Large language model (LLM) generated texts now rival human quality, creating four text categories: purely machine-generated, machine-rewritten, machine-polished, and human-written content. Traditional detection methods face significant challenges in human-machine hybrid scenarios where LLMs perform rewriting or polishing, as existing approaches focus on single-level features and fail to capture subtle, multi-layered machine traces. To address this, we propose the Multi-level Style Preference Optimization (MSPO) framework, capturing machine style features at multiple granularities: sequence-level (overall consistency), phrase-level (distinctive n-gram patterns), and lexical-level (word selection distributions). We further incorporate four text complexity indicators (Type-Token Ratio, Average Sentence Length, Average Word Length, and Punctuation Ratio) to dynamically adjust optimization parameters based on human-machine text complexity differences, enhancing adaptability across diverse text types. Additionally, we construct a comprehensive detection dataset spanning three representative domains (scientific writing, news articles, and creative writing) across four text types (human-written, purely machine-generated, machine-rewritten, and machine-polished), generated using state-of-the-art LLMs for robust evaluation. Experimental results demonstrate that MSPO significantly outperforms existing methods across all text types. On the challenging rewritten texts, MSPO achieves up to 82.14% AUROC, representing an improvement of 11.15 percentage points over the strongest baseline ImBD, while maintaining robust cross-domain generalizability across scientific, news, and creative writing domains.

Current text style transfer task mainly focuses on short texts, while the field has not been fully developed for long texts. Considering the richer semantics and more complex sentence structures in long text sequences, existing methods that employ traditional style-content disentanglement ways and learn the target style to generate target sequences face two key issues: 1) During disentanglement, they usually directly separate style words or fragments, such coarse-grained disentanglement risks losing original semantics and hinder the model's content preservation. 2) During target style learning, they often focus on the transfer of certain style attributes or aspects, which makes it difficult to grasp the holistic style of target objects. To this end, we propose Cognitive enhancement Chain-of-Thought (CeCoT) towards enhancing style learning and content preservation for long style transfer. CeCoT first constructs progressive CoT to facilitate LLMs to gradually rewrite source content and separate source styles, thereby enhancing the retention of original content. Then, we propose cognitive CoT, which comprehensively considers hierarchical cognitive content (i.e., shallower-deeper-normal level) and cognitive behavior (i.e., prompt order of CoT) to learn the overall target style. To enhance the robustness of our model, we also propose two constraint losses in a dual validation way towards content preservation enhancing and style consistency learning. Extensive experiments on two competitive datasets demonstrate the superiority of our CeCoT.

Applying Electrical Impedance Tomography (EIT) at the microscopic scale is a promising approach for label-free cellular monitoring in the Internet of Medical Things (IoMT). However, practical deployment faces challenges such as ill-posed inverse problems, low Signal-to-Noise Ratios (SNRs), and the lack of labeled training data. To address these issues, this paper proposes SwinLoAttn-DIP, an unsupervised reconstruction framework designed for a custom miniature sensing system. The core network, SwinLoAttnNet, combines Swin Transformer blocks with a hybrid attention mechanism. Unlike standard convolutional methods that may blur fine details, this architecture captures global dependencies to reconstruct complex microstructures without requiring pre-training. We validated the proposed method using a self-developed 15-mm sensor node. Through systematic comparisons with recent architectures, including pretrained Transformers and Multilayer Perceptron (MLP)-based models, the results demonstrate that our framework achieves superior boundary fidelity and reduced artifacts across simulations,ex vivotissues, and public datasets. This work establishes a robust and data-efficient paradigm for high-precision microscopic imaging, facilitating the implementation of reliable remote biosensing in data-scarce IoMT environments.

This work proposes the quantum-state-based mapping (QSM) for machine learning. QSM uses wave functions that describe microscopic particle systems as mappings. By QSM, original inputs or features extracted by neural networks are processed as quantum states to train wave function parameters. QSM has a low computational cost, almost no additional parameters, and is easy to integrate with other modules. We demonstrate the simplest form of the wave function as a mapping, that is, when a one-dimensional particle is in an infinitely deep potential well, in combination with advanced attention modules. Experiments show that QSM significantly improves the feature recalibration ability of attention module in transfer learning tasks. Then, we tried to analyze the effectiveness of QSM. This work indicates that QSM has an important application value in interdisciplinary machine learning.

The channel attention mechanism, which adaptively recalibrates each channel's weight, can enhance the performance of deep neural networks. Most channel attention modules use simple pooling operations to aggregate spatial information. The drawback is the incapability to express complex global spatial information effectively. In this paper, we propose a Quantum-based Channel Attention (QCA), which only involves a handful of parameters but brings apparent performance gain. Using quantum mechanics analogy, we utilize wave functions describing microscopic particles to generate complex global spatial information. In addition, the QCA module has no convolutional layer, making it suitable for integration with various network architectures, including transformer and multilayer perceptron (MLP). We evaluate QCA through experiments on ImageNet-1K, and we also demonstrated the effect of QCA in combination with pre-training networks on small downstream transfer learning tasks.

This work proposes a quantum-state-based feature engineering (QSFE) method for machine learning. QSFE uses wave functions that describe microscopic particle systems as mappings. By QSFE, original inputs or features extracted by neural networks are processed as quantum states to train wave function parameters. The experiments demonstrate that QSFE can improve the feature recalibration ability in deep neural networks. QSFE has a low computational cost, almost no additional parameters, and is easy to integrate with other modules. This work unfolds two effectiveness of QSFE: firstly, QSFE can enhance the expression ability of the model and make full use of the features extracted from the previous network; secondly, QSFE can extract complex spatial and temporal interactions, following the self-organization theory. The validations on various machine learning tasks, including a classical self-organization model, indicate that QSFE is valuable in interdisciplinary machine learning applications.

Abstract For the lack of labels in infrared and visible image fusion network, an infrared and visible image fusion model based on multi‐channel unsupervised convolutional neural network (CNN) is proposed in this paper, in order to extract more detailed information through multi‐channel inputs. In contrast to conventional unsupervised fusion network, the proposed network contains three channels for extracting infrared features, visible features and common features of infrared and visible images, respectively. The square loss function is used to train the network. Pairs of infrared and visible images are input to DenseNet to extract as more useful features as possible. A fusion module is designed to fuse the extracted features for testing. Experimental results show that the proposed method can preserve both the clear target of infrared and detailed information of visible images simultaneously. Experiments also demonstrate the superiority of the proposed method over the state‐of‐the‐art methods in objective metrics.