Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection

Semantic error patterns on the Boston Naming Test in normal aging, amnestic mild cognitive impairment, and mild Alzheimer's disease: Is there semantic disruption?

The increasing availability of Web APIs has amplified the complexity of mashup creation, where developers must identify compatible and functionally relevant APIs based on often ambiguous natural language descriptions. Traditional methods also fall short in capturing hierarchical semantic cues, modeling compatibility, and aligning with developer intent. Although large language models (LLMs) offer strong generalization capabilities, they remain unreliable in mashup recommendation due to hallucinated outputs, limited controllability, and token-length constraints when dealing with large-scale API repositories. To overcome these limitations, we introduce <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LIMR</i>, an intent-aware mashup recommendation framework that combines LLM-augmented semantic reasoning with structured, multi-scale neural modeling. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LIMR</i> first prompts a LLM to extract high-level intent from user requirements, which serves as a global semantic signal. This intent is fused with low-level, multi-scale features extracted by a convolutional encoder, which are designed to capture fine-grained lexical/phrasal patterns at different granularities and provide precise semantic grounding for API matching. These heterogeneous representations are further contextually refined through a Transformer-based interaction module. To handle nonlinear semantic dependencies and compositional complexity, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LIMR</i> integrates a Kolmogorov-Arnold Network (KAN) with learnable activation functions, enhancing the model's capacity to capture intricate feature interactions. The entire framework is optimized via LLM, incorporating auxiliary objectives such as mashup category prediction and API quality estimation to guide generalization and reduce overfitting. Comprehensive experiments on the ProgrammableWeb and APIBench datasets show that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LIMR</i> significantly outperforms state-of-the-art baselines, which the ranking-oriented metrics, including NDCG and mAP, achieves improvements of 17.1%–34.2% over the strongest competitors. These results confirm the effectiveness of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LIMR</i>'s hybrid design in delivering precise, robust, and intent-aware mashup API recommendations, especially in scenarios where LLMs alone fail to meet accuracy and scalability demands.

Object proposal algorithms have shown great promise as a first step for object recognition and detection. Good object proposal generation algorithms require high object detection recall rate as well as low computational cost, because generating object proposals is usually utilized as a preprocessing step. The problem of how to accelerate the object proposal generation and evaluation process without decreasing recall is thus of great interest. In this paper, we propose a new object proposal generation method using two-stage cascade support vector machines (SVMs), where in the first stage linear filters are learned for predefined quantized scales/aspect-ratios independently, and in the second stage a global linear classifier is learned across all the quantized scales/aspect-ratios for calibration, so that all the windows from the first stage can be compared properly. The windows with highest scores from the second stage are kept as inputs to our new efficient proposal calibration algorithm to improve their localization quality significantly, resulting in our final object proposals. We explain our scale/aspect-ratio quantization scheme, and investigate the effects of combinations of l1 and l2 regularizers in cascade SVMs with/without ranking constraints in learning. Comprehensive experiments on VOC2007 dataset are conducted, and our method is comparable with the current state-of-the-art methods with much better computational efficiency.

Multi-attribute network refers to network data with multiple attribute views and relational view. Although semi-supervised collective classification has been investigated extensively, little attention is received for such kind of network data. In this paper, we aim to study and solve the semi-supervised learning problem for multi-attribute networks. There are two important challenges: (1) how to extract effective information from the rich multi-attribute and relational information; (2) how to make use of unlabeled data in the network. We propose a new generative model with network regularization, called MARL, which addresses the two challenges. In the approach, a generative model based on the probabilistic latent semantic analysis method is developed to leverage attribute information, and a network regularizer is incorporated to smooth label probability with relational information and unlabeled data. Comprehensive experiments on various data sets have been conducted to demonstrate the effectiveness of the proposed MARL, and the results reveal that our approach outperforms existing collective classification methods and multi-view classification methods in terms of accuracy.

Handling emotions in human‐computer dialogues has emerged as a challenging task which requires artificial intelligence systems to generate emotional responses by jointly perceiving the emotion involved in the input posts and incorporating it into the generation of semantically coherent and emotionally reasonable responses. However, most previous works generate emotional responses solely from input posts, which do not take full advantage of the training corpus and suffer from generating generic responses. In this study, we introduce a h ierarchical s emantic‐ e motional m emory module for e motional c onversation generation (called HSEMEC), which can learn abstract semantic conversation patterns and emotional information from the large training corpus. The learnt semantic and emotional knowledge helps to enrich the post representation and assist the emotional conversation generation. Comprehensive experiments on a large real‐world conversation corpus show that HSEMEC can outperform the strong baselines on both automatic and manual evaluation. For reproducibility, we release the code and data publicly at: https://github.com/siat‐nlp/HSEMEC‐code‐data .

Oriented object detection in remote sensing images remains a challenging task due to arbitrary target rotations, extreme scale variations, and complex backgrounds. However, current rotated detectors still face several limitations: insufficient orientation-sensitive feature representation, feature misalignment for rotated proposals, and unstable optimization of rotation parameters. To address these issues, this paper proposes an enhanced Rotation-Sensitive Feature Pyramid Network (RSFPN) framework. Building upon the effective Oriented R-CNN paradigm, we introduce three novel core components: (1) a Dynamic Adaptive Feature Pyramid Network (DAFPN) that enables bidirectional multi-scale feature fusion through semantic-guided upsampling and structure-enhanced downsampling paths; (2) an Angle-Aware Collaborative Attention (AACA) module that incorporates orientation priors to guide feature refinement; (3) a Geometrically Consistent Multi-Task Loss (GC-MTL) that unifies the regression of rotation parameters with periodic smoothing and adaptive weight mechanisms. Comprehensive experiments on the DOTA-v1.0 and HRSC2016 benchmarks show that our RSFPN achieves superior performance. It attains a state-of-the-art mAP of 77.42% on DOTA-v1.0 and 91.85% on HRSC2016, while maintaining efficient inference at 14.5 FPS, demonstrating a favorable accuracy-efficiency trade-off. Visual analysis confirms that our method produces concentrated, rotation-aware feature responses and effectively suppresses background interference. The proposed approach provides a robust solution for detecting multi-oriented objects in high-resolution remote sensing imagery, with significant practical value for urban planning, environmental monitoring, and security applications.

NTLFlowLyzer: Towards generating an intrusion detection dataset and intruders behavior profiling through network and transport layers traffic analysis and pattern extraction

Internet and mobile devices have made IT ubiquitous and rapid technology evolution has led to diminishing cost of ownership for IT products. Consequently, entrepreneurs who create IT products and services are viewed with broad interest by investors, researchers, governments, and incubators. This research proposes that IT entrepreneurs need to be distinguished from those in other sectors and studied as a unique typology in any entrepreneurship research and investigates whether IT entrepreneurs are more likely to reattempt entrepreneurship due to the influence of five external factors viz., Funding availability, Opportunity cost, Value of knowledge acquired in failure, and Technology evolution and IT and non-IT entrepreneurs view failure differently. The theoretical rationale for bifurcating entrepreneurs as IT and Non-IT for analysis emerged from a) the recent observation that the top five companies in the US by market capitalization are all IT ventures whereas in 2001 when only one constituted the list, b) rapid growth in the application of ML and AI in all sectors, and c) the observed differences between IT and Non-IT entrepreneurs with respect to the five external factors. We theorize that variations in the external factors may differently influence IT and Non-IT entrepreneurs’ decision to reattempt and/or sentiments about failure. The objective of this thesis is to recommend new policies and modifications to existing ones if IT entrepreneurs are observed to have distinct advantages/disadvantages compared to Non-IT ones.Our mixed method approach included an online quantitative survey that measured the influence of the five factors on a scale and qualitative semi-structured interviews to comprehend the sentiments that led to the responses in the survey. To understand the degree of influence of the five external factors quantitatively, hypothesis testing and regression analysis were adopted whereas a thematic analysis was performed on qualitative data.The evidence from our data indicated that non-IT entrepreneurs viewed venture failures more negatively than did IT ones and surprisingly that the sentiments about Funding availability were identical between IT and non-IT entrepreneurs. However the Opportunity cost, the Value of knowledge acquired, the Stigma of failure, and the Technology evolution were higher in their respective measures for IT entrepreneurs than for non-IT ones. Finally it was shown that IT entrepreneurs were more likely to reattempt entrepreneurship after failure than do Non-IT ones.Based on the findings of this study, we recommend that new policies relating to leasing of capital equipment, job opportunities upon failure, public announcement campaigns to mitigate the Stigma of failure, the creation of specific targeted loan/funding mechanisms, and special training and education be formulated to mitigate the disadvantages that are unique to non-IT entrepreneurs.The findings of this study underline how the typology based research can expose certain characteristics of entrepreneurship that may not be evident otherwise. This study may be unique in juxtaposing IT and Non-IT entrepreneurs through the lens of five external factors. Entrepreneurs have been documented to be heterogeneous and this research lays the foundation for further focused research on IT entrepreneurs especially due to the role played by IT in people’s lives.

The rapid evolution of mobile Internet and artificial intelligence technology has pushed Fragmented Learning to the main learning space for college students and lifelong learners. While Fragmented Learning brings convenience, it also faces challenges such as insufficient learning motivation, lack of social learning, and faulty knowledge system, etc. The emergence of generative artificial intelligence technology opens the door to new possibilities for solving these problems. This paper first analyzes the current situation and challenges of Fragmented Learning for college students, then explores the potential of generative AI technology in Fragmented Learning, and then puts forward three optimization strategies: launching a learning motivation and feedback mechanism, constructing a community and collaborative learning platform, and implementing an intelligent learning navigation system, with a view to providing references to improve the efficiency and overall effectiveness of Fragmented Learning.

Compared to single-modality magnetic resonance (MR) image super-resolution (SR) methods, multi-modality MR image methods can utilize high-resolution reference modality (e.g., T1 modality) to provide valuable complementary information for low-resolution target modality (e.g., T2 modality) in SR reconstruction, which can further improve the quality of the SR images. Although they have achieved impressive results, these methods still suffer from the following drawbacks: (1) They can only handle fixed integer upsampling factors, such as 2X, 3X, and 4X, and require training and storing corresponding models for each upsampling factor, which is infeasible in clinical practice; (2) They only perform feature extraction and reconstruction in the image domain. However, the aliasing artifacts produced in the image domain are structural and non-local. Therefore, using only the image domain cannot effectively reconstruct high-quality aliasing-free SR images. To address these issues, we develop a brand-new Dual-Domain Implicit Network (DuDoINet) for multi-modality MR image arbitrary-scale SR. Specifically, we propose a dual-domain learning scheme for multi-modality MR image SR, which allows the network to sufficiently exploit the frequency and image domain information in MR images. In addition, we design implicit attention to achieve arbitrary-scale upsampling of MR images, which utilizes a continuously differentiable function that generates pixel values from pixel coordinates. Furthermore, we designed a deformable cross-modality attention mechanism that can adaptively transfer high-frequency details from the T1 to the T2 modality, better integrating valuable complementary information from the T1 modality. Extensive and comprehensive experiments on healthy subjects and patient datasets demonstrate that our DuDoINet outperforms SOTA methods, demonstrating its great potential for clinical practice.

The nearest neighbor search is an essential operation for many computer vision, data mining, and machine learning problems. Since it is so widely used, the nearest neighbor search should be as fast as possible. This paper explores lower bound-based approaches to speed up the exact nearest neighbor search in high dimensional Euclidean space. We compute the lower bound of Euclidean Distance by using the block vectors and Cauchy–Schwartz inequality. The proposed lower bound is calculated efficiently and is close to the real Euclidean Distance. Besides, the preprocessing step of the proposal has linear time complexity. Given a query, during the procedure of identifying the nearest neighbor, our method can eliminate many expensive actual distance computations using the lower bound to approximate Euclidean Distance. In addition, we develop a multilevel lower bound strategy, which calculates the lower bound step by step and utilizes the multistep filtering mechanism to improve the searching process further. Theoretical analysis is provided to show that the proposals can guarantee to obtain the same result as the brute-force search. Comprehensive experiments on 16 public data sets collected from various domains demonstrate that our approach performs well in finding the exact nearest neighbor compared to related competitors. The experimental results also illustrate that the multilevel lower bound strategy is effective.

Unsupervised 4D-flow MRI reconstruction based on partially-independent generative modeling and complex-difference sparsity constraint.

Visualization of high-dimensional data such as text documents is widely applicable. The traditional means is to find an appropriate embedding of the high-dimensional representation in a low-dimensional visualizable space. As topic modeling is a useful form of dimensionality reduction that preserves the semantics in documents, recent approaches aim for a visualization that is consistent with both the original word space, as well as the semantic topic space. In this paper, we address the semantic visualization problem. Given a corpus of documents, the objective is to simultaneously learn the topic distributions as well as the visualization coordinates of documents. We propose to develop a semantic visualization model that approximates L2-normalized data directly. The key is to associate each document with three representations: a coordinate in the visualization space, a multinomial distribution in the topic space, and a directional vector in a high-dimensional unit hypersphere in the word space. We join these representations in a unified generative model, and describe its parameter estimation through variational inference. Comprehensive experiments on real-life text datasets show that the proposed method outperforms the existing baselines on objective evaluation metrics for visualization quality and topic interpretability.

Summary 3D reconstruction of porous media plays a crucial role in materials science and petroleum engineering, particularly for pore structure characterization and physical-mechanical property prediction. Although deep learning–based generative models have emerged as promising tools for 3D porous media reconstruction, challenges remain, including inadequate feature representation, training instability, and limited generation diversity. To address these issues, we propose the Kolmogorov-Arnold (KA) generative adversarial network (GAN) (KA-GAN) for 3D reconstruction of porous media, where an improved KA convolutional layer is incorporated in the generator. Moreover, KA-GAN employs grouped convolution mechanisms and phase-controlled activation functions to enhance spatial structure preservation and generation diversity while mitigating geometric distortions. The discriminator integrates gradient penalty (GP) regularization to improve training stability. Comprehensive experiments were conducted on diverse porous media data sets, including heterogeneous sandstone and structurally complex carbonate rocks. Qualitative results show accurate visual resemblance to ground truth (GT), while quantitative evaluations demonstrate improvements in porosity, throat geometry, connectivity metrics, and absolute permeability, confirming that KA-GAN outperforms existing state-of-the-art methods. The source code for this paper is publicly available at https://github.com/HoneyOrangeSummer/ka-gan/.

Received waveforms contain rich information for both range information and environment semantics. However, its full potential is hard to exploit under multipath and non-line-of-sight conditions. This paper proposes a deep generative model (DGM) for simultaneous range error mitigation and environment identification. In particular, we present a Bayesian model for the generative process of the received waveform composed by latent variables for both range-related features and environment semantics. The simultaneous range error mitigation and environment identification is interpreted as an inference problem based on the DGM, and implemented in a unique end-to-end learning scheme. Comprehensive experiments on a general Ultra-wideband dataset demonstrate the superior performance on range error mitigation, scalability to different environments, and novel capability on simultaneous environment identification.