems lies in how to construct high-quality and complete CKM for all locations of interest, based on only limited and noisy on-site channel knowledge data. This problem resembles the long-standing ill-posed inverse problem, which tries to infer from a set of limited and noisy observations the cause factors that produced them. By utilizing the recent advances of solving inverse problems with learned priors using generative artificial intelligence (AI), we propose CKMDiff, a conditional diffusion model that can be applied to perform various tasks for CKM constructions such as denoising, inpainting, and super-resolution, without having to know the physical environment maps or transceiver locations. Furthermore, we propose an environment-aware data augmentation mechanism to enhance the model's ability to learn implicit relations between electromagnetic propagation patterns and spatial-geometric features. Extensive numerical results are provided based on the CKMImageNet and RadioMapSeer datasets, which demonstrate that the proposed CKMDiff achieves state-of-the-art performance, outperforming various benchmark methods.

eess.SP↗

arXiv2025

Tinkering Against Scaling

The ascent of scaling in artificial intelligence research has revolutionized the field over the past decade, yet it presents significant challenges for academic researchers, particularly in computational social science and critical algorithm studies. The dominance of large language models, characterized by their extensive parameters and costly training processes, creates a disparity where only industry-affiliated researchers can access these resources. This imbalance restricts academic researchers from fully understanding their tools, leading to issues like reproducibility in computational social science and a reliance on black-box metaphors in critical studies. To address these challenges, we propose a "tinkering" approach that is inspired by existing works. This method involves engaging with smaller models or components that are manageable for ordinary researchers, fostering hands-on interaction with algorithms. We argue that tinkering is both a way of making and knowing for computational social science and a way of knowing for critical studies, and fundamentally, it is a way of caring that has broader implications for both fields.

cs.CY↗

arXiv2025

Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments

Large language models (LLMs) are being widely applied across various fields, but as tasks become more complex, evaluating their responses is increasingly challenging. Compared to human evaluators, the use of LLMs to support performance evaluation offers a more efficient alternative. However, most studies focus mainly on aligning LLMs' judgments with human preferences, overlooking the existence of biases and mistakes in human judgment. Furthermore, how to select suitable LLM judgments given multiple potential LLM responses remains underexplored. To address these two aforementioned issues, we propose a three-stage meta-judge selection pipeline: 1) developing a comprehensive rubric with GPT-4 and human experts, 2) using three advanced LLM agents to score judgments, and 3) applying a threshold to filter out low-scoring judgments. Compared to methods using a single LLM as both judge and meta-judge, our pipeline introduces multi-agent collaboration and a more comprehensive rubric. Experimental results on the JudgeBench dataset show about 15.55\% improvement compared to raw judgments and about 8.37\% improvement over the single-agent baseline. Our work demonstrates the potential of LLMs as meta-judges and lays the foundation for future research on constructing preference datasets for LLM-as-a-judge reinforcement learning.

cs.AI↗

arXiv2025

LookAhead: Preventing DeFi Attacks via Unveiling Adversarial Contracts

The exploitation of smart contract vulnerabilities in Decentralized Finance (DeFi) has resulted in financial losses exceeding 3 billion US dollars. Existing defense mechanisms primarily focus on detecting and reacting to adversarial transactions executed by attackers that target victim contracts. However, with the emergence of private transaction pools where transactions are sent directly to miners without first appearing in public mempools, current detection tools face significant challenges in identifying attack activities effectively. Based on the fact that most attack logic rely on deploying intermediate smart contracts as supporting components to the exploitation of victim contracts, novel detection methods have been proposed that focus on identifying these adversarial contracts instead of adversarial transactions. However, previous state-of-the-art approaches in this direction have failed to produce results satisfactory enough for real-world deployment. In this paper, we propose LookAhead, a new framework for detecting DeFi attacks via unveiling adversarial contracts. LookAhead leverages common attack patterns, code semantics and intrinsic characteristics found in adversarial smart contracts to train Machine Learning (ML)-based classifiers that can effectively distinguish adversarial contracts from benign ones and make timely predictions of different types of potential attacks. Experiments on our labeled datasets show that LookAhead achieves an F1-score as high as 0.8966, which represents an improvement of over 44.4% compared to the previous state-of-the-art solution, with a False Positive Rate (FPR) at only 0.16%.

cs.CR↗

arXiv2025

Supporting Urban Low-Altitude Economy: Channel Gain Map Inference Based on 3D Conditional GAN

The advancement of advanced air mobility (AAM) in recent years has given rise to the concept of low-altitude economy (LAE). However, the diverse flight activities associated with the emerging LAE applications in urban scenarios confront complex physical environments, which urgently necessitates ubiquitous and reliable communication to guarantee the operation safety of the low-altitude aircraft. As one of promising technologies for the sixth generation (6G) mobile networks, channel knowledge map (CKM) enables the environment-aware communication by constructing a site-specific dataset, thereby providing a priori on-site information for the aircraft to obtain the channel state information (CSI) at arbitrary locations with much reduced online overhead. Diverse base station (BS) deployments in the three-dimensional (3D) urban low-altitude environment require efficient 3D CKM construction to capture spatial channel characteristics with less overhead. Towards this end, this paper proposes a 3D channel gain map (CGM) inference method based on a 3D conditional generative adversarial network (3D-CGAN). Specifically, we first analyze the potential deployment types of BSs in urban low-altitude scenario, and investigate the CGM representation with the corresponding 3D channel gain model. The framework of the proposed 3D-CGAN is then discussed, which is trained by a dataset consisting of existing CGMs. Consequently, the trained 3D-CGAN is capable of inferring the corresponding CGM only based on the BS coordinate without additional measurement. The simulation results demonstrate that the CGMs inferred by the proposed 3D-CGAN outperform those of the benchmark schemes, which can accurately reflect the radio propagation condition in 3D environment.

eess.SP↗

arXiv2025

NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results

This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement. The challenge comprises two tracks: (i) Efficient Video Quality Assessment (KVQ), and (ii) Diffusion-based Image Super-Resolution (KwaiSR). Track 1 aims to advance the development of lightweight and efficient video quality assessment (VQA) models, with an emphasis on eliminating reliance on model ensembles, redundant weights, and other computationally expensive components in the previous IQA/VQA competitions. Track 2 introduces a new short-form UGC dataset tailored for single image super-resolution, i.e., the KwaiSR dataset. It consists of 1,800 synthetically generated S-UGC image pairs and 1,900 real-world S-UGC images, which are split into training, validation, and test sets using a ratio of 8:1:1. The primary objective of the challenge is to drive research that benefits the user experience of short-form UGC platforms such as Kwai and TikTok. This challenge attracted 266 participants and received 18 valid final submissions with corresponding fact sheets, significantly contributing to the progress of short-form UGC VQA and image superresolution. The project is publicly available at https://github.com/lixinustc/KVQE- ChallengeCVPR-NTIRE2025.

eess.IV↗

arXiv2025

Universal thermodynamic topological classes of three-dimensional BTZ black holes

We establish a universal thermodynamic topological classification for three-dimensional static neutral Bañados-Teitelboim-Zanelli (BTZ), charged BTZ, and rotating BTZ black holes. We demonstrate that in all three cases (static neutral BTZ, charged BTZ, and rotating BTZ black holes), both the innermost small black hole states and the outermost large black hole states exhibit stable thermodynamic behavior. In the low-temperature limit, all three cases exhibit a thermodynamically stable small black hole state. Conversely, in the high-temperature limit, each system admits a thermodynamically stable large black hole state. Through this analysis, we have rigorously shown that static neutral, charged, and rotating BTZ black holes are consistently classified within the $W^{1+}$ category. Our results demonstrate that neither the charge parameter nor the rotation parameter exerts significant influence on the universal thermodynamic topological classification of three-dimensional static neutral BTZ black holes. This reveals a fundamental dichotomy: while angular momentum and electric charge dominate the thermodynamic topology of four-dimensional static black holes, their effects become negligible in the three-dimensional static BTZ case, highlighting a dimension-driven divergence in black hole thermodynamic behavior.

hep-th↗

arXiv2025

Multi-Reference UCCSD Variational Quantum Algorithm for Molecular Ground State Energies

We implement the Multi-Reference Unitary Coupled Cluster Singles and Doubles (MR-UCCSD) model with a quantum circuit that conserves the particle number to study the ground state energies of LiH, BeH$_2$, and H$_6$. This approach simplifies the MR-UCCSD computation by integrating quantum computing techniques, and reduces its complexity. As a profit of the better MR states, our MR-UCCSD approach satisfies systematically the predefined errors below 10$^{-5}$ Hartree,which is the highest precision of single reference UCCSD approach, along the whole bond length with only hundreds of CNOT gates, and meets satisfactory the requirements of both computational precision and quantum resource reduction.

quant-ph↗

arXiv2025

CKMImageNet: A Dataset for AI-Based Channel Knowledge Map Towards Environment-Aware Communication and Sensing

With the increasing demand for real-time channel state information (CSI) in sixth-generation (6G) mobile communication networks, channel knowledge map (CKM) emerges as a promising technique, offering a site-specific database that enables environment-awareness and significantly enhances communication and sensing performance by leveraging a priori wireless channel knowledge. However, efficient construction and utilization of CKMs require high-quality, massive, and location-specific channel knowledge data that accurately reflects the real-world environments. Inspired by the great success of ImageNet dataset in advancing computer vision and image understanding in artificial intelligence (AI) community, we introduce CKMImageNet, a dataset developed to bridge AI and environment-aware wireless communications and sensing by integrating location-specific channel knowledge data, high-fidelity environmental maps, and their visual representations. CKMImageNet supports a wide range of AI-driven approaches for CKM construction with spatially consistent and location-specific channel knowledge data, including both supervised and unsupervised, as well as discriminative and generative AI methods.

eess.SP↗

arXiv2025

Hallmarks of terahertz magnon currents in an antiferromagnetic insulator

The efficient transport of spin angular momentum is expected to play a crucial role in future spintronic devices, which potentially operate at frequencies reaching the terahertz range. Antiferromagnetic insulators exhibit significant potential for facilitating ultrafast pure spin currents by terahertz magnons. Consequently, we here use femtosecond laser pulses to trigger ultrafast spin currents across antiferromagnetic NiO thin films in Py|NiO|Pt stacks, where permalloy (Py) and Pt serve as spin-current source and detector respectively. We find that the spin current pulses traversing NiO reach a velocity up to 40 nm/ps and experience increasing delay and broadening as the NiO thickness is increased. We can consistently explain our observations by ballistic transport of incoherent magnon. Our approach has high potential to characterize terahertz magnon transport in magnetic insulators with any kind of magnetic order.

cond-mat.mes-hall↗

arXiv2025

Trisimplicial vertices in (fork, odd parachute)-free graphs

An {\em odd hole} in a graph is an induced subgraph which is a cycle of odd length at least five. An {\em odd parachute} is a graph obtained from an odd hole $H$ by adding a new edge $uv$ such that $x$ is adjacent to $u$ but not to $v$ for each $x\in V(H)$. A graph $G$ is perfectly divisible if for each induced subgraph $H$ of $G$, $V(H)$ can be partitioned into $A$ and $B$ such that $H[A]$ is perfect and $ω(H[B])<ω(H)$. A vertex of a graph is {\em trisimplicial} if its neighbourhood is the union of three cliques. In this paper, we prove that $χ(G)\leq \binom{ω(G)+1}{2}$ if $G$ is a (fork, odd parachute)-free graph by showing that $G$ contains a trisimplicial vertex when $G$ is nonperfectly divisible. This generalizes some results of Karthick, Kaufmann and Sivaraman [{\em Electron. J. Combin.} \textbf{29} (2022) \#P3.19], and Wu and Xu [{\em Discrete Math.} \textbf{347} (2024) 114121]. As a corollary, every nonperfectly divisible claw-free graph contains a trisimplicial vertex.

math.CO↗

arXiv2025

Ultrasound-Guided Robotic Blood Drawing and In Vivo Studies on Submillimetre Vessels of Rats

Billions of vascular access procedures are performed annually worldwide, serving as a crucial first step in various clinical diagnostic and therapeutic procedures. For pediatric or elderly individuals, whose vessels are small in size (typically 2 to 3 mm in diameter for adults and less than 1 mm in children), vascular access can be highly challenging. This study presents an image-guided robotic system aimed at enhancing the accuracy of difficult vascular access procedures. The system integrates a 6-DoF robotic arm with a 3-DoF end-effector, ensuring precise navigation and needle insertion. Multi-modal imaging and sensing technologies have been utilized to endow the medical robot with precision and safety, while ultrasound imaging guidance is specifically evaluated in this study. To evaluate in vivo vascular access in submillimeter vessels, we conducted ultrasound-guided robotic blood drawing on the tail veins (with a diameter of 0.7 plus or minus 0.2 mm) of 40 rats. The results demonstrate that the system achieved a first-attempt success rate of 95 percent. The high first-attempt success rate in intravenous vascular access, even with small blood vessels, demonstrates the system's effectiveness in performing these procedures. This capability reduces the risk of failed attempts, minimizes patient discomfort, and enhances clinical efficiency.

cs.RO↗

arXiv2025

Temporal Gaussian Copula For Clinical Multivariate Time Series Data Imputation

The imputation of the Multivariate time series (MTS) is particularly challenging since the MTS typically contains irregular patterns of missing values due to various factors such as instrument failures, interference from irrelevant data, and privacy regulations. Existing statistical methods and deep learning methods have shown promising results in time series imputation. In this paper, we propose a Temporal Gaussian Copula Model (TGC) for three-order MTS imputation. The key idea is to leverage the Gaussian Copula to explore the cross-variable and temporal relationships based on the latent Gaussian representation. Subsequently, we employ an Expectation-Maximization (EM) algorithm to improve robustness in managing data with varying missing rates. Comprehensive experiments were conducted on three real-world MTS datasets. The results demonstrate that our TGC substantially outperforms the state-of-the-art imputation methods. Additionally, the TGC model exhibits stronger robustness to the varying missing ratios in the test dataset. Our code is available at https://github.com/MVL-Lab/TGC-MTS.

cs.LG↗