arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 595 records · Page 33Linked to original sources

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↗

arXiv2025

VisTaxa: Developing a Taxonomy of Historical Visualizations

Historical visualizations are a rich resource for visualization research. While taxonomy is commonly used to structure and understand the design space of visualizations, existing taxonomies primarily focus on contemporary visualizations and largely overlook historical visualizations. To address this gap, we describe an empirical method for taxonomy development. We introduce a coding protocol and the VisTaxa system for taxonomy labeling and comparison. We demonstrate using our method to develop a historical visualization taxonomy by coding 400 images of historical visualizations. We analyze the coding result and reflect on the coding process. Our work is an initial step toward a systematic investigation of the design space of historical visualizations.

cs.HC↗

arXiv2025

Leveraging Pretrained Diffusion Models for Zero-Shot Part Assembly

3D part assembly aims to understand part relationships and predict their 6-DoF poses to construct realistic 3D shapes, addressing the growing demand for autonomous assembly, which is crucial for robots. Existing methods mainly estimate the transformation of each part by training neural networks under supervision, which requires a substantial quantity of manually labeled data. However, the high cost of data collection and the immense variability of real-world shapes and parts make traditional methods impractical for large-scale applications. In this paper, we propose first a zero-shot part assembly method that utilizes pre-trained point cloud diffusion models as discriminators in the assembly process, guiding the manipulation of parts to form realistic shapes. Specifically, we theoretically demonstrate that utilizing a diffusion model for zero-shot part assembly can be transformed into an Iterative Closest Point (ICP) process. Then, we propose a novel pushing-away strategy to address the overlap parts, thereby further enhancing the robustness of the method. To verify our work, we conduct extensive experiments and quantitative comparisons to several strong baseline methods, demonstrating the effectiveness of the proposed approach, which even surpasses the supervised learning method. The code has been released on https://github.com/Ruiyuan-Zhang/Zero-Shot-Assembly.

cs.CV↗

arXiv2025

CAE-DFKD: Bridging the Transferability Gap in Data-Free Knowledge Distillation

Data-Free Knowledge Distillation (DFKD) enables the knowledge transfer from the given pre-trained teacher network to the target student model without access to the real training data. Existing DFKD methods focus primarily on improving image recognition performance on associated datasets, often neglecting the crucial aspect of the transferability of learned representations. In this paper, we propose Category-Aware Embedding Data-Free Knowledge Distillation (CAE-DFKD), which addresses at the embedding level the limitations of previous rely on image-level methods to improve model generalization but fail when directly applied to DFKD. The superiority and flexibility of CAE-DFKD are extensively evaluated, including: \textit{\textbf{i.)}} Significant efficiency advantages resulting from altering the generator training paradigm; \textit{\textbf{ii.)}} Competitive performance with existing DFKD state-of-the-art methods on image recognition tasks; \textit{\textbf{iii.)}} Remarkable transferability of data-free learned representations demonstrated in downstream tasks.

cs.CV↗

arXiv2025

Large Language Models to Accelerate Organic Chemistry Synthesis

Chemical synthesis, as a foundational methodology in the creation of transformative molecules, exerts substantial influence across diverse sectors from life sciences to materials and energy. Current chemical synthesis practices emphasize laborious and costly trial-and-error workflows, underscoring the urgent need for advanced AI assistants. Nowadays, large language models (LLMs), typified by GPT-4, have been introduced as an efficient tool to facilitate scientific research. Here, we present Chemma, a fully fine-tuned LLM with 1.28 million pairs of Q&A about reactions, as an assistant to accelerate organic chemistry synthesis. Chemma surpasses the best-known results in multiple chemical tasks, e.g., single-step retrosynthesis and yield prediction, which highlights the potential of general AI for organic chemistry. Via predicting yields across the experimental reaction space, Chemma significantly improves the reaction exploration capability of Bayesian optimization. More importantly, integrated in an active learning framework, Chemma exhibits advanced potential for autonomous experimental exploration and optimization in open reaction spaces. For an unreported Suzuki-Miyaura cross-coupling reaction of cyclic aminoboronates and aryl halides for the synthesis of $α$-Aryl N-heterocycles, the human-AI collaboration successfully explored suitable ligand and solvent (1,4-dioxane) within only 15 runs, achieving an isolated yield of 67%. These results reveal that, without quantum-chemical calculations, Chemma can comprehend and extract chemical insights from reaction data, in a manner akin to human experts. This work opens avenues for accelerating organic chemistry synthesis with adapted large language models.

physics.chem-ph↗

arXiv2025

A Line Graph-Based Framework for Identifying Optimal Routing Paths in Decentralized Exchanges

Decentralized exchanges, such as those employing constant product market makers (CPMMs) like Uniswap V2, play a crucial role in the blockchain ecosystem by enabling peer-to-peer token swaps without intermediaries. Despite the increasing volume of transactions, there remains limited research on identifying optimal trading paths across multiple DEXs. This paper presents a novel line-graph-based algorithm (LG) designed to efficiently discover profitable trading routes within DEX environments. We benchmark LG against the widely adopted Depth-First Search (DFS) algorithm under a linear routing scenario, encompassing platforms such as Uniswap, SushiSwap, and PancakeSwap. Experimental results demonstrate that LG consistently identifies trading paths that are as profitable as, or more profitable than, those found by DFS, while incurring comparable gas costs. Evaluations on Uniswap V2 token graphs across two temporal snapshots further validate LG's performance. Although LG exhibits exponential runtime growth with respect to graph size in empirical tests, it remains viable for practical, real-world use cases. Our findings underscore the potential of the LG algorithm for industrial adoption, offering tangible benefits to traders and market participants in the DeFi space.

q-fin.CP↗

arXiv2025

Charting the Uncharted: The Landscape of Monero Peer-to-Peer Network

The Monero blockchain enables anonymous transactions through advanced cryptography in its peer-to-peer network, which underpins decentralization, security, and trustless interactions. However, privacy measures obscure peer connections, complicating network analysis. This study proposes a method to infer peer connections in Monero's latest protocol version, where timestamp data is unavailable. We collect peerlist data from TCP flows, validate our inference algorithm, and map the network structure. Our results show high accuracy, improving with longer observation periods. This work is the first to reveal connectivity patterns in Monero's updated protocol, providing visualizations and insights into its topology. Our findings enhance the understanding of Monero's P2P network, including the role of supernodes, and highlight potential protocol and security improvements.

cs.DC↗

arXiv2025

Monero Peer-to-peer Network Topology Analysis

Monero, a privacy-focused cryptocurrency, employs a decentralized peer-to-peer (P2P) network that plays a critical role in transaction propagation and consensus formation. While much research has explored Monero's privacy transaction mechanisms, its underlying P2P network architecture has remained relatively underexplored. In this study, building on our recent work on Monero network detection, we further investigate the network topology of Monero's P2P structure, which has evolved following recent protocol updates that enhanced security by obscuring peer information. Using k-core decomposition, we confirm that the Monero network exhibits a core-periphery structure, where a tightly interconnected core of supernodes is crucial for maintaining network cohesion, while peripheral nodes rely on these core nodes for connectivity. This structure explains why targeting central nodes does not easily lead to the rapid disintegration of the network's largest connected component while also providing a deeper understanding of the true architecture of Monero's peer protocol.

cs.NI↗

arXiv2025

TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching

Singing voice synthesis has made remarkable progress in generating natural and high-quality voices. However, existing methods rarely provide precise control over vocal techniques such as intensity, mixed voice, falsetto, bubble, and breathy tones, thus limiting the expressive potential of synthetic voices. We introduce TechSinger, an advanced system for controllable singing voice synthesis that supports five languages and seven vocal techniques. TechSinger leverages a flow-matching-based generative model to produce singing voices with enhanced expressive control over various techniques. To enhance the diversity of training data, we develop a technique detection model that automatically annotates datasets with phoneme-level technique labels. Additionally, our prompt-based technique prediction model enables users to specify desired vocal attributes through natural language, offering fine-grained control over the synthesized singing. Experimental results demonstrate that TechSinger significantly enhances the expressiveness and realism of synthetic singing voices, outperforming existing methods in terms of audio quality and technique-specific control. Audio samples can be found at https://gwx314.github.io/tech-singer/.

cs.SD↗

arXiv2025

Hierarchical and Step-Layer-Wise Tuning of Attention Specialty for Multi-Instance Synthesis in Diffusion Transformers

Text-to-image (T2I) generation models often struggle with multi-instance synthesis (MIS), where they must accurately depict multiple distinct instances in a single image based on complex prompts detailing individual features. Traditional MIS control methods for UNet architectures like SD v1.5/SDXL fail to adapt to DiT-based models like FLUX and SD v3.5, which rely on integrated attention between image and text tokens rather than text-image cross-attention. To enhance MIS in DiT, we first analyze the mixed attention mechanism in DiT. Our token-wise and layer-wise analysis of attention maps reveals a hierarchical response structure: instance tokens dominate early layers, background tokens in middle layers, and attribute tokens in later layers. Building on this observation, we propose a training-free approach for enhancing MIS in DiT-based models with hierarchical and step-layer-wise attention specialty tuning (AST). AST amplifies key regions while suppressing irrelevant areas in distinct attention maps across layers and steps, guided by the hierarchical structure. This optimizes multimodal interactions by hierarchically decoupling the complex prompts with instance-based sketches. We evaluate our approach using upgraded sketch-based layouts for the T2I-CompBench and customized complex scenes. Both quantitative and qualitative results confirm our method enhances complex layout generation, ensuring precise instance placement and attribute representation in MIS.

cs.CV↗