arXiv subjects

Yan Zhang

Publications and source records attributed to Yan Zhang.

At least 199 records · Page 11Linked to original sources

arXiv2025

Privacy-Utility-Fairness: A Balanced Approach to Vehicular-Traffic Management System

Location-based vehicular traffic management faces significant challenges in protecting sensitive geographical data while maintaining utility for traffic management and fairness across regions. Existing state-of-the-art solutions often fail to meet the required level of protection against linkage attacks and demographic biases, leading to privacy leakage and inequity in data analysis. In this paper, we propose a novel algorithm designed to address the challenges regarding the balance of privacy, utility, and fairness in location-based vehicular traffic management systems. In this context, utility means providing reliable and meaningful traffic information, while fairness ensures that all regions and individuals are treated equitably in data use and decision-making. Employing differential privacy techniques, we enhance data security by integrating query-based data access with iterative shuffling and calibrated noise injection, ensuring that sensitive geographical data remains protected. We ensure adherence to epsilon-differential privacy standards by implementing the Laplace mechanism. We implemented our algorithm on vehicular location-based data from Norway, demonstrating its ability to maintain data utility for traffic management and urban planning while ensuring fair representation of all geographical areas without being overrepresented or underrepresented. Additionally, we have created a heatmap of Norway based on our model, illustrating the privatized and fair representation of the traffic conditions across various cities. Our algorithm provides privacy in vehicular traffic

cs.CR↗

arXiv2025

Anti-Interference Diffractive Deep Neural Networks for Multi-Object Recognition

Optical neural networks (ONNs) are emerging as a promising neuromorphic computing paradigm for object recognition, offering unprecedented advantages in light-speed computation, ultra-low power consumption, and inherent parallelism. However, most of ONNs are only capable of performing simple object classification tasks. These tasks are typically constrained to single-object scenarios, which limits their practical applications in multi-object recognition tasks. Here, we propose an anti-interference diffractive deep neural network (AI D2NN) that can accurately and robustly recognize targets in multi-object scenarios, including intra-class, inter-class, and dynamic interference. By employing different deep-learning-based training strategies for targets and interference, two transmissive diffractive layers form a physical network that maps the spatial information of targets all-optically into the power spectrum of the output light, while dispersing all interference as background noise. We demonstrate the effectiveness of this framework in classifying unknown handwritten digits under dynamic scenarios involving 40 categories of interference, achieving a simulated blind testing accuracy of 87.4% using terahertz waves. The presented framework can be physically scaled to operate at any electromagnetic wavelength by simply scaling the diffractive features in proportion to the wavelength range of interest. This work can greatly advance the practical application of ONNs in target recognition and pave the way for the development of real-time, high-throughput, low-power all-optical computing systems, which are expected to be applied to autonomous driving perception, precision medical diagnosis, and intelligent security monitoring.

physics.optics↗

arXiv2025

A Theory for Conditional Generative Modeling on Multiple Data Sources

The success of large generative models has driven a paradigm shift, leveraging massive multi-source data to enhance model capabilities. However, the interaction among these sources remains theoretically underexplored. This paper takes the first step toward a rigorous analysis of multi-source training in conditional generative modeling, where each condition represents a distinct data source. Specifically, we establish a general distribution estimation error bound in average total variation distance for conditional maximum likelihood estimation based on the bracketing number. Our result shows that when source distributions share certain similarities and the model is expressive enough, multi-source training guarantees a sharper bound than single-source training. We further instantiate the general theory on conditional Gaussian estimation and deep generative models including autoregressive and flexible energy-based models, by characterizing their bracketing numbers. The results highlight that the number of sources and similarity among source distributions improve the advantage of multi-source training. Simulations and real-world experiments are conducted to validate the theory, with code available at: https://github.com/ML-GSAI/Multi-Source-GM.

cs.LG↗

arXiv2025

Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learning

Decentralized federated learning (DFL) is inherently vulnerable to data poisoning attacks, as malicious clients can transmit manipulated gradients to neighboring clients. Existing defense methods either reject suspicious gradients per iteration or restart DFL aggregation after excluding all malicious clients. They all neglect the potential benefits that may exist within contributions from malicious clients. In this paper, we propose a novel gradient purification defense, termed GPD, to defend against data poisoning attacks in DFL. It aims to separately mitigate the harm in gradients and retain benefits embedded in model weights, thereby enhancing overall model accuracy. For each benign client in GPD, a recording variable is designed to track historically aggregated gradients from one of its neighbors. It allows benign clients to precisely detect malicious neighbors and mitigate all aggregated malicious gradients at once. Upon mitigation, benign clients optimize model weights using purified gradients. This optimization not only retains previously beneficial components from malicious clients but also exploits canonical contributions from benign clients. We analyze the convergence of GPD, as well as its ability to harvest high accuracy. Extensive experiments demonstrate that, GPD is capable of mitigating data poisoning attacks under both iid and non-iid data distributions. It also significantly outperforms state-of-the-art defense methods in terms of model accuracy.

cs.LG↗

arXiv2025

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering

Large language models (LLMs) are prone to capturing biases from training corpus, leading to potential negative social impacts. Existing prompt-based debiasing methods exhibit instability due to their sensitivity to prompt changes, while fine-tuning-based techniques incur substantial computational overhead and catastrophic forgetting. In this paper, we propose FairSteer, a novel inference-time debiasing framework without requiring customized prompt design or model retraining. Motivated by the linear representation hypothesis, our preliminary investigation demonstrates that fairness-related features can be encoded into separable directions in the hidden activation space. FairSteer operates in three steps: biased activation detection, debiasing steering vector (DSV) computation, and dynamic activation steering. Specifically, it first trains a lightweight linear classifier to detect bias signatures in activations, and then computes DSVs as intervention directions derived from small contrastive prompt pairs. Subsequently, it performs debiasing by adjusting activations with DSVs in the inference stage. Comprehensive evaluation with six LLMs demonstrates the superiority of FairSteer across question-answering, counterfactual input evaluation and open-ended text generation tasks. Code will be released.

cs.CL↗

arXiv2025

Human-Centered Explainability in Interactive Information Systems: A Survey

Human-centered explainability has become a critical foundation for the responsible development of interactive information systems, where users must be able to understand, interpret, and scrutinize AI-driven outputs to make informed decisions. This systematic survey of literature aims to characterize recent progress in user studies on explainability in interactive information systems by reviewing how explainability has been conceptualized, designed, and evaluated in practice. Following PRISMA guidelines, eight academic databases were searched, and 100 relevant articles were identified. A structural encoding approach was then utilized to extract and synthesize insights from these articles. The main contributions include 1) five dimensions that researchers have used to conceptualize explainability; 2) a classification scheme of explanation designs; 3) a categorization of explainability measurements into six user-centered dimensions. The review concludes by reflecting on ongoing challenges and providing recommendations for future exploration of related issues. The findings shed light on the theoretical foundations of human-centered explainability, informing the design of interactive information systems that better align with diverse user needs and promoting the development of systems that are transparent, trustworthy, and accountable.

cs.HC↗

arXiv2025

MMLU-Reason: Benchmarking Multi-Task Multi-modal Language Understanding and Reasoning

Recent advances in Multi-Modal Large Language Models (MLLMs) have enabled unified processing of language, vision, and structured inputs, opening the door to complex tasks such as logical deduction, spatial reasoning, and scientific analysis. Despite their promise, the reasoning capabilities of MLLMs, particularly those augmented with intermediate thinking traces (MLLMs-T), remain poorly understood and lack standardized evaluation benchmarks. Existing work focuses primarily on perception or final answer correctness, offering limited insight into how models reason or fail across modalities. To address this gap, we introduce the MMLU-Reason, a new benchmark designed to rigorously evaluate multi-modal reasoning with explicit thinking. The MMLU-Reason comprises 1) a high-difficulty dataset of 1,083 questions spanning six diverse reasoning types with symbolic depth and multi-hop demands and 2) a modular Reasoning Trace Evaluation Pipeline (RTEP) for assessing reasoning quality beyond accuracy through metrics like relevance, consistency, and structured error annotations. Empirical results show that MLLMs-T overall outperform non-thinking counterparts, but even top models like Claude-3.7-Sonnet and Gemini-2.5 Pro suffer from reasoning pathologies such as inconsistency and overthinking. This benchmark reveals persistent gaps between accuracy and reasoning quality and provides an actionable evaluation pipeline for future model development. Overall, the MMLU-Reason offers a scalable foundation for evaluating, comparing, and improving the next generation of multi-modal reasoning systems.

cs.AI↗

arXiv2025

AI-Empowered Channel Generation for IoV Semantic Communications in Dynamic Conditions

The Internet of Vehicles (IoV) transforms the transportation ecosystem promising pervasive connectivity and data-driven approaches. Deep learning and generative Artificial Intelligence (AI) have the potential to significantly enhance the operation of applications within IoV by facilitating efficient decision-making and predictive capabilities, including intelligent navigation, vehicle safety monitoring, accident prevention, and intelligent traffic management. Nevertheless, efficiently transmitting and processing the massive volumes of data generated by the IoV in real-time remains a significant challenge, particularly in dynamic and unpredictable wireless channel conditions. To address these challenges, this paper proposes a semantic communication framework based on channel perception to improve the accuracy and efficiency of data transmission. The semantic communication model extracts and compresses the information to be transmitted. In addition, the wireless channel is estimated by using a generative diffusion model, which is employed to predict the dynamic channel states, thereby improving the quality of IoV service. In dynamic scenarios, however, the channel estimation performance may be degraded when substantially new scenarios take place, which will adversely affect user experience. To mitigate this limitation, we employ a large model to fine-tune the channel generation model to enhance its adaptability for varying scenarios. The performance and reliability of the proposed framework are evaluated on the two public datasets.

cs.NI↗

arXiv2025

Influence of oxygen-defects on intraband terahertz conductivity of carbon nanotubes

The exceptional charge transport properties of single-walled carbon nanotubes (SWCNTs) enable numerous ultrafast optoelectronic applications. Modifying SWCNTs by introducing defects significantly impacts the performance of nanotube-based devices, making defect characterization crucial. This research tracked these effects in oxygen plasma-treated SWCNT thin films. Sub-picosecond electric fields of varying strengths and additional photoexcitation were used to assess how defects influence charge carrier transport. Changes in effective conductivity within the terahertz (THz) range were found to be strongly dependent on impurity levels. The plasmon resonance shift to higher THz frequencies aligns with the defect-induced reduction in conductivity and slowed carrier migration within the network. An increase in THz field strength resulted in diminished conductivity due to intraband absorption bleaching. To address the emergence of hot charge carriers, a modified Drude model, which considers non-equilibrium charge carrier distribution via fielddependent scattering rates, was applied. The dominant charge-impurity scattering rate in plasma-treated samples corresponded with an increase in defects. Additionally, the impact of defects on charge carrier dynamics on a picosecond timescale was examined. The modeled plasma-treated SWCNTs wire-grid polarizer for the THz range reveals the potential for multi-level engineering of THz devices to customize properties through controlled defect populations.

cond-mat.mtrl-sci↗

arXiv2025

From Conversation to Orchestration: HCI Challenges and Opportunities in Interactive Multi-Agentic Systems

Recent advances in multi-agentic systems (e.g. AutoGen, OpenAI Swarm) allow users to interact with a group of specialised AI agents rather than a single general-purpose agent. Despite the promise of this new paradigm, the HCI community has yet to fully examine the opportunities, risks, and user-centred challenges it introduces. We contribute to research on multi-agentic systems by exploring their architectures and key features through a human-centred lens. While literature and use cases remain limited, we build on existing tools and frameworks available to developers to identify a set of overarching challenges, e.g. orchestration and conflict resolution, that can guide future research in HCI. We illustrate these challenges through examples, offer potential design considerations, and provide research opportunities to spark interdisciplinary conversation. Our work lays the groundwork for future exploration and offers a research agenda focused on user-centred design in multi-agentic systems.

cs.HC↗

arXiv2025

Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learning

Medical Question-Answering (QA) encompasses a broad spectrum of tasks, including multiple choice questions (MCQ), open-ended text generation, and complex computational reasoning. Despite this variety, a unified framework for delivering high-quality medical QA has yet to emerge. Although recent progress in reasoning-augmented large language models (LLMs) has shown promise, their ability to achieve comprehensive medical understanding is still largely unexplored. In this paper, we present Med-U1, a unified framework for robust reasoning across medical QA tasks with diverse output formats, ranging from MCQs to complex generation and computation tasks. Med-U1 employs pure large-scale reinforcement learning with mixed rule-based binary reward functions, incorporating a length penalty to manage output verbosity. With multi-objective reward optimization, Med-U1 directs LLMs to produce concise and verifiable reasoning chains. Empirical results reveal that Med-U1 significantly improves performance across multiple challenging Med-QA benchmarks, surpassing even larger specialized and proprietary models. Furthermore, Med-U1 demonstrates robust generalization to out-of-distribution (OOD) tasks. Extensive analysis presents insights into training strategies, reasoning chain length control, and reward design for medical LLMs. Our code is available here.

cs.CL↗

arXiv2025

Video-Mediated Emotion Disclosure: Expressions of Fear, Sadness, and Joy by People with Schizophrenia on YouTube

Individuals with schizophrenia frequently experience intense emotions and often turn to vlogging as a medium for emotional expression. While previous research has predominantly focused on text based disclosure, little is known about how individuals construct narratives around emotions and emotional experiences in video blogs. Our study addresses this gap by analyzing 200 YouTube videos created by individuals with schizophrenia. Drawing on media research and self presentation theories, we developed a visual analysis framework to disentangle these videos. Our analysis revealed diverse practices of emotion disclosure through both verbal and visual channels, highlighting the dynamic interplay between these modes of expression. We found that the deliberate construction of visual elements, including environmental settings and specific aesthetic choices, appears to foster more supportive and engaged viewer responses. These findings underscore the need for future large scale quantitative research examining how visual features shape video mediated communication on social media platforms. Such investigations would inform the development of care centered video sharing platforms that better support individuals managing illness experiences.

cs.HC↗

arXiv2025

Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity

The current state-of-the-art No-Reference Image Quality Assessment (NR-IQA) methods typically rely on feature extraction from upstream semantic backbone networks, assuming that all extracted features are relevant. However, we make a key observation that not all features are beneficial, and some may even be harmful, necessitating careful selection. Empirically, we find that many image pairs with small feature spatial distances can have vastly different quality scores, indicating that the extracted features may contain a significant amount of quality-irrelevant noise. To address this issue, we propose a Quality-Aware Feature Matching IQA Metric (QFM-IQM) that employs an adversarial perspective to remove harmful semantic noise features from the upstream task. Specifically, QFM-IQM enhances the semantic noise distinguish capabilities by matching image pairs with similar quality scores but varying semantic features as adversarial semantic noise and adaptively adjusting the upstream task's features by reducing sensitivity to adversarial noise perturbation. Furthermore, we utilize a distillation framework to expand the dataset and improve the model's generalization ability. Our approach achieves superior performance to the state-of-the-art NR-IQA methods on eight standard IQA datasets.

cs.CV↗

arXiv2025

Faces of the Mind: Unveiling Mental Health States Through Facial Expressions in 11,427 Adolescents

Mood disorders such as depression and anxiety often manifest through facial expressions, but existing machine learning algorithms designed to assess these disorders have been hindered by small datasets and limited real-world applicability. To address this gap, we analyzed facial videos of 11,427 participants - a dataset two orders of magnitude larger than those used in previous studies - including standardized facial expression videos and psychological assessments of depression, anxiety, and stress. However, scaling up the dataset introduces significant challenges due to increased symptom heterogeneity, making it difficult for models to learn accurate representations. To address this, we introduced the Symptom Discrepancy Index (SDI), a novel metric for quantifying dataset heterogeneity caused by variability in individual symptoms among samples with identical total scores. By removing the 10% most heterogeneous cases as identified by the SDI, we raised the F1 scores of all models from approximately 50% to 80%. Notably, comparable performance gains were observed within both the retained and excluded subsets. These findings demonstrate symptom heterogeneity, not model capacity, as the principal bottleneck in large scale automated assessment and provide a general solution that is readily applicable to other psychometric data sets.

cs.CV↗

arXiv2025

CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making

In medical visual question answering (Med-VQA), achieving accurate responses relies on three critical steps: precise perception of medical imaging data, logical reasoning grounded in visual input and textual questions, and coherent answer derivation from the reasoning process. Recent advances in general vision-language models (VLMs) show that large-scale reinforcement learning (RL) could significantly enhance both reasoning capabilities and overall model performance. However, their application in medical domains is hindered by two fundamental challenges: 1) misalignment between perceptual understanding and reasoning stages, and 2) inconsistency between reasoning pathways and answer generation, both compounded by the scarcity of high-quality medical datasets for effective large-scale RL. In this paper, we first introduce Med-Zero-17K, a curated dataset for pure RL-based training, encompassing over 30 medical image modalities and 24 clinical tasks. Moreover, we propose a novel large-scale RL framework for Med-VLMs, Consistency-Aware Preference Optimization (CAPO), which integrates rewards to ensure fidelity between perception and reasoning, consistency in reasoning-to-answer derivation, and rule-based accuracy for final responses. Extensive experiments on both in-domain and out-of-domain scenarios demonstrate the superiority of our method over strong VLM baselines, showcasing strong generalization capability to 3D Med-VQA benchmarks and R1-like training paradigms.

cs.CV↗

arXiv2025

A review of theories and models utilized by empirical studies about mental health help-seeking and implications for future research

Purpose: With the rise of mental health risks globally, it is urgent to provide effective mental health support. However, a holistic understanding of how people seek help for mental health problems remains limited, impeding the development of evidence-based intervention programs to facilitate help-seeking behavior. This study reviews current theories that guide empirical research on young adults' help-seeking behavior using technologies, identifies limitations in existing frameworks, and proposes directions for future research. Methods: We searched databases that are most likely to contain mental health help-seeking practices in relation to information technology, including PubMed, ACM Digital Library, Web of Science, PsycInfo, ScienceDirect, EBSCO, and Cochrane Library. Results: Of 2443 abstracts reviewed, 43 studies met the criteria and were included in the analysis. We identified 16 theories and models. They represent seven perspectives to view mental health help-seeking and reveal factors such as accessibility, stigma, and social support as key factors influencing help-seeking. Limitations: We summarized the theories and models and categorized them based on their primary perspectives. Cross-perspective connections could be explored in future reviews. Conclusions: A holistic approach to creating culturally sensitive multi-level interventions that consider individual, interpersonal, and community factors is needed to advance effective mental health help-seeking support strategies.

cs.HC↗

arXiv2025

Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding

While Large Language Models (LLMs) support long contexts, they struggle with performance degradation within the context window. Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored. From the decoding perspective, we identify the Posterior Salience Attenuation (PSA) phenomenon, where the salience ratio correlates with long-text performance degradation. Notably, despite the attenuation, gold tokens still occupy high-ranking positions in the decoding space. Motivated by it, we propose the training-free Positional Contrastive Decoding (PCD) that contrasts the logits derived from long-aware attention with those from designed local-aware attention, enabling the model to focus on the gains introduced by large-scale short-to-long training. Through the analysis of long-term decay simulation, we demonstrate that PCD effectively alleviates attention score degradation. Experimental results show that PCD achieves state-of-the-art performance on long-context benchmarks.

cs.CL↗

arXiv2025

Coherence-guided Preference Disentanglement for Cross-domain Recommendations

Discovering user preferences across different domains is pivotal in cross-domain recommendation systems, particularly when platforms lack comprehensive user-item interactive data. The limited presence of shared users often hampers the effective modeling of common preferences. While leveraging shared items' attributes, such as category and popularity, can enhance cross-domain recommendation performance, the scarcity of shared items between domains has limited research in this area. To address this, we propose a Coherence-guided Preference Disentanglement (CoPD) method aimed at improving cross-domain recommendation by i) explicitly extracting shared item attributes to guide the learning of shared user preferences and ii) disentangling these preferences to identify specific user interests transferred between domains. CoPD introduces coherence constraints on item embeddings of shared and specific domains, aiding in extracting shared attributes. Moreover, it utilizes these attributes to guide the disentanglement of user preferences into separate embeddings for interest and conformity through a popularity-weighted loss. Experiments conducted on real-world datasets demonstrate the superior performance of our proposed CoPD over existing competitive baselines, highlighting its effectiveness in enhancing cross-domain recommendation performance.

cs.IR↗