arXiv subjects

Yan Zhang

Publications and source records attributed to Yan Zhang.

At least 217 records · Page 12Linked to original sources

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↗

arXiv2025

FuXi-Air: Urban Air Quality Forecasting Based on Emission-Meteorology-Pollutant multimodal Machine Learning

Air pollution has emerged as a major public health challenge in megacities. Numerical simulations and single-site machine learning approaches have been widely applied in air quality forecasting tasks. However, these methods face multiple limitations, including high computational costs, low operational efficiency, and limited integration with observational data. With the rapid advancement of artificial intelligence, there is an urgent need to develop a low-cost, efficient air quality forecasting model for smart urban management. An air quality forecasting model, named FuXi-Air, has been constructed in this study based on multimodal data fusion to support high-precision air quality forecasting and operated in typical megacities. The model integrates meteorological forecasts, emission inventories, and pollutant monitoring data under the guidance of air pollution mechanism. By combining an autoregressive prediction framework with a frame interpolation strategy, the model successfully completes 72-hour forecasts for six major air pollutants at an hourly resolution across multiple monitoring sites within 25-30 seconds. In terms of both computational efficiency and forecasting accuracy, it outperforms the mainstream numerical air quality models in operational forecasting work. Ablation experiments concerning key influencing factors show that although meteorological data contribute more to model accuracy than emission inventories do, the integration of multimodal data significantly improves forecasting precision and ensures that reliable predictions are obtained under differing pollution mechanisms across megacities. This study provides both a technical reference and a practical example for applying multimodal data-driven models to air quality forecasting and offers new insights into building hybrid forecasting systems to support air pollution risk warning in smart city management.

cs.LG↗

arXiv2025

UCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learning

Unsupervised Camoflaged Object Detection (UCOD) has gained attention since it doesn't need to rely on extensive pixel-level labels. Existing UCOD methods typically generate pseudo-labels using fixed strategies and train 1 x1 convolutional layers as a simple decoder, leading to low performance compared to fully-supervised methods. We emphasize two drawbacks in these approaches: 1). The model is prone to fitting incorrect knowledge due to the pseudo-label containing substantial noise. 2). The simple decoder fails to capture and learn the semantic features of camouflaged objects, especially for small-sized objects, due to the low-resolution pseudo-labels and severe confusion between foreground and background pixels. To this end, we propose a UCOD method with a teacher-student framework via Dynamic Pseudo-label Learning called UCOD-DPL, which contains an Adaptive Pseudo-label Module (APM), a Dual-Branch Adversarial (DBA) decoder, and a Look-Twice mechanism. The APM module adaptively combines pseudo-labels generated by fixed strategies and the teacher model to prevent the model from overfitting incorrect knowledge while preserving the ability for self-correction; the DBA decoder takes adversarial learning of different segmentation objectives, guides the model to overcome the foreground-background confusion of camouflaged objects, and the Look-Twice mechanism mimics the human tendency to zoom in on camouflaged objects and performs secondary refinement on small-sized objects. Extensive experiments show that our method demonstrates outstanding performance, even surpassing some existing fully supervised methods. The code is available now.

cs.CV↗

arXiv2025

Modality-Fair Preference Optimization for Trustworthy MLLM Alignment

Multimodal large language models (MLLMs) have achieved remarkable success across various tasks. However, separate training of visual and textual encoders often results in a misalignment of the modality. Such misalignment may lead models to generate content that is absent from the input image, a phenomenon referred to as hallucination. These inaccuracies severely undermine the trustworthiness of MLLMs in real-world applications. Despite attempts to optimize text preferences to mitigate this issue, our initial investigation indicates that the trustworthiness of MLLMs remains inadequate. Specifically, these models tend to provide preferred answers even when the input image is heavily distorted. Analysis of visual token attention also indicates that the model focuses primarily on the surrounding context rather than the key object referenced in the question. These findings highlight a misalignment between the modalities, where answers inadequately leverage input images. Motivated by our findings, we propose Modality-Fair Preference Optimization (MFPO), which comprises three components: the construction of a multimodal preference dataset in which dispreferred images differ from originals solely in key regions; an image reward loss function encouraging the model to generate answers better aligned with the input images; and an easy-to-hard iterative alignment strategy to stabilize joint modality training. Extensive experiments on three trustworthiness benchmarks demonstrate that MFPO significantly enhances the trustworthiness of MLLMs. In particular, it enables the 7B models to attain trustworthiness levels on par with, or even surpass, those of the 13B, 34B, and larger models.

cs.CV↗

arXiv2025

CSVAR: Enhancing Visual Privacy in Federated Learning via Adaptive Shuffling Against Overfitting

Although federated learning preserves training data within local privacy domains, the aggregated model parameters may still reveal private characteristics. This vulnerability stems from clients' limited training data, which predisposes models to overfitting. Such overfitting enables models to memorize distinctive patterns from training samples, thereby amplifying the success probability of privacy attacks like membership inference. To enhance visual privacy protection in FL, we present CSVAR(Channel-Wise Spatial Image Shuffling with Variance-Guided Adaptive Region Partitioning), a novel image shuffling framework to generate obfuscated images for secure data transmission and each training epoch, addressing both overfitting-induced privacy leaks and raw image transmission risks. CSVAR adopts region-variance as the metric to measure visual privacy sensitivity across image regions. Guided by this, CSVAR adaptively partitions each region into multiple blocks, applying fine-grained partitioning to privacy-sensitive regions with high region-variances for enhancing visual privacy protection and coarse-grained partitioning to privacy-insensitive regions for balancing model utility. In each region, CSVAR then shuffles between blocks in both the spatial domains and chromatic channels to hide visual spatial features and disrupt color distribution. Experimental evaluations conducted on diverse real-world datasets demonstrate that CSVAR is capable of generating visually obfuscated images that exhibit high perceptual ambiguity to human eyes, simultaneously mitigating the effectiveness of adversarial data reconstruction attacks and achieving a good trade-off between visual privacy protection and model utility.

cs.CR↗

arXiv2025

HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models

Medical Vision-Language Models (Med-VLMs) have achieved success across various tasks, yet most existing methods overlook the modality misalignment issue that can lead to untrustworthy responses in clinical settings. In this paper, we propose Hierarchical Self-Contrastive Rewarding (HSCR), a novel approach that addresses two critical challenges in Med-VLM alignment: 1) Cost-effective generation of high-quality preference data; 2) Capturing nuanced and context-aware preferences for improved alignment. HSCR first leverages the inherent capability of Med-VLMs to generate dispreferred responses with higher sampling probability. By analyzing output logit shifts after visual token dropout, we identify modality-coupled tokens that induce misalignment and derive an implicit alignment reward function. This function guides token replacement with hallucinated ones during decoding, producing high-quality dispreferred data. Furthermore, HSCR introduces a multi-level preference optimization strategy, which extends beyond traditional adjacent-level optimization by incorporating nuanced implicit preferences, leveraging relative quality in dispreferred data to capture subtle alignment cues for more precise and context-aware optimization. Extensive experiments across multiple medical tasks, including Med-VQA, medical image captioning and instruction following, demonstrate that HSCR not only enhances zero-shot performance but also significantly improves modality alignment and trustworthiness with just 2,000 training entries.

cs.CV↗

arXiv2025

Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering

Multimodal large language models (MLLMs) still struggle with complex reasoning tasks in Visual Question Answering (VQA). While current methods have advanced by incorporating visual prompts, our study uncovers critical limitations: these approaches indiscriminately annotate all detected objects for every visual question, generating excessive visual markers that degrade task performance. This issue stems primarily from a lack of focus on key visual elements, raising two important questions: Are all objects equally important, and do all questions require visual prompts? Motivated by Dual Process Theory, which distinguishes between instinctive and deliberate cognitive modes in human reasoning, we propose FOCUS, a plug-and-play approach that dynamically adapts to the complexity of questions, combining fast intuitive judgments with deliberate analytical reasoning to enhance the vision-language reasoning capability of the MLLM. For straightforward questions, FOCUS supports efficient zero-shot reasoning. For more complex tasks, it employs the conceptualizing before observation strategy to highlight critical elements. Extensive experiments on four benchmarks, ScienceQA, TextQA, VizWiz, and MME, demonstrate that FOCUS consistently improves the performance of both open-source and black-box MLLMs, achieving significant gains across all datasets. Ablation studies further validate the importance of combining diverse cognitive strategies with refined visual information for superior performance. Code will be released.

cs.CL↗

arXiv2025

Network Model Averaging Prediction for Latent Space Models by K-Fold Edge Cross-Validation

In complex systems, networks represent connectivity relationships between nodes through edges. Latent space models are crucial in analyzing network data for tasks like community detection and link prediction due to their interpretability and visualization capabilities. However, when the network size is relatively small, and the true latent space dimension is considerable, the parameters in latent space models may not be estimated very well. To address this issue, we propose a Network Model Averaging (NetMA) method tailored for latent space models with varying dimensions, specifically focusing on link prediction in networks. For both single-layer and multi-layer networks, we first establish the asymptotic optimality of the proposed averaging prediction in the sense of achieving the lowest possible prediction loss. Then we show that when the candidate models contain some correct models, our method assigns all weights to the correct models. Furthermore, we demonstrate the consistency of the NetMA-based weight estimator tending to the optimal weight vector. Extensive simulation studies show that NetMA performs better than simple averaging and model selection methods, and even outperforms the "oracle" method when the real latent space dimension is relatively large. Evaluation on collaboration and virtual event networks further emphasizes the competitiveness of NetMA in link prediction performance.

stat.ME↗

arXiv2025

Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs

Multi-modal Large Language Models (MLLMs) excel at single-image tasks but struggle with multi-image understanding due to cross-modal misalignment, leading to hallucinations (context omission, conflation, and misinterpretation). Existing methods using Direct Preference Optimization (DPO) constrain optimization to a solitary image reference within the input sequence, neglecting holistic context modeling. We propose Context-to-Cue Direct Preference Optimization (CcDPO), a multi-level preference optimization framework that enhances per-image perception in multi-image settings by zooming into visual clues -- from sequential context to local details. It features: (i) Context-Level Optimization : Re-evaluates cognitive biases underlying MLLMs' multi-image context comprehension and integrates a spectrum of low-cost global sequence preferences for bias mitigation. (ii) Needle-Level Optimization : Directs attention to fine-grained visual details through region-targeted visual prompts and multimodal preference supervision. To support scalable optimization, we also construct MultiScope-42k, an automatically generated dataset with high-quality multi-level preference pairs. Experiments show that CcDPO significantly reduces hallucinations and yields consistent performance gains across general single- and multi-image tasks.

cs.CV↗

arXiv2025

MLEP: Multi-granularity Local Entropy Patterns for Universal AI-generated Image Detection

Advancements in image generation technologies have raised significant concerns about their potential misuse, such as producing misinformation and deepfakes. Therefore, there is an urgent need for effective methods to detect AI-generated images (AIGI). Despite progress in AIGI detection, achieving reliable performance across diverse generation models and scenes remains challenging due to the lack of source-invariant features and limited generalization capabilities in existing methods. In this work, we explore the potential of using image entropy as a cue for AIGI detection and propose Multi-granularity Local Entropy Patterns (MLEP), a set of entropy feature maps computed across shuffled small patches over multiple image scaled. MLEP comprehensively captures pixel relationships across dimensions and scales while significantly disrupting image semantics, reducing potential content bias. Leveraging MLEP, a robust CNN-based classifier for AIGI detection can be trained. Extensive experiments conducted in an open-world scenario, evaluating images synthesized by 32 distinct generative models, demonstrate significant improvements over state-of-the-art methods in both accuracy and generalization.

cs.CV↗

arXiv2025

Confidence-Regulated Generative Diffusion Models for Reliable AI Agent Migration in Vehicular Metaverses

Vehicular metaverses are an emerging paradigm that merges intelligent transportation systems with virtual spaces, leveraging advanced digital twin and Artificial Intelligence (AI) technologies to seamlessly integrate vehicles, users, and digital environments. In this paradigm, vehicular AI agents are endowed with environment perception, decision-making, and action execution capabilities, enabling real-time processing and analysis of multi-modal data to provide users with customized interactive services. Since vehicular AI agents require substantial resources for real-time decision-making, given vehicle mobility and network dynamics conditions, the AI agents are deployed in RoadSide Units (RSUs) with sufficient resources and dynamically migrated among them. However, AI agent migration requires frequent data exchanges, which may expose vehicular metaverses to potential cyber attacks. To this end, we propose a reliable vehicular AI agent migration framework, achieving reliable dynamic migration and efficient resource scheduling through cooperation between vehicles and RSUs. Additionally, we design a trust evaluation model based on the theory of planned behavior to dynamically quantify the reputation of RSUs, thereby better accommodating the personalized trust preferences of users. We then model the vehicular AI agent migration process as a partially observable markov decision process and develop a Confidence-regulated Generative Diffusion Model (CGDM) to efficiently generate AI agent migration decisions. Numerical results demonstrate that the CGDM algorithm significantly outperforms baseline methods in reducing system latency and enhancing robustness against cyber attacks.

cs.LG↗