Search Results (56)

The diffusion model (DM) is a hot topic in deep generative models and is widely applied in image generation. In diffusion models, there are four main “secrets” that affect high-quality image generation: constructing the diffusion model, improving the sampling velocity, designing the diffusion process, and guiding diffusion models. How should one construct the diffusion model? How can one improve the sampling velocity? How should one design the diffusion process? How should one guide diffusion models? These questions are critical to enhancing diffusion model performance. However, most existing review papers focus on applications, while discussion of the four key technical aspects remains limited. In response, this paper summarizes four key technologies and six representative application directions. First, the basic principles of diffusion models are reviewed from three perspectives: denoising diffusion probabilistic models, noise conditional score network models, and stochastic differential equation models. Second, key techniques for improving sampling velocity are summarized from three perspectives: non-Markovian sampling, knowledge distillation sampling, and discrete optimization sampling. Third, the diffusion process design is summarized from three perspectives: latent space, Transformer-based diffusion, and non-Euclidean space. Fourth, guidance strategies are summarized from three perspectives: classifier guidance, classifier-free guidance, and multimodal guidance. Fifth, the advantages and applications of diffusion models are discussed in high-quality text-to-image generation, high-quality text-to-video generation, and high-quality image-to-image generation. Finally, this paper discusses the challenges faced by diffusion models in image generation. Overall, this review systematically discusses the four “secrets” of diffusion models for image generation and provides a useful reference for future research in this field. Full article

Neural language models have achieved remarkable progress in semantic representation learning. However, cross-domain representation learning still suffers from prominent semantic noise propagation issues. Existing methods still face challenges in cross-domain semantic modeling, including limited robustness across different semantic granularities, difficulty in separating transferable semantics from task-irrelevant semantic interference, and insufficient adaptability to specialized scenarios. These issues may reduce feature discriminability in fine-grained semantic tasks and complex application settings. To address these problems, we propose the Diffusion-Coded Attention Network (DCANet), a novel cross-domain representation learning architecture with three synergistic core modules: a multi-granular parallel diffusion masking mechanism for cross-scale context fusion via stochastic path activation, an implicit semantic encoder that distills domain-invariant patterns into adaptive bias codes via shared latent manifolds, and a self-correcting attention topology realizing dynamic semantic purification via closed-loop interactions between local features and global bias states. Extensive evaluations are conducted on nine well-recognized benchmark datasets to verify DCANet’s effectiveness and reliability. Experimental results show that DCANet attains state-of-the-art results on the majority of the benchmark datasets, with significant accuracy improvements on text classification and sentiment analysis tasks. Full article

Adverse drug reaction (ADR) detection is essential for ensuring drug safety and effective pharmacovigilance. The rapid growth of users’ medication reviews posted on social media has introduced a valuable new data source for ADR detection. However, the large scale and high noise inherent in social media text pose substantial challenges to existing detection methods. Although large language models (LLMs) exhibit strong robustness to noisy and interfering information, they are often limited by issues such as stochastic outputs and hallucinations. To address these challenges, this paper proposes two generative detection frameworks based on Chain of Thought (CoT), namely LLaMA-DetectionADR for Supervised Fine-Tuning (SFT) and DetectionADRGPT for low-resource in-context learning. LLaMA-DetectionADR automatically generates CoT reasoning sequences to construct an instruction tuning dataset, which is then used to fine-tune the LLaMA3-8B model via Quantized Low-Rank Adaptation (QLoRA). In contrast, DetectionADRGPT leverages clustering algorithms to select representative unlabeled samples and enhances in-context learning by incorporating CoT reasoning paths together with their corresponding labels. Experimental results on the Twitter and CADEC social media datasets show that LLaMA-DetectionADR achieves excellent performance, with F1 scores of 92.67% and 86.13%, respectively. Meanwhile, DetectionADRGPT obtains competitive F1 scores of 87.29% and 82.80% with only a few labeled examples, approaching the performance of fully supervised advanced models. The overall results demonstrate the effectiveness and practical value of the proposed CoT-based generative frameworks for ADR detection from social media. Full article

Current security solutions predominantly rely on cloud-based implementations, often neglecting computational resource constraints and operational efficiency. While contemporary methodologies typically require additional training, the few that operate without retraining frequently yield suboptimal performance. To address these limitations, this work leverages a pre-trained MTCNN architecture to detect faces of copyright-protected individuals. We construct a facial landmark database comprising five critical fiducial points, which serves as a supplementary module integrated into the stable diffusion framework, enabling real-time security filtering for synthesized video content. The proposed system utilizes MTCNN models pre-trained in the cloud to build a repository of copyrighted facial signatures, generating a geometric parameter database of facial landmarks. This database, coupled with a parallel verification unit, functions as a plugin within the standard Stable Diffusion pipeline. By leveraging Stable Diffusion’s native decoder, we decode stochastic frames from the U-Net latent representations and perform real-time comparative analysis to identify potential copyright violations in generated video sequences. Upon detecting an infringement, an on-screen display (OSD) alert notifies the user and immediately halts the text-to-video (T2V) generation process. Experimental evaluations demonstrate that our framework effectively mitigates the resource constraints and latency issues inherent in edge deployment scenarios of prior security implementations. Leveraging MTCNN’s proven robustness and extensive edge compatibility for facial recognition, the proposed detection and obfuscation plugin integrates seamlessly with Stable Diffusion while preserving generation quality. Full article

Diffusion models have emerged as a powerful class of generative models, demonstrating impressive results across visual domains such as image and video synthesis. This survey provides a comprehensive taxonomy of generative models, with a particular focus on diffusion models and their applications in enhancing visual fidelity for text-to-image and text-to-video generation. We discuss the theoretical foundations of diffusion models, including their formulation through stochastic differential equations, and analyze the forward noising and reverse denoising processes that enable stable training and high-quality generation. The survey further categorizes diffusion architectures, including pixel-space and latent-space models, and examines their design choices, training strategies, and trade-offs across different resolution regimes. In addition, we review noise characteristics in real-world imaging domains and discuss their implications for diffusion-based models. Denoising strategies are analyzed by distinguishing between in-model denoising mechanisms and external denoising techniques used in preprocessing and post-processing pipelines. The survey also summarizes commonly used datasets and evaluation metrics for generative modeling, providing a practical perspective on benchmarking and model comparison. Finally, we discuss current challenges, including computational efficiency, scalability, and robustness to diverse noise distributions, and outline potential directions for future research. This survey aims to provide a structured reference for understanding diffusion models and their applications in visual generation tasks. Full article

Financial data analysis remains a significant challenge due to the inherent stochasticity, non-stationarity, and low signal-to-noise ratio of market data. Conventional methods often struggle to disentangle intrinsic trends from noise and frequently overlook the critical influence of investor sentiment on price dynamics. To address these issues, we propose an adaptive trading model named CBAM-BiLSTM-DDQN, which integrates signal decomposition, multi-source feature fusion, and deep reinforcement learning. First, we construct a comprehensive heterogeneous feature set by combining price signals decomposed via Variational Mode Decomposition (VMD) and investor sentiment indices extracted from financial texts. Subsequently, a Genetic Algorithm (GA) is employed to identify the most significant feature subset, effectively reducing dimensionality and redundancy. Finally, these optimized features are input into a Double Deep Q-Network (DDQN) agent equipped with a Convolutional Block Attention Module (CBAM) and a Bidirectional Long Short-Term Memory (BiLSTM) network to capture complex spatiotemporal dependencies. We evaluated this approach through simulated trading on three major Chinese stock indices—the Shanghai Stock Exchange Composite (SSEC), the Shenzhen Stock Exchange Component (SZSE), and the China Securities 300 (CSI 300). Experimental results demonstrate the superiority of our method over traditional strategies and standard baselines; specifically, the trading agent achieved robust cumulative returns across the SSEC and CSI 300 indices, confirming the model’s exceptional capability in balancing profitability and risk aversion in complex financial environments. Furthermore, additional experiments on individual stocks in the Chinese A-share market reinforce the robustness and generalization ability of our proposed model, validating its practical potential for diverse trading scenarios. Furthermore, additional experiments on individual stocks in the Chinese A-share market reinforce the robustness and generalization ability of our proposed model, validating its practical potential for diverse trading scenarios. Full article

This paper presents a bibliometric analysis and literature review of methodologies for optimal capital structure decision making, focusing on research published between 2000 and 2024. This study reviews current research, identifies gaps, and outlines a plan to support with financial decisions. A mixed-methods approach was employed, combining data from the Web of Science and Scopus databases using the search string “capital structure” AND (“decision making” OR “optimal structure”). The study used Bibliometrix(R), VOSviewer, and NVivo tools, and followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) flowchart for choosing studies. The findings show that this field is well-developed but still changing. The intellectual structure is organized around two main clusters: one focused on testing classical theories and another oriented toward optimization and managerial applications, revealing a clear theory–practice divide. The mapping also highlights the dominance of Chinese and U.S. scholarship and the central role of practitioner-oriented journals such as Managerial Finance, indicating both a shift toward emerging markets and a strong demand for applicable research. The study provides three key contributions. First, it identifies important countries, authors, outlets, and themes. Second, it uses a method that combines bibliometric and text-mining tools. Third, it introduces a new decision-support framework that is thorough, context-sensitive, and flexible. There are some limitations. These include relying on Scopus and Web of Science, language limits, and the fact that bibliometrics cannot judge the quality of methods. Future research should empirically validate the proposed framework in different contexts, expand studies in emerging markets, test emerging theories such as Brusov–Filatova–Orekhova (BFO) theory, and develop more dynamic and stochastic models to better capture financial uncertainty. Full article

Profile images from social networks are a valuable source of data for AI analytics, but they contain biometric identifiers that pose serious privacy risks. The current face anonymization techniques often destroy semantic information, and generative de-identification methods are vulnerable to re-identification attacks. In this paper, we propose a template-driven multimodal face pseudonymization framework that allows for the privacy-preserving analysis of facial image data while retaining analytically relevant attributes. Our approach uses a FaceNet-based CelebA attribute classifier to extract fine-grained facial attributes and a DeepFace model to extract high-level demographic attributes. Rather than relying on stochastic large language models, we introduce deterministic template-based attribute-to-text conversion to ensure consistency and reproducibility and prevent unintended attribute hallucination. The resulting textual description serves as the sole conditioning input for Janus-Pro, a multimodal text-to-image generation model that synthesizes realistic yet non-identifiable face images. We evaluate our method on the CelebA dataset under a strong adversarial threat model, employing state-of-the-art face recognition systems to assess re-identification and linkability attacks. Our results demonstrate a substantial reduction in identity leakage while preserving semantic attributes. Full article

As large language models (LLMs) are increasingly used as digital respondents and generative agents in computational social science, prior work has primarily focused on the fidelity of their expressed opinions, often overlooking a fundamental question: the behavioral stability of outputs across repeated runs of the same model when the persona specification and task conditions remain unchanged. This paper proposes a behavioral stability evaluation framework for role-playing tasks, using the Political Compass questionnaire as the testbed. The questionnaire maps responses onto a two-dimensional coordinate system defined by an economic axis and a social axis, enabling political orientations to be directly quantified and compared in a continuous space. To ground the simulation in realistic user behaviors, we construct personas from publicly available social media texts and stratify them based on Political Signal Clarity. Across three LLMs, we compare repeated questionnaire completions under different decoding temperatures and prompting strategies. We characterize it along two complementary dimensions: dispersion of the resulting two-dimensional coordinates across runs, measured by an Overall Stability Score (OSS), and dispersion of per-item choices across runs, quantified by response entropy. We further use linear mixed-effects models to account for persona-level heterogeneity and to estimate the effects of key factors on stability. Our results show that coordinate drift and item-level dispersion do not always move in tandem. Increasing temperature typically amplifies variability, although models differ in their sensitivity. Contrary to its success in reasoning tasks, Chain-of-Thought (CoT) prompting failed to enhance stability in this value-laden context. Instead, it frequently amplified coordinate drift by introducing stochasticity into intermediate reasoning steps. Results show that LLMs exhibit greater behavioral stability when role-playing personas with clearer political signals. These findings suggest that stability should be treated as a pre-study benchmark before deploying LLM-based role-playing simulations, and that key generation settings and stability statistics should be reported alongside substantive conclusions. Full article

Ontology learning from unstructured text has become a critical task for knowledge-driven applications in Big Data and Artificial Intelligence. While significant advances have been made in the automatic extraction of concepts and relations using neural and Transformer-based models, the generation of formal Description Logic axioms required for constructing logically consistent and computationally tractable ontologies remains largely underexplored. This paper puts forward a novel pipeline for automated axiom generation through schema mapping. Our paper introduces three key innovations: a deterministic mapping framework that guarantees logical consistency (unlike stochastic Large Language Models); guaranteed formal consistency verified by OWL reasoners (unaddressed by prior statistical methods); and a transparent, scalable bridge from neural extractions to symbolic logic, eliminating manual post-processing. Technically, the pipeline builds upon the outputs of a Transformer-based fusion model for joint concept and relation extraction. We then map lexical relational phrases to formal ontological properties through a lemmatization-based schema alignment step. Entity typing and hierarchical induction are then employed to infer class structures, as well as domain and range constraints. Using RDFLib and structured data processing, we transform the extracted triples into both assertional (ABox) and terminological (TBox) axioms expressed in Description Logic. Experimental evaluation on benchmark datasets (Conll04 and NYT) demonstrates the efficacy of the approach, with expert validation showing high acceptance rates (>95%) and reasoners confirming zero inconsistencies. The pipeline thus establishes a reliable, scalable foundation for automated ontology learning, advancing the field from extraction to formally verifiable knowledge base construction. Full article

Phishing emails continue to evade conventional detection systems due to their increasingly sophisticated, multi-faceted social engineering tactics. To address the limitations of single-modality or rule-based approaches, we propose SAHF-PD, a novel phishing detection framework that integrates multi-modal feature extraction with semantic-aware hierarchical fusion, based on large language models (LLMs). Our method leverages modality-specialized large models, each guided by domain-specific prompts and constrained to a standardized output schema, to extract structured feature representations from four complementary sources associated with each phishing email: email body text; open-source intelligence (OSINT) derived from the key embedded URL; screenshot of the landing page; and the corresponding HTML/JavaScript source code. This design mitigates the unstructured and stochastic nature of raw generative outputs, yielding consistent, interpretable, and machine-readable features. These features are then integrated through our Semantic-Aware Hierarchical Fusion (SAHF) mechanism, which organizes them into core, auxiliary, and weakly associated layers according to their semantic relevance to phishing intent. This layered architecture enables dynamic weighting and redundancy reduction based on semantic relevance, which in turn highlights the most discriminative signals across modalities and enhances model interpretability. We also introduce PhishMMF, a publicly released multimodal feature dataset for phishing detection, comprising 11,672 human-verified samples with meticulously extracted structured features from all four modalities. Experiments with eight diverse classifiers demonstrate that the SAHF-PD framework enables exceptional performance. For instance, XGBoost equipped with SAHF attains an AUC of 0.99927 and an F1-score of 0.98728, outperforming the same model using the original feature representation. Moreover, SAHF compresses the original 228-dimensional feature space into a compact 56-dimensional representation (a 75.4% reduction), reducing the average training time across all eight classifiers by 43.7% while maintaining comparable detection accuracy. Ablation studies confirm the unique contribution of each modality. Our work establishes a transparent, efficient, and high-performance foundation for next-generation anti-phishing systems. Full article

Background/Objectives: Fluoroscopy-guided procedures are widely used across surgical and interventional specialties but expose operators to ionizing radiation with associated stochastic and deterministic effects. The aim is to characterize occupational radiation exposure, evaluate the effectiveness of shielding strategies, assess long-term cancer risks, and identify compliance patterns. Methods: This structured narrative review summarizes evidence on operator dose, shielding effectiveness, compliance with protective practices, and long-term cancer risk. A search of PubMed, Scopus, Embase, and Web of Science (limited to January 2000–March 2024) identified 62 records; 27 full texts were reviewed, and 16 studies met the inclusion criteria. Results: Across studies, unshielded chest exposure averaged 0.08–0.11 mSv per procedure, and eye exposure averaged 0.04–0.05 mSv. Lead aprons reduced exposure by about 90% at 0.25 mm and 99% at 0.5 mm, thyroid collars reduced neck dose by 60–70%, and lead glasses reduced ocular dose 2.5–4.5-fold. Compliance with aprons and thyroid collars was high, whereas lead glasses and lower-body shielding were inconsistently used. Limited epidemiologic data suggested a higher cancer burden in exposed surgeons, and Biologic Effects of Ionizing Radiation (BEIR) VII–based modeling projected increased lifetime risks of solid cancers in chronically exposed operators. Conclusions: Protective equipment substantially reduces operator dose, but exposure variability and inconsistent shielding practices persist and justify standardized monitoring, stronger enforcement of radiation safety protocols, and longitudinal studies. Full article

Urban welfare can deteriorate over a few weeks, yet most official indicators are only updated quarterly. This mismatch in time scales leaves city administrations effectively blind to the early stages of emerging crises, especially in areas where vulnerable residents generate few administrative or digital records. We cast urban socioeconomic monitoring as a systems problem: a six-dimensional welfare state on a spatial grid, observed through sparse delayed administrative data and noisy digital traces whose reliability declines with digital exclusion. On top of this latent state, we design a four-layer cyber–physical–social (CPSS) architecture centered on a stochastic state-space model with empirically guided couplings. This is supported by a semantic sensing layer where large language models (LLMs) convert daily geo-referenced public text into noisy welfare indicators. These signals are then fused with quarterly administrative records via an extended Kalman filter (EKF). Finally, a lightweight convex post-processing layer enforces fairness, differential privacy, and minimum representation as hard constraints. A key ingredient is a state-dependent noise model in which the LLM observation variance grows exponentially with digital exclusion. Under this model, we study finite-horizon observability and obtain an exclusion threshold beyond which several welfare dimensions become effectively unobservable over 30–60 day horizons; EKF error bounds scale with the same exponent, clarifying when semantic sensing is informative and when it is not. Finally, a 100,000-agent agent-based model of a synthetic city with daily shocks suggests that, relative to a quarterly-only baseline, the LLM-augmented fusion pipeline substantially reduces detection lags and multi-dimensional cascade failures while keeping estimation error bounded and satisfying the explicit fairness and privacy constraints. Full article

This paper introduces a novel adversarial learning framework for reconstructing hidden layers in historical palimpsests. Recovering text hidden in historical palimpsests is complicated by various artifacts, such as ink diffusion, degradation of the writing substrate, and interference between overlapping layers. To address these challenges, the authors of this paper combine a synthetic data generator grounded in physical modeling with three generative architectures: a baseline VAE, an improved variant with stronger regularization, and a U-Net-based GAN that incorporates residual pathways and a mixed loss strategy. The synthetic data engine aims to emulate key degradation effects—such as ink bleeding, the irregularity of parchment fibers, and multispectral layer interactions—using stochastic approximations of underlying physical processes. The quantitative results suggest that the U-Net-based GAN architecture outperforms the VAE-based models by a notable margin, particularly in scenarios with heavy degradation or overlapping ink layers. By relying on synthetic training data, the proposed method facilitates the non-invasive recovery of lost text in culturally important documents, and does so without requiring costly or specialized imaging setups. Full article

Personality is a fundamental psychological trait that exerts a long-term influence on human behavior patterns and social interactions. Automatic personality recognition (APR) has exhibited increasing importance across various domains, including Human–Robot Interaction (HRI), personalized services, and psychological assessments. In this study, we propose a multimodal personality recognition model that classifies the Big Five personality traits by extracting features from three heterogeneous sources: audio processed using Wav2Vec2, video represented as Skeleton Landmark time series, and text encoded through Bidirectional Encoder Representations from Transformers (BERT) and Doc2Vec embeddings. Each modality is handled through an independent Self-Attention block that highlights salient temporal information, and these representations are then summarized and integrated using a late fusion approach to effectively reflect both the inter-modal complementarity and cross-modal interactions. Compared to traditional recurrent neural network (RNN)-based multimodal models and unimodal classifiers, the proposed model achieves an improvement of up to 12 percent in the F1-score. It also maintains a high prediction accuracy and robustness under limited input conditions. Furthermore, a visualization based on t-distributed Stochastic Neighbor Embedding (t-SNE) demonstrates clear distributional separation across the personality classes, enhancing the interpretability of the model and providing insights into the structural characteristics of its latent representations. To support real-time deployment, a lightweight thread-based processing architecture is implemented, ensuring computational efficiency. By leveraging deep learning-based feature extraction and the Self-Attention mechanism, we present a novel personality recognition framework that balances performance with interpretability. The proposed approach establishes a strong foundation for practical applications in HRI, counseling, education, and other interactive systems that require personalized adaptation. Full article