arXiv subjects

Xiaowei Chen

Publications and source records attributed to Xiaowei Chen.

At least 19 recordsLinked to original sources

arXiv2026

Generative Auto-Bidding with Unified Modeling and Exploration

Automated bidding is central to modern digital advertising. Early rule-based methods lacked adaptability, while subsequent Reinforcement Learning approaches modeled bidding as a Markov Decision Process but struggled with long-term dependencies. Recent generative models show promise, yet they lack explicit mechanisms to balance exploration and safety, relying solely on action perturbations or trajectory guidance without a safety fallback. This results in inefficient exploration and elevated financial risk for advertising platforms. To address this gap, we propose GUIDE (Generative Auto-Bidding with Unified Modeling and Exploration), a framework that synergistically integrates directed exploration with a safe fallback mechanism. GUIDE employs a Decision Transformer (DT) to jointly model historical bidding actions and environmental state transitions. A Q-value module guides the DT's exploration via regularization constraints, while an Inverse Dynamics Module (IDM) leverages DT-predicted future states to infer robust, behaviorally consistent actions as a safe policy fallback. The Q-value module then adaptively selects the final action between these two options, balancing exploration and safety. Together, these components form an integrated "explore-safeguard-select" pipeline that unifies efficiency and safety. We conduct extensive experiments on public datasets, in simulated auction environments, and through large-scale online deployment on Taobao, a leading Chinese advertising platform. Results show GUIDE consistently outperforms state-of-the-art baselines across all scenarios. In real-world deployment, GUIDE achieves notable gains: +4.10% ad GMV, +1.40% ad clicks, +1.66% ad cost, and +3.52% ad ROI, demonstrating its effectiveness and strong industrial applicability.

cs.AI↗

arXiv2026

From Harm to Healing: Understanding Individual Resilience after Cybercrimes

How do individuals recover from cybercrimes? Victims experience various types of harm after cybercrimes, including monetary loss, data breaches, negative emotions, and even psychological trauma. The aspects that support their recovery process and contribute to individual cyber resilience remain underinvestigated. To address this gap, we interviewed 18 cybercrime victims from Western Europe using a trauma-informed approach. We identified four common stages following victimization: recognition, coping, processing, and recovery. Participants adopted various strategies to mitigate the impact of cybercrime and used different indicators to describe recovery. While they mostly relied on social support and self-regulation for emotional coping, service providers largely determined whether victims were able to recover their money. Internal factors, external support, and context sensitivity collectively contribute to individuals' cyber resilience. We recommend trauma-informed support for cybercrime victims. Extending our conceptualization of individual cyber resilience, we propose collaborative and context-sensitive strategies to address the harmful impacts of cybercrime.

cs.HC↗

arXiv2026

Experiencer, Helper, or Observer: Online Fraud Intervention for Older Adults Through Role-based Simulation

Online fraud is a critical global threat that disproportionately targets older adults. Prior anti-fraud education for older adults has largely relied on static, traditional instruction that limits engagement and real-world transfer, whereas role-based simulation offers realistic yet low-risk opportunities for practice. Moreover, most interventions situate learners as victims, overlooking that fraud encounters often involve multiple roles, such as bystanders who witness scams and helpers who support victims. To address this gap, we developed ROLESafe, an anti-fraud educational intervention in which older adults learn through different learning roles, including Experiencer (experiencing fraud), Helper (assisting a victim), and Observer (witnessing fraud). In a between-subjects study with 144 older adults in China, we found that the Experiencer and Helper roles significantly improved participants' ability to identify online fraud. These findings highlight the promise of role-based, multi-perspective simulations for enhancing fraud awareness among older adults and provide design implications for future anti-fraud education.

cs.HC↗

arXiv2025

A large-scale complexity-graded dataset of neuronal images and annotations

Accurate reconstruction of neuronal morphology is essential for classifying cell types and understanding brain connectivity. Recent advances in imaging and reconstruction techniques have greatly expanded the scale and quality of neuronal data. However, large-scale, standardized annotated datasets remain limited. Here, we present an open, multi-level neuronal dataset covering the whole mouse brain. Using a hierarchical strategy, we divided imaging data from 237 mouse brains into about 13,570,000 standardized blocks, classified into four levels of reconstruction difficulty. With the custom-developed reconstruction platform, we achieved high-precision three-dimensional reconstructions of 9,676 neurons at the whole-brain scale. This dataset will be made publicly available, providing a valuable resource for algorithm development and brain circuit modeling in neuroscience research.

q-bio.NC↗

arXiv2024

MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples

Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Reinforcement Learning from Human Feedback (RLHF), are inherently derived from PPO, requiring a reference model that adds GPU memory resources and relies heavily on abundant preference data. Meanwhile, current preference optimization research mainly targets single-question scenarios with two replies, neglecting optimization with multiple replies, which leads to a waste of data in the application. This study introduces the MPPO algorithm, which leverages the average likelihood of model responses to fit the reward function and maximizes the utilization of preference data. Through a comparison of Point-wise, Pair-wise, and List-wise implementations, we found that the Pair-wise approach achieves the best performance, significantly enhancing the quality of model responses. Experimental results demonstrate MPPO's outstanding performance across various benchmarks. On MT-Bench, MPPO outperforms DPO, ORPO, and SimPO. Notably, on Arena-Hard, MPPO surpasses DPO and ORPO by substantial margins. These achievements underscore the remarkable advantages of MPPO in preference optimization tasks.

cs.CL↗

arXiv2024

Unveiling Nonlinear Dynamics in Catastrophe Bond Pricing: A Machine Learning Perspective

This paper explores the implications of using machine learning models in the pricing of catastrophe (CAT) bonds. By integrating advanced machine learning techniques, our approach uncovers nonlinear relationships and complex interactions between key risk factors and CAT bond spreads -- dynamics that are often overlooked by traditional linear regression models. Using primary market CAT bond transaction records between January 1999 and March 2021, our findings demonstrate that machine learning models not only enhance the accuracy of CAT bond pricing but also provide a deeper understanding of how various risk factors interact and influence bond prices in a nonlinear way. These findings suggest that investors and issuers can benefit from incorporating machine learning to better capture the intricate interplay between risk factors when pricing CAT bonds. The results also highlight the potential for machine learning models to refine our understanding of asset pricing in markets characterized by complex risk structures.

q-fin.CP↗

arXiv2024

Few-Shot Medical Image Segmentation with Large Kernel Attention

Medical image segmentation has witnessed significant advancements with the emergence of deep learning. However, the reliance of most neural network models on a substantial amount of annotated data remains a challenge for medical image segmentation. To address this issue, few-shot segmentation methods based on meta-learning have been employed. Presently, the methods primarily focus on aligning the support set and query set to enhance performance, but this approach hinders further improvement of the model's effectiveness. In this paper, our objective is to propose a few-shot medical segmentation model that acquire comprehensive feature representation capabilities, which will boost segmentation accuracy by capturing both local and long-range features. To achieve this, we introduce a plug-and-play attention module that dynamically enhances both query and support features, thereby improving the representativeness of the extracted features. Our model comprises four key modules: a dual-path feature extractor, an attention module, an adaptive prototype prediction module, and a multi-scale prediction fusion module. Specifically, the dual-path feature extractor acquires multi-scale features by obtaining features of 32{\times}32 size and 64{\times}64 size. The attention module follows the feature extractor and captures local and long-range information. The adaptive prototype prediction module automatically adjusts the anomaly score threshold to predict prototypes, while the multi-scale fusion prediction module integrates prediction masks of various scales to produce the final segmentation result. We conducted experiments on publicly available MRI datasets, namely CHAOS and CMR, and compared our method with other advanced techniques. The results demonstrate that our method achieves state-of-the-art performance.

cs.CV↗

arXiv2024

SuDA: Support-based Domain Adaptation for Sim2Real Motion Capture with Flexible Sensors

Flexible sensors hold promise for human motion capture (MoCap), offering advantages such as wearability, privacy preservation, and minimal constraints on natural movement. However, existing flexible sensor-based MoCap methods rely on deep learning and necessitate large and diverse labeled datasets for training. These data typically need to be collected in MoCap studios with specialized equipment and substantial manual labor, making them difficult and expensive to obtain at scale. Thanks to the high-linearity of flexible sensors, we address this challenge by proposing a novel Sim2Real Mocap solution based on domain adaptation, eliminating the need for labeled data yet achieving comparable accuracy to supervised learning. Our solution relies on a novel Support-based Domain Adaptation method, namely SuDA, which aligns the supports of the predictive functions rather than the instance-dependent distributions between the source and target domains. Extensive experimental results demonstrate the effectiveness of our method andits superiority over state-of-the-art distribution-based domain adaptation methods in our task.

cs.CV↗

arXiv2024

Support-Query Prototype Fusion Network for Few-shot Medical Image Segmentation

In recent years, deep learning based on Convolutional Neural Networks (CNNs) has achieved remarkable success in many applications. However, their heavy reliance on extensive labeled data and limited generalization ability to unseen classes pose challenges to their suitability for medical image processing tasks. Few-shot learning, which utilizes a small amount of labeled data to generalize to unseen classes, has emerged as a critical research area, attracting substantial attention. Currently, most studies employ a prototype-based approach, in which prototypical networks are used to construct prototypes from the support set, guiding the processing of the query set to obtain the final results. While effective, this approach heavily relies on the support set while neglecting the query set, resulting in notable disparities within the model classes. To mitigate this drawback, we propose a novel Support-Query Prototype Fusion Network (SQPFNet). SQPFNet initially generates several support prototypes for the foreground areas of the support images, thus producing a coarse segmentation mask. Subsequently, a query prototype is constructed based on the coarse segmentation mask, additionally exploiting pattern information in the query set. Thus, SQPFNet constructs high-quality support-query fused prototypes, upon which the query image is segmented to obtain the final refined query mask. Evaluation results on two public datasets, SABS and CMR, show that SQPFNet achieves state-of-the-art performance.

cs.CV↗

arXiv2024

Multi-Task Learning for Fatigue Detection and Face Recognition of Drivers via Tree-Style Space-Channel Attention Fusion Network

In driving scenarios, automobile active safety systems are increasingly incorporating deep learning technology. These systems typically need to handle multiple tasks simultaneously, such as detecting fatigue driving and recognizing the driver's identity. However, the traditional parallel-style approach of combining multiple single-task models tends to waste resources when dealing with similar tasks. Therefore, we propose a novel tree-style multi-task modeling approach for multi-task learning, which rooted at a shared backbone, more dedicated separate module branches are appended as the model pipeline goes deeper. Following the tree-style approach, we propose a multi-task learning model for simultaneously performing driver fatigue detection and face recognition for identifying a driver. This model shares a common feature extraction backbone module, with further separated feature extraction and classification module branches. The dedicated branches exploit and combine spatial and channel attention mechanisms to generate space-channel fused-attention enhanced features, leading to improved detection performance. As only single-task datasets are available, we introduce techniques including alternating updation and gradient accumulation for training our multi-task model using only the single-task datasets. The effectiveness of our tree-style multi-task learning model is verified through extensive validations.

cs.CV↗

arXiv2024

The Effects of Group Discussion and Role-playing Training on Self-efficacy, Support-seeking, and Reporting Phishing Emails: Evidence from a Mixed-design Experiment

Organizations rely on phishing interventions to enhance employees' vigilance and safe responses to phishing emails that bypass technical solutions. While various resources are available to counteract phishing, studies emphasize the need for interactive and practical training approaches. To investigate the effectiveness of such an approach, we developed and delivered two anti-phishing trainings, group discussion and role-playing, at a European university. We conducted a pre-registered experiment (N = 105), incorporating repeated measures at three time points, a control group, and three in-situ phishing tests. Both trainings enhanced employees' anti-phishing self-efficacy and support-seeking intention in within-group analyses. Only the role-playing training significantly improved support-seeking intention when compared to the control group. Participants in both trainings reported more phishing tests and demonstrated heightened vigilance to phishing attacks compared to the control group. We discuss practical implications for evaluating and improving phishing interventions and promoting safe responses to phishing threats within organizations.

cs.HC↗

arXiv2024

Multi-functional oxidase-like activity of praseodymia nanorods and nanoparticles

The ability to mimic protein-based oxidase with multi-functional inorganic nanozymes would greatly advance biomedical and clinical practices. Praseodymia (PrOx) nanorods (NRs) and nanoparticles (NPs) have been synthesized using hydrothermal and precipitation methods. Both PrOx catalysts with different morphologies exhibit significantly higher oxidase-like activities (Michaelis-Menten constant Km < 0.026 mM) than commercial PrOx and most so-far-reported artificial enzymes. One of the substrates, dopamine, can be oxidized and further polymerized to generate polydopamine in acidic conditions. Akin to CeO2, which is a well-studied nanozyme, a different mechanism involving holes+, oxygen vacancies and oxygen mobility over PrOx catalysts has been proposed in this work. However, fluoride ions were found to impose opposite effects on the oxidase-mimicking activity of PrOx and CeO2, implying a promising path for the exploration of new nanozymes. In support of this, PrOx was further applied in colorimetric sensing of L-cysteine and fluoride with high sensitivity.

physics.chem-ph↗

arXiv2024

Size, nanostructure, and composition dependence of bimetallic Au-Pd supported on ceria-zirconia mixed oxide catalysts for selective oxidation of benzyl alcohol

A bimetallic Au-Pd catalyst supported on ceriazirconia with Au:Pd molar ratio 0.8 has been synthesized using a simultaneous deposition-precipitation method and oxidized at 250, 450, and 700 $^\circ$C in order to modify its particle size, nanostructure, and composition. Combined Xray energy dispersive spectroscopy and Xray photoelectron spectroscopy analysis clearly evidence that the bimetallic Au-Pd catalyst oxidized at 250 $^\circ$C is made up of a mixture of monometallic Au and Pd and bimetallic Au-Pd nanoparticles with Au:Pd ratios varying over a wide range. Increasing oxidation temperature leads to a stronger interaction between Au and Pd. Meanwhile, a slight increase of particle size and a narrowing of the Au:Pd ratio in the bimetallic nanoparticles take place. Compared with titania and activated carbon supports, the resistance against sintering at high temperatures of Au-Pd metal particles supported on ceriazirconia is proven to be higher. A synergistic effect has been observed for selective oxidation of benzyl alcohol on these catalysts. The catalytic activity decreases only slightly after oxidation at 450 $^\circ$C. However, oxidation at 700 $^\circ$C results in much lower catalytic activity. Migration of Pd onto Au particles during oxidation of benzyl alcohol enhances the catalytic activity of a physical mixture of monometallic Au and Pd supported on ceriazirconia catalysts. This fact, jointly with an analysis of the intrinsic activity, reveals the influence of the actual nature of Au-Pd interactions in the bimetallic particles, which points to higher activity of Au@Pd or Au@Pd@Pd nanostructures on ceria-zirconia support.

physics.chem-ph↗

arXiv2024

A facile one-pot hydrothermal synthesis as an efficient method to modulate the potassium content of cryptomelane and its effects on the redox and catalytic properties

Cryptomelane has been widely applied as catalyst in oxidation reactions due to its excellent redox properties and low cost. Here, a novel one-pot hydrothermal synthesis using a potassium permanganate aqueous solution as precursor and ethanol as reducing agent has successfully been developed to obtain cryptomelane nano-oxides. This synthetic route makes it possible to control the amount of potassium incorporated into the structure of the cryptomelane by selecting the appropriate synthesis temperature and ethanol initial concentration. Taking advantage of this approach, the effect of potassium concentration on the structural stability and reducibility of the cryptomelane, which are poorly discussed in the literature, has been studied. We have observed that samples with low content of potassium (~11%) show high conversions of CO to CO2 especially at low temperatures. The lower activity of the samples with high K contents (~16%) can be ascribed to the beneficial effect of K on the structural stability of cryptomelane in detriment of labile oxygen on cryptomelane surface.

cond-mat.mtrl-sci↗

arXiv2023

Comparison of home detection algorithms using smartphone GPS data

Estimation of people's home locations using location-based services data from smartphones is a common task in human mobility assessment. However, commonly used home detection algorithms (HDAs) are often arbitrary and unexamined. In this study, we review existing HDAs and examine five HDAs using eight high-quality mobile phone geolocation datasets. These include four commonly used HDAs as well as an HDA proposed in this work. To make quantitative comparisons, we propose three novel metrics to assess the quality of detected home locations and test them on eight datasets across four U.S. cities. We find that all three metrics show a consistent rank of HDAs' performances, with the proposed HDA outperforming the others. We infer that the temporal and spatial continuity of the geolocation data points matters more than the overall size of the data for accurate home detection. We also find that HDAs with high (and similar) performance metrics tend to create results with better consistency and closer to common expectations. Further, the performance deteriorates with decreasing data quality of the devices, though the patterns of relative performance persist. Finally, we show how the differences in home detection can lead to substantial differences in subsequent inferences using two case studies - (i) hurricane evacuation estimation, and (ii) correlation of mobility patterns with socioeconomic status. Our work contributes to improving the transparency of large-scale human mobility assessment applications.

cs.CY↗

arXiv2023

HB-net: Holistic bursting cell cluster integrated network for occluded multi-objects recognition

Within the realm of image recognition, a specific category of multi-label classification (MLC) challenges arises when objects within the visual field may occlude one another, demanding simultaneous identification of both occluded and occluding objects. Traditional convolutional neural networks (CNNs) can tackle these challenges; however, those models tend to be bulky and can only attain modest levels of accuracy. Leveraging insights from cutting-edge neural science research, specifically the Holistic Bursting (HB) cell, this paper introduces a pioneering integrated network framework named HB-net. Built upon the foundation of HB cell clusters, HB-net is designed to address the intricate task of simultaneously recognizing multiple occluded objects within images. Various Bursting cell cluster structures are introduced, complemented by an evidence accumulation mechanism. Testing is conducted on multiple datasets comprising digits and letters. The results demonstrate that models incorporating the HB framework exhibit a significant $2.98\%$ enhancement in recognition accuracy compared to models without the HB framework ($1.0298$ times, $p=0.0499$). Although in high-noise settings, standard CNNs exhibit slightly greater robustness when compared to HB-net models, the models that combine the HB framework and EA mechanism achieve a comparable level of accuracy and resilience to ResNet50, despite having only three convolutional layers and approximately $1/30$ of the parameters. The findings of this study offer valuable insights for improving computer vision algorithms. The essential code is provided at https://github.com/d-lab438/hb-net.git.

cs.CV↗

arXiv2023

Do Persuasive Designs Make Smartphones More Addictive? -- A Mixed-Methods Study on Chinese University Students

Persuasive designs become prevalent on smartphones, and an increasing number of users report having problematic smartphone use behaviours. Persuasive designs in smartphones might be accountable for the development and reinforcement of such problematic use. This paper uses a mixed-methods approach to study the relationship between persuasive designs and problematic smartphone use: (1) questionnaires (N=183) to investigate the proportion of participants having multiple problematic smartphone use behaviours and smartphone designs and applications (apps) that they perceived affecting their attitudes and behaviours, and (2) interviews (N=10) to deepen our understanding of users' observations and evaluations of persuasive designs. 25\% of the participants self-reported having multiple problematic smartphone use behaviours, with short video, social networking, game and learning apps perceived as most attitude and behaviour-affecting. Interviewees identified multiple persuasive designs in most of these apps and stated that persuasive designs prolonged their screen time, reinforced phone-checking habits, and caused distractions. Overall, this study provides evidence to argue that persuasive designs contribute to problematic smartphone use, potentially making smartphones more addictive. We end our study by discussing the ethical implications of persuasive designs that became salient in our study.

cs.HC↗

arXiv2023

DisPad: Flexible On-Body Displacement of Fabric Sensors for Robust Joint-Motion Tracking

The last few decades have witnessed an emerging trend of wearable soft sensors; however, there are important signal-processing challenges for soft sensors that still limit their practical deployment. They are error-prone when displaced, resulting in significant deviations from their ideal sensor output. In this work, we propose a novel prototype that integrates an elbow pad with a sparse network of soft sensors. Our prototype is fully bio-compatible, stretchable, and wearable. We develop a learning-based method to predict the elbow orientation angle and achieve an average tracking error of 9.82 degrees for single-user multi-motion experiments. With transfer learning, our method achieves the average tracking errors of 10.98 degrees and 11.81 degrees across different motion types and users, respectively. Our core contributions lie in a solution that realizes robust and stable human joint motion tracking across different device displacements.

cs.HC↗