arXiv subjects

Yang Lu

Publications and source records attributed to Yang Lu.

At least 73 records · Page 4Linked to original sources

arXiv2026

HyReaL: Clustering Attributed Graph via Hyper-Complex Space Representation Learning

Clustering complex data in the form of attributed graphs has attracted increasing attention, where powerful graph representation is a critical prerequisite. However, the well-known Over-Smoothing (OS) effect makes Graph Convolutional Networks tend to homogenize the representation of graph nodes, while the existing OS solutions focus on alleviating the homogeneity of nodes' embeddings from the aspect of graph topology information, which is inconsistent with the attributed graph clustering objective. Therefore, we introduce hyper-complex space with powerful quaternion feature transformation to enhance the representation learning of the attributes. A generalized \textbf{Hy}per-complex space \textbf{Re}present\textbf{a}tion \textbf{L}earning (\textbf{HyReaL}) model is designed to: 1) bridge arbitrary dimensional attributes to the well-developed quaternion algebra with four parts, and 2) connect the learned representations to more generalized clustering objective without being restricted to a given number of clusters $k$. The novel introduction of quaternion benefits attributed graph clustering from two aspects: 1) enhanced attribute coupling learning capability allows complex attribute information to be sufficiently exploited in clustering, and 2) stronger learning capability makes it unnecessary to stack too many graph convolution layers, naturally alleviating the OS problem. It turns out that the node representations learned by HyReaL are more discriminative and widely suit downstream clustering with different $k$s. Extensive experiments including significance tests, ablation studies, qualitative results, etc., show the superiority of HyReaL.

cs.LG↗

arXiv2026

Capability at a Glance: Design Guidelines for Intuitive Avatars Communicating Augmented Actions in Virtual Reality

Virtual Reality (VR) enables users to engage with capabilities beyond human limitations, but it is not always obvious how to trigger these capabilities. Taking the lens of Affordance, we believe avatar design is the key to solving this issue, which ideally should communicate its capabilities and how to activate them. To understand the current practice, we selected eight capabilities across four categories and invited twelve professional designers to design avatars that communicate the capabilities and their corresponding interactions. From the resulting designs, we formed 16 guidelines to provide general and category-specific recommendations. Then, we validated these guidelines by letting two groups of twelve participants design avatars with and without guidelines. Participants rated the guidelines' clarity and usefulness highly. External judges confirmed that avatars designed with the guidelines were more intuitive in conveying the capabilities and interaction methods. Finally, we demonstrated the applicability of the guidelines in avatar design for four VR applications.

cs.HC↗

arXiv2026

Learning Unbiased Cluster Descriptors for Interpretable Imbalanced Concept Drift Detection

Unlabeled streaming data are usually collected to describe dynamic systems, where concept drift detection is a vital prerequisite to understanding the evolution of systems. However, the drifting concepts are usually imbalanced in most real cases, which brings great challenges to drift detection. That is, the dominant statistics of large clusters can easily mask the drifting of small cluster distributions (also called small concepts), which is known as the `masking effect'. Considering that most existing approaches only detect the overall existence of drift under the assumption of balanced concepts, two critical problems arise: 1) where the small concept is, and 2) how to detect its drift. To address the challenging concept drift detection for imbalanced data, we propose Imbalanced Cluster Descriptor-based Drift Detection (ICD3) approach that is unbiased to the imbalanced concepts. This approach first detects imbalanced concepts by employing a newly designed multi-distribution-granular search, which ensures that the distribution of both small and large concepts is effectively captured. Subsequently, it trains a One-Cluster Classifier (OCC) for each identified concept to carefully monitor their potential drifts in the upcoming data chunks. Since the detection is independently performed for each concept, the dominance of large clusters is thus circumvented. ICD3 demonstrates highly interpretability by specifically locating the drifted concepts, and is robust to the changing of the imbalance ratio of concepts. Comprehensive experiments with multi-aspect ablation studies conducted on various benchmark datasets demonstrate the superiority of ICD3 against the state-of-the-art counterparts.

cs.LG↗

arXiv2026

Learning Unified Distance Metric for Heterogeneous Attribute Data Clustering

Datasets composed of numerical and categorical attributes (also called mixed data hereinafter) are common in real clustering tasks. Differing from numerical attributes that indicate tendencies between two concepts (e.g., high and low temperature) with their values in well-defined Euclidean distance space, categorical attribute values are different concepts (e.g., different occupations) embedded in an implicit space. Simultaneously exploiting these two very different types of information is an unavoidable but challenging problem, and most advanced attempts either encode the heterogeneous numerical and categorical attributes into one type, or define a unified metric for them for mixed data clustering, leaving their inherent connection unrevealed. This paper, therefore, studies the connection among any-type of attributes and proposes a novel Heterogeneous Attribute Reconstruction and Representation (HARR) learning paradigm accordingly for cluster analysis. The paradigm transforms heterogeneous attributes into a homogeneous status for distance metric learning, and integrates the learning with clustering to automatically adapt the metric to different clustering tasks. Differing from most existing works that directly adopt defined distance metrics or learn attribute weights to search clusters in a subspace. We propose to project the values of each attribute into unified learnable multiple spaces to more finely represent and learn the distance metric for categorical data. HARR is parameter-free, convergence-guaranteed, and can more effectively self-adapt to different sought number of clusters $k$. Extensive experiments illustrate its superiority in terms of accuracy and efficiency.

cs.LG↗

arXiv2026

Learning Order Forest for Qualitative-Attribute Data Clustering

Clustering is a fundamental approach to understanding data patterns, wherein the intuitive Euclidean distance space is commonly adopted. However, this is not the case for implicit cluster distributions reflected by qualitative attribute values, e.g., the nominal values of attributes like symptoms, marital status, etc. This paper, therefore, discovered a tree-like distance structure to flexibly represent the local order relationship among intra-attribute qualitative values. That is, treating a value as the vertex of the tree allows to capture rich order relationships among the vertex value and the others. To obtain the trees in a clustering-friendly form, a joint learning mechanism is proposed to iteratively obtain more appropriate tree structures and clusters. It turns out that the latent distance space of the whole dataset can be well-represented by a forest consisting of the learned trees. Extensive experiments demonstrate that the joint learning adapts the forest to the clustering task to yield accurate results. Comparisons of 10 counterparts on 12 real benchmark datasets with significance tests verify the superiority of the proposed method.

stat.ML↗

arXiv2026

A Multi-agent Framework for Physical Laws Discovery

Discovering explicit physical laws has traditionally depended on human intuition and domain expertise. Recent advances in artificial intelligence, particularly large language models (LLMs), offer a new route to accelerate this process by automating key steps from hypothesis generation to interpretable model construction. Here we develop an LLM-based multi-agent framework for physical-law discovery that integrates literature-guided variable selection, hypothesis formulation, symbolic regression, formula derivation, and mechanistic explanation. We validate the framework on three representative materials problems: the glass-forming ability (GFA) of metallic glasses, the Vickers hardness of compounds, and the Young's modulus of multi-component alloys. Using physically and chemically meaningful descriptors as inputs, the discovered formulas achieve strong agreement with reference data, with correlation coefficients up to 0.94 (GFA), 0.86 (hardness), and 0.94 (Young's modulus), while remaining compact and interpretable. Beyond fitting, the Young's modulus formula generalizes to quaternary and quinary alloys, improving prediction accuracy by up to 78.8% relative to the classical rule of mixtures. By integrating cross-disciplinary knowledge, reflection mechanisms, and expert-like reasoning ability into symbolic regression, our AI-centric framework offers a robust and extensible platform for automated physical laws discovery, demonstrating that AI can increasingly serve as an essential role in modern scientific research by thinking and acting like field experts.

cond-mat.mtrl-sci↗

arXiv2026

Near-field effects on cathodoluminescence outcoupling in perovskite thin films

Halide perovskite semiconductors are a promising material for high-efficiency solar cells. Their optical properties can vary within and between crystallographic grains. We present spatially-resolved cathodoluminescence (CL) spectroscopy at 2 keV and 5 keV on polycrystalline CsPbBr3 perovskite films to study these variations at the nanoscale. The CL maps show a strongly reduced intensity near the polycrystalline grain boundaries. We perform numerical simulations of the far-field emission of the electron beam-generated optical near fields using the surface profiles from AFM as input. We find that near grain boundaries the light outcoupling is strongly reduced due to enhanced internal reflection and light trapping at the curved surfaces. Lateral variations in CL intensity inside grains are due to Fabry-Perot-like resonances in the film, with the substrate acting as a back reflector. Our results show that near-field coupling and interference effects can dominate nanoscale luminescence maps of halide perovskite films. The results are broadly relevant for the analysis of cathodoluminescence and photoluminescence of corrugated thin films.

cond-mat.mtrl-sci↗

arXiv2026

Generative metamaterials based on large language models

Mechanical metamaterials utilize intricate architectural designs to achieve advanced properties beyond those of their bulk counterparts. Existing metamaterial designs often rely on design inspirations and extensive experimental and numerical studies operated by design professionals, which can be time- and resource-consuming and limited in exploring the vast design space. Here, we transform metamaterial design by developing ChatMetamaterials based on large language models, a prompt-based generative metamaterial design engine capable of inventing architecture codes, and conducting reasoning-based diagnostics and evolution for complex metamaterial systems based on simple text prompts or hand-drawn sketches. This approach changes the way metamaterials are designed, and provides new opportunities for high-throughput metamaterial discovery.

physics.app-ph↗

arXiv2026

Using Directed Acyclic Graphs to Illustrate Common Biases in Diagnostic Test Accuracy Studies

Background: Diagnostic test accuracy (DTA) studies, like etiological studies, are susceptible to various biases including reference standard error bias, partial verification bias, spectrum effect, confounding, and bias from misassumption of conditional independence. While directed acyclic graphs (DAGs) are widely used in etiological research to identify and illustrate bias structures, they have not been systematically applied to DTA studies. Methods: We developed DAGs to illustrate the causal structures underlying common biases in DTA studies. For each bias, we present the corresponding DAG structure and demonstrate the parallel with equivalent biases in etiological studies. We use real-world examples to illustrate each bias mechanism. Results: We demonstrate that five major biases in DTA studies can be represented using DAGs with clear structural parallels to etiological studies: reference standard error bias corresponds to exposure misclassification, misassumption of conditional independence creates spurious correlations similar to unmeasured confounding, spectrum effect parallels effect modification, confounding operates through backdoor paths in both settings, and partial verification bias mirrors selection bias. These DAG representations reveal the causal mechanisms underlying each bias and suggest appropriate correction strategies. Conclusions: DAGs provide a valuable framework for understanding bias structures in DTA studies and should complement existing quality assessment tools like STARD and QUADAS-2. We recommend incorporating DAGs during study design to prospectively identify potential biases and during reporting to enhance transparency. DAG construction requires interdisciplinary collaboration and sensitivity analyses under alternative causal structures.

stat.ME↗

arXiv2026

zkRansomware: Proof-of-Data Recoverability and Multi-round Game Theoretic Modeling of Ransomware Decisions

Ransomware is still one of the most serious cybersecurity threats. Victims often pay but fail to regain access to their data, while also facing the danger of losing data privacy. These uncertainties heavily shape the attacker-victim dynamics in decision-making. In this paper, we introduce and analyze zkRansomware. This new ransomware model integrates zero-knowledge proofs to enable verifiable data recovery and uses smart contracts to enforce multi-round payments while mitigating the risk of data disclosure and privacy loss. We show that zkRansomware is technically feasible using existing cryptographic and blockchain tools and, perhaps counterintuitively, can align incentives between the attacker and the victim. Finally, we develop a theoretical decision-making framework for zkRansomware that distinguishes it from known ransomware decision models and discusses its implications for ransomware risk analysis and response decision support.

cs.CR↗

arXiv2026

Estimation of the intercept parameter in integrated Galton-Watson processes

We study estimation of the intercept parameter in an integrated Galton-Watson process, a basic building-block for many count-valued time series models. In this unit root setting, the ordinary least squares estimator is inconsistent, whereas an existing weighted least squares (WLS) estimator is consistent only in the case where the process is transient, a condition that depends on the unknown intercept parameter . We propose an alternative WLS estimator based on the new weight function of $1/t$, and show that it is consistent regardless of whether the process is transient or null recurrent, with a convergence rate of $\sqrt{\ln n}$.

math.ST↗

arXiv2025

Embodied AI-Enhanced IoMT Edge Computing: UAV Trajectory Optimization and Task Offloading with Mobility Prediction

Due to their inherent flexibility and autonomous operation, unmanned aerial vehicles (UAVs) have been widely used in Internet of Medical Things (IoMT) to provide real-time biomedical edge computing service for wireless body area network (WBAN) users. In this paper, considering the time-varying task criticality characteristics of diverse WBAN users and the dual mobility between WBAN users and UAV, we investigate the dynamic task offloading and UAV flight trajectory optimization problem to minimize the weighted average task completion time of all the WBAN users, under the constraint of UAV energy consumption. To tackle the problem, an embodied AI-enhanced IoMT edge computing framework is established. Specifically, we propose a novel hierarchical multi-scale Transformer-based user trajectory prediction model based on the users' historical trajectory traces captured by the embodied AI agent (i.e., UAV). Afterwards, a prediction-enhanced deep reinforcement learning (DRL) algorithm that integrates predicted users' mobility information is designed for intelligently optimizing UAV flight trajectory and task offloading decisions. Real-word movement traces and simulation results demonstrate the superiority of the proposed methods in comparison with the existing benchmarks.

cs.NI↗

arXiv2025

Pinching-Antenna System Design under Random LoS and NLoS Channels

Pinching antennas, realized through position-adjustable radiating elements along dielectric waveguides, have emerged as a promising flexible-antenna technology thanks to their ability to dynamically reshape large-scale channel conditions. However, most existing studies focus on idealized LoS-dominated environments, overlooking the stochastic nature of realistic wireless propagation. This paper investigates a more practical multiuser pinching-antenna system under a composite probabilistic channel model that captures distance-dependent LoS blockage and NLoS scattering. To account for both efficiency and reliability aspects of communication, two complementary design metrics are considered: an average signal-to-noise ratio (SNR) metric characterizing long-term throughput and fairness, and an outage-constrained metric ensuring a prescribed reliability level. Based on these metrics, we formulate two optimization problems: the first maximizes the max-min average SNR across users, while the second maximizes a guaranteed SNR threshold under per-user outage constraints. Although both problems are inherently nonconvex, we exploit their underlying monotonic structures and develop low-complexity, bisection-based algorithms that achieve globally optimal solutions using only simple scalar evaluations. Extensive simulations validate the effectiveness of the proposed methods and demonstrate that pinching-antenna systems significantly outperform conventional fixed-antenna designs even under random LoS and NLoS channels.

eess.SP↗

arXiv2025

Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective

Open-vocabulary semantic segmentation (OVSS) employs pixel-level vision-language alignment to associate category-related prompts with corresponding pixels. A key challenge is enhancing the multimodal dense prediction capability, specifically this pixel-level multimodal alignment. Although existing methods achieve promising results by leveraging CLIP's vision-language alignment, they rarely investigate the performance boundaries of CLIP for dense prediction from an interpretability mechanisms perspective. In this work, we systematically investigate CLIP's internal mechanisms and identify a critical phenomenon: analogous to human distraction, CLIP diverts significant attention resources from target regions to irrelevant tokens. Our analysis reveals that these tokens arise from dimension-specific over-activation; filtering them enhances CLIP's dense prediction performance. Consequently, we propose ReFocusing CLIP (RF-CLIP), a training-free approach that emulates human distraction-refocusing behavior to redirect attention from distraction tokens back to target regions, thereby refining CLIP's multimodal alignment granularity. Our method achieves SOTA performance on eight benchmarks while maintaining high inference efficiency.

cs.CV↗

arXiv2025

Break the Tie: Learning Cluster-Customized Category Relationships for Categorical Data Clustering

Categorical attributes with qualitative values are ubiquitous in cluster analysis of real datasets. Unlike the Euclidean distance of numerical attributes, the categorical attributes lack well-defined relationships of their possible values (also called categories interchangeably), which hampers the exploration of compact categorical data clusters. Although most attempts are made for developing appropriate distance metrics, they typically assume a fixed topological relationship between categories when learning distance metrics, which limits their adaptability to varying cluster structures and often leads to suboptimal clustering performance. This paper, therefore, breaks the intrinsic relationship tie of attribute categories and learns customized distance metrics suitable for flexibly and accurately revealing various cluster distributions. As a result, the fitting ability of the clustering algorithm is significantly enhanced, benefiting from the learnable category relationships. Moreover, the learned category relationships are proved to be Euclidean distance metric-compatible, enabling a seamless extension to mixed datasets that include both numerical and categorical attributes. Comparative experiments on 12 real benchmark datasets with significance tests show the superior clustering accuracy of the proposed method with an average ranking of 1.25, which is significantly higher than the 5.21 ranking of the current best-performing method.

cs.LG↗

arXiv2025

The Causal-Noncausal Tail Processes

This paper considers one-dimensional mixed causal/noncausal autoregressive (MAR) processes with heavy tail, usually introduced to model trajectories with patterns including asymmetric peaks and throughs, speculative bubbles, flash crashes, or jumps. We especially focus on the extremal behaviour of these processes when at a given date the process is above a large threshold and emphasize the roles of pure causal and noncausal components of the tail process. We provide the dynamic of the tail process and explain how it can be updated during the life of a speculative bubble. In particular we discuss the prediction of the turning point(s) and introduce pure residual plots as a diagnostic for the bubble episodes.

stat.ME↗

arXiv2025

Progressive Data Dropout: An Embarrassingly Simple Approach to Faster Training

The success of the machine learning field has reliably depended on training on large datasets. While effective, this trend comes at an extraordinary cost. This is due to two deeply intertwined factors: the size of models and the size of datasets. While promising research efforts focus on reducing the size of models, the other half of the equation remains fairly mysterious. Indeed, it is surprising that the standard approach to training remains to iterate over and over, uniformly sampling the training dataset. In this paper we explore a series of alternative training paradigms that leverage insights from hard-data-mining and dropout, simple enough to implement and use that can become the new training standard. The proposed Progressive Data Dropout reduces the number of effective epochs to as little as 12.4% of the baseline. This savings actually do not come at any cost for accuracy. Surprisingly, the proposed method improves accuracy by up to 4.82%. Our approach requires no changes to model architecture or optimizer, and can be applied across standard training pipelines, thus posing an excellent opportunity for wide adoption. Code can be found here: https://github.com/bazyagami/LearningWithRevision

cs.CV↗

arXiv2025

NeurIPT: Foundation Model for Neural Interfaces

Electroencephalography (EEG) has wide-ranging applications, from clinical diagnosis to brain-computer interfaces (BCIs). With the increasing volume and variety of EEG data, there has been growing interest in establishing foundation models (FMs) to scale up and generalize neural decoding. Despite showing early potential, applying FMs to EEG remains challenging due to substantial inter-subject, inter-task, and inter-condition variability, as well as diverse electrode configurations across recording setups. To tackle these open challenges, we propose NeurIPT, a foundation model developed for diverse EEG-based Neural Interfaces with a Pre-trained Transformer by capturing both homogeneous and heterogeneous spatio-temporal characteristics inherent in EEG signals. Temporally, we introduce Amplitude-Aware Masked Pretraining (AAMP), masking based on signal amplitude rather than random intervals, to learn robust representations across varying signal intensities beyond local interpolation. Moreover, this temporal representation is enhanced by a Progressive Mixture-of-Experts (PMoE) architecture, where specialized expert subnetworks are progressively introduced at deeper layers, adapting effectively to the diverse temporal characteristics of EEG signals. Spatially, NeurIPT leverages the 3D physical coordinates of electrodes, enabling effective transfer of embedding across varying EEG settings, and develops Intra-Inter Lobe Pooling (IILP) during fine-tuning to efficiently exploit regional brain features. Empirical evaluations across eight downstream BCI datasets, via fine-tuning, demonstrated NeurIPT consistently achieved state-of-the-art performance, highlighting its broad applicability and robust generalization. Our work pushes forward the state of FMs in EEG and offers insights into scalable and generalizable neural information processing systems.

cs.LG↗