arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 577 records · Page 32Linked to original sources

arXiv2025

Burst Image Super-Resolution via Multi-Cross Attention Encoding and Multi-Scan State-Space Decoding

Multi-image super-resolution (MISR) can achieve higher image quality than single-image super-resolution (SISR) by aggregating sub-pixel information from multiple spatially shifted frames. Among MISR tasks, burst super-resolution (BurstSR) has gained significant attention due to its wide range of applications. Recent methods have increasingly adopted Transformers over convolutional neural networks (CNNs) in super-resolution tasks, due to their superior ability to capture both local and global context. However, most existing approaches still rely on fixed and narrow attention windows that restrict the perception of features beyond the local field. This limitation hampers alignment and feature aggregation, both of which are crucial for high-quality super-resolution. To address these limitations, we propose a novel feature extractor that incorporates two newly designed attention mechanisms: overlapping cross-window attention and cross-frame attention, enabling more precise and efficient extraction of sub-pixel information across multiple frames. Furthermore, we introduce a Multi-scan State-Space Module with the cross-frame attention mechanism to enhance feature aggregation. Extensive experiments on both synthetic and real-world benchmarks demonstrate the superiority of our approach. Additional evaluations on ISO 12233 resolution test charts further confirm its enhanced super-resolution performance.

cs.CV↗

arXiv2025

HaloGS: Loose Coupling of Compact Geometry and Gaussian Splats for 3D Scenes

High fidelity 3D reconstruction and rendering hinge on capturing precise geometry while preserving photo realistic detail. Most existing methods either fuse these goals into a single cumbersome model or adopt hybrid schemes whose uniform primitives lead to a trade off between efficiency and fidelity. In this paper, we introduce HaloGS, a dual representation that loosely couples coarse triangles for geometry with Gaussian primitives for appearance, motivated by the lightweight classic geometry representations and their proven efficiency in real world applications. Our design yields a compact yet expressive model capable of photo realistic rendering across both indoor and outdoor environments, seamlessly adapting to varying levels of scene complexity. Experiments on multiple benchmark datasets demonstrate that our method yields both compact, accurate geometry and high fidelity renderings, especially in challenging scenarios where robust geometric structure make a clear difference.

cs.CV↗

arXiv2025

MOSLIM:Align with diverse preferences in prompts through reward classification

The multi-objective alignment of Large Language Models (LLMs) is essential for ensuring foundational models conform to diverse human preferences. Current research in this field typically involves either multiple policies or multiple reward models customized for various preferences, or the need to train a preference-specific supervised fine-tuning (SFT) model. In this work, we introduce a novel multi-objective alignment method, MOSLIM, which utilizes a single reward model and policy model to address diverse objectives. MOSLIM provides a flexible way to control these objectives through prompting and does not require preference training during SFT phase, allowing thousands of off-the-shelf models to be directly utilized within this training framework. MOSLIM leverages a multi-head reward model that classifies question-answer pairs instead of scoring them and then optimize policy model with a scalar reward derived from a mapping function that converts classification results from reward model into reward scores. We demonstrate the efficacy of our proposed method across several multi-objective benchmarks and conduct ablation studies on various reward model sizes and policy optimization methods. The MOSLIM method outperforms current multi-objective approaches in most results while requiring significantly fewer GPU computing resources compared with existing policy optimization methods.

cs.CL↗

arXiv2025

A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion

Entity set expansion, taxonomy expansion, and seed-guided taxonomy construction are three representative tasks that can be applied to automatically populate an existing taxonomy with emerging concepts. Previous studies view them as three separate tasks. Therefore, their proposed techniques usually work for one specific task only, lacking generalizability and a holistic perspective. In this paper, we aim at a unified solution to the three tasks. To be specific, we identify two common skills needed for entity set expansion, taxonomy expansion, and seed-guided taxonomy construction: finding "siblings" and finding "parents". We propose a taxonomy-guided instruction tuning framework to teach a large language model to generate siblings and parents for query entities, where the joint pre-training process facilitates the mutual enhancement of the two skills. Extensive experiments on multiple benchmark datasets demonstrate the efficacy of our proposed TaxoInstruct framework, which outperforms task-specific baselines across all three tasks.

cs.CL↗

arXiv2025

Make Silence Speak for Itself: a multi-modal learning analytic approach with neurophysiological data

Background: Silence is a common phenomenon in classrooms, yet its implicit nature limits a clear understanding of students' underlying learning statuses. Aim: This study proposed a nuanced framework to classify classroom silence based on class events and student status, and examined neurophysiological markers to reveal similarities and differences in silent states across achievement groups. Sample: The study involved 54 middle school students during 34 math lessons, with simultaneous recordings of electroencephalogram (EEG), electrodermal activity (EDA), and heart rate signals, alongside video coding of classroom behaviors. Results: We found that high-achieving students showed no significant difference in mean EDA features between strategic silence (i.e., students choose silence deliberately) and active speaking during open questioning but exhibited higher EEG high-frequency relative power spectral density (RPSD) during strategic silence. In structural silence (i.e., students maintain silence following an external command) during directed questioning, they demonstrated significantly higher heart rates while listening to lectures compared to group activities, indicating heightened engagement. Both high- and medium-achieving students displayed elevated heart rates and EDA tonic components in structural silence during questioning compared to teaching. Furthermore, high-achieving students exhibited lower high-frequency RPSD during structural silence than strategic silence, a pattern not observed in other groups, highlighting group heterogeneity. Conclusions: The findings contribute to validating the complexity of silence, challenge its traditional association with passivity, and offer a novel classification framework along with preliminary empirical evidence to deepen the understanding of silent learning behaviors in classroom contexts.

q-bio.NC↗

arXiv2025

Sampling of Graph Signals Based on Joint Time-Vertex Fractional Fourier Transform

With the growing demand for non-Euclidean data analysis, graph signal processing (GSP) has gained significant attention for its capability to handle complex time-varying data. This paper introduces a novel sampling method based on the joint time-vertex fractional Fourier transform (JFRFT), enhancing signal representation in time-frequency analysis and GSP. The JFRFT sampling theory is established by deriving conditions for the perfect recovery of jointly bandlimited signals, along with an optimal sampling set selection strategy. To further enhance the efficiency of large-scale time-vertex signal processing, the design of localized sampling operators is investigated. Numerical simulations and real data experiments validate the superior performance of the proposed methods in terms of recovery accuracy and computational efficiency, offering new insights into efficient time-varying signal processing.

math.GM↗

arXiv2025

Auxiliary Field Quantum Monte Carlo for Electron-Photon Correlation

Hybrid light-matter polaritonic states have shown great promise for altering already known and enabling novel chemical reactions and controlling photophysical phenomena. This field has recently become one of the most prominent and active areas of research that connects the communities of chemistry and quantum optics. The ab initio modeling of such polaritonic phenomena has led to updating commonly used electronic structure methods, such as Hartree-Fock, density functional, and coupled cluster theories, to explicitly include Bosonic degrees of freedom. In this work, we explore the quantum electrodynamic auxiliary field quantum Monte Carlo (QED-AFQMC) method to accurately capture the polaritonic ground state of representative quantum chemical benchmark systems to explore electron-photon correlations. We analyze these correlations across multiple examples and benchmark the QED-AFQMC results against other ab initio quantum electrodynamics methods, including QED-coupled cluster and QED-full configuration interaction, demonstrating the method's accuracy and its potential for scalable simulations of strongly coupled light-matter systems.

quant-ph↗

arXiv2025

Internal and External Impacts of Natural Language Processing Papers

We investigate the impacts of NLP research published in top-tier conferences (i.e., ACL, EMNLP, and NAACL) from 1979 to 2024. By analyzing citations from research articles and external sources such as patents, media, and policy documents, we examine how different NLP topics are consumed both within the academic community and by the broader public. Our findings reveal that language modeling has the widest internal and external influence, while linguistic foundations have lower impacts. We also observe that internal and external impacts generally align, but topics like ethics, bias, and fairness show significant attention in policy documents with much fewer academic citations. Additionally, external domains exhibit distinct preferences, with patents focusing on practical NLP applications and media and policy documents engaging more with the societal implications of NLP models.

cs.CL↗

arXiv2025

Reconstruction of Graph Signals on Complex Manifolds with Kernel Methods

Graph signals are widely used to describe vertex attributes or features in graph-structured data, with applications spanning the internet, social media, transportation, sensor networks, and biomedicine. Graph signal processing (GSP) has emerged to facilitate the analysis, processing, and sampling of such signals. While kernel methods have been extensively studied for estimating graph signals from samples provided on a subset of vertices, their application to complex-valued graph signals remains largely unexplored. This paper introduces a novel framework for reconstructing graph signals using kernel methods on complex manifolds. By embedding graph vertices into a higher-dimensional complex ambient space that approximates a lower-dimensional manifold, the framework extends the reproducing kernel Hilbert space to complex manifolds. It leverages Hermitian metrics and geometric measures to characterize kernels and graph signals. Additionally, several traditional kernels and graph topology-driven kernels are proposed for reconstructing complex graph signals. Finally, experimental results on synthetic and real-world datasets demonstrate the effectiveness of this framework in accurately reconstructing complex graph signals, outperforming conventional kernel-based approaches. This work lays a foundational basis for integrating complex geometry and kernel methods in GSP.

eess.SP↗

arXiv2025

Insights into the 3D layered structure of nearby open clusters through N-body simulations

Context. Open clusters (OCs) are important for understanding star formation, dynamics, and evolution. Previous studies have indicated a relationship between cluster structure and member star properties, but the formation mechanism of the layered structure of OCs remains unclear. Aims. We study the three-dimensional spatial distribution of 279 nearby OCs to understand the formation mechanism of the layered structure. Methods. We analyzed the spatial distribution of member stars within each OC and correlated the presence of a layered structure with the number of member stars. Additionally, we performd N-body simulations to model the evolution of OCSN 125. We assessd the correlation between the binary fraction, the most massive star, and the radius of the layered structure in each simulated OC. Results. Our analysis reveals that OCs with fewer member stars tend to lack a layered structure. The results from N-body simulations indicate that the presence of a layered structure is strongly influenced by dynamical factors, particularly the most massive star and the binary fraction. Massive stars drive mass loss through supernova explosions and stellar winds, which weaken the spatial layering. Furthermore, clusters with higher binary fractions exhibit a weaker layered structure, likely due to energy equipartition, dynamical friction, and perturbations caused by binary systems. These factors contribute to delaying core collapse and slowing the emergence of a layered structure. Conclusions. Our findings suggest that dynamical interactions, including the effects of the most massive stars and binary fraction, play a critical role in the formation and disruption of the layered structure in OCs.

astro-ph.GA↗

arXiv2025

How Students Use AI Feedback Matters: Experimental Evidence on Physics Achievement and Autonomy

Despite the precision and adaptiveness of generative AI (GAI)-powered feedback provided to students, existing practice and literature might ignore how usage patterns impact student learning. This study examines the heterogeneous effects of GAI-powered personalized feedback on high school students' physics achievement and autonomy through two randomized controlled trials, with a major focus on usage patterns. Each experiment lasted for five weeks, involving a total of 387 students. Experiment 1 (n = 121) assessed compulsory usage of the personalized recommendation system, revealing that low-achieving students significantly improved academic performance (d = 0.673, p < 0.05) when receiving AI-generated heuristic solution hints, whereas medium-achieving students' performance declined (d = -0.539, p < 0.05) with conventional answers provided by workbook. Notably, high-achieving students experienced a significant decline in self-regulated learning (d = -0.477, p < 0.05) without any significant gains in achievement. Experiment 2 (n = 266) investigated the usage pattern of autonomous on-demand help, demonstrating that fully learner-controlled AI feedback significantly enhanced academic performance for high-achieving students (d = 0.378, p < 0.05) without negatively impacting their autonomy. However, autonomy notably declined among lower achievers exposed to on-demand AI interventions (d = -0.383, p < 0.05), particularly in the technical-psychological dimension (d = -0.549, p < 0.05), which has a large overlap with self-regulation. These findings underscore the importance of usage patterns when applying GAI-powered personalized feedback to students.

cs.CY↗

arXiv2025

A reconstruction algorithm of electrical impedance tomography based on one-dimensional convolutional neural network

Electrical impedance tomography (EIT) is a novel computational imaging technology. In order to improve the quality and spatial resolution of the reconstructed images, the G-CNN and HG-CNN algorithms are proposed based on a one-dimensional convolutional neural network (1D-CNN) in this paper. The input of the 1D-CNN is the reconstructed conductivity distribution obtained by the GVSPM algorithm or the H-GVSPM algorithm. The reconstructed images with higher resolution are obtained through the calculation of 1D-CNN. Finally, the Hadamard product is applied to calculate the output of the 1D-CNN. In the simulation results of the lung cross-section models, the correlation coefficients of the G-CNN algorithm and HG-CNN algorithm maximumly are 2.52 times and 2.20 times greater than the GVSPM algorithm and H-GVSPM algorithm, respectively. In the results of the simulation and experiment, the reconstructed images of the G-CNN and HG-CNN algorithms are distortion-free. In addition, the artifacts of the reconstructed images are diminished after calculations of the Hadamard product. This research provides a reference method for improving the quality of the reconstructed images so that EIT is better applied in medical detection.

physics.med-ph↗

arXiv2025

Analyzing Consumer IoT Traffic from Security and Privacy Perspectives: a Comprehensive Survey

The Consumer Internet of Things (CIoT), a notable segment within the IoT domain, involves the integration of IoT technology into consumer electronics and devices, such as smart homes and smart wearables. Compared to traditional IoT fields, CIoT differs notably in target users, product types, and design approaches. While offering convenience to users, it also raises new security and privacy concerns. Network traffic analysis, a widely used technique in the security community, has been extensively applied to investigate these concerns about CIoT. Compared to traditional network traffic analysis in fields like mobile apps and websites, CIoT introduces unique characteristics that pose new challenges and research opportunities. Researchers have made significant contributions in this area. To aid researchers in understanding the application of traffic analysis tools for assessing CIoT security and privacy risks, this survey reviews 310 publications on traffic analysis within the CIoT security and privacy domain from January 2018 to June 2024, focusing on three research questions. Our work: 1) outlines the CIoT traffic analysis process and highlights its differences from general network traffic analysis. 2) summarizes and classifies existing research into four categories according to its application objectives: device fingerprinting, user activity inference, malicious traffic detection, and measurement. 3) explores emerging challenges and potential future research directions based on each step of the CIoT traffic analysis process. This will provide new insights to the community and guide the industry towards safer product designs.

cs.CR↗

arXiv2025

HMPNet: A Feature Aggregation Architecture for Maritime Object Detection from a Shipborne Perspective

In the realm of intelligent maritime navigation, object detection from a shipborne perspective is paramount. Despite the criticality, the paucity of maritime-specific data impedes the deployment of sophisticated visual perception techniques, akin to those utilized in autonomous vehicular systems, within the maritime context. To bridge this gap, we introduce Navigation12, a novel dataset annotated for 12 object categories under diverse maritime environments and weather conditions. Based upon this dataset, we propose HMPNet, a lightweight architecture tailored for shipborne object detection. HMPNet incorporates a hierarchical dynamic modulation backbone to bolster feature aggregation and expression, complemented by a matrix cascading poly-scale neck and a polymerization weight sharing detector, facilitating efficient multi-scale feature aggregation. Empirical evaluations indicate that HMPNet surpasses current state-of-the-art methods in terms of both accuracy and computational efficiency, realizing a 3.3% improvement in mean Average Precision over YOLOv11n, the prevailing model, and reducing parameters by 23%.

cs.CV↗

arXiv2025

Do Language Model Agents Align with Humans in Rating Visualizations? An Empirical Study

Large language models encode knowledge in various domains and demonstrate the ability to understand visualizations. They may also capture visualization design knowledge and potentially help reduce the cost of formative studies. However, it remains a question whether large language models are capable of predicting human feedback on visualizations. To investigate this question, we conducted three studies to examine whether large model-based agents can simulate human ratings in visualization tasks. The first study, replicating a published study involving human subjects, shows agents are promising in conducting human-like reasoning and rating, and its result guides the subsequent experimental design. The second study repeated six human-subject studies reported in literature on subjective ratings, but replacing human participants with agents. Consulting with five human experts, this study demonstrates that the alignment of agent ratings with human ratings positively correlates with the confidence levels of the experts before the experiments. The third study tests commonly used techniques for enhancing agents, including preprocessing visual and textual inputs, and knowledge injection. The results reveal the issues of these techniques in robustness and potential induction of biases. The three studies indicate that language model-based agents can potentially simulate human ratings in visualization experiments, provided that they are guided by high-confidence hypotheses from expert evaluators. Additionally, we demonstrate the usage scenario of swiftly evaluating prototypes with agents. We discuss insights and future directions for evaluating and improving the alignment of agent ratings with human ratings. We note that simulation may only serve as complements and cannot replace user studies.

cs.HC↗

arXiv2025

LREA: Low-Rank Efficient Attention on Modeling Long-Term User Behaviors for CTR Prediction

With the rapid growth of user historical behavior data, user interest modeling has become a prominent aspect in Click-Through Rate (CTR) prediction, focusing on learning user intent representations. However, this complexity poses computational challenges, requiring a balance between model performance and acceptable response times for online services. Traditional methods often utilize filtering techniques. These techniques can lead to the loss of significant information by prioritizing top K items based on item attributes or employing low-precision attention mechanisms. In this study, we introduce LREA, a novel attention mechanism that overcomes the limitations of existing approaches while ensuring computational efficiency. LREA leverages low-rank matrix decomposition to optimize runtime performance and incorporates a specially designed loss function to maintain attention capabilities while preserving information integrity. During the inference phase, matrix absorption and pre-storage strategies are employed to effectively meet runtime constraints. The results of extensive offline and online experiments demonstrate that our method outperforms state-of-the-art approaches.

cs.IR↗

arXiv2025

Impact of Radio Frequency Power on Columnar and Filamentary Modes in Atmospheric Pressure Very Low Frequency Plasma within Pores

The impact of radio frequency (RF) power on columnar and filamentary modes of very low frequency (VLF) plasma within pores is investigated in this work. The 12.5 kHz VLF discharge under various RF powers (13.56 MHz) was analyzed using optical photography and current-voltage measurements. Two-dimensional electron densities were derived using optical emission spectroscopy combined with collisional radiation modeling methods. It is found that RF power and very low frequency voltage (VVLF) significantly influence the plasma and its discharge modes within the 200 μm pore. Under low VVLF conditions, the plasma is more intense within the pore, and the discharge mode is columnar discharge. With increasing RF power, the reciprocal motion of electrons counteracts the local enhancement effect of columnar discharge, the discharge transforms into RF discharge, the pore is completely wrapped by the sheath, and the plasma inside is gradually quenched. Under high VVLF conditions, the electron density within the pore is low and the discharge mode is filamentary discharge. RF introduction reduces plasma intensity within the pores firstly. As RF power increases, more ion trapping in the pore increases the field strength distortion and enhances the plasma intensity inside the pore, this enhancement effects becomes more obvious with increasing RF power. In addition, the above effects were observed for all pore widths from 100 um to 1000 um. These findings provide key insights for controlling plasma in pores and offer new methodologies for plasma technology applications.

physics.plasm-ph↗

arXiv2025

SMUTF: Schema Matching Using Generative Tags and Hybrid Features

We introduce SMUTF (Schema Matching Using Generative Tags and Hybrid Features), a unique approach for large-scale tabular data schema matching (SM), which assumes that supervised learning does not affect performance in open-domain tasks, thereby enabling effective cross-domain matching. This system uniquely combines rule-based feature engineering, pre-trained language models, and generative large language models. In an innovative adaptation inspired by the Humanitarian Exchange Language, we deploy "generative tags" for each data column, enhancing the effectiveness of SM. SMUTF exhibits extensive versatility, working seamlessly with any pre-existing pre-trained embeddings, classification methods, and generative models. Recognizing the lack of extensive, publicly available datasets for SM, we have created and open-sourced the HDXSM dataset from the public humanitarian data. We believe this to be the most exhaustive SM dataset currently available. In evaluations across various public datasets and the novel HDXSM dataset, SMUTF demonstrated exceptional performance, surpassing existing state-of-the-art models in terms of accuracy and efficiency, and improving the F1 score by 11.84% and the AUC of ROC by 5.08%. Code is available at https://github.com/fireindark707/Python-Schema-Matching.

cs.CL↗