Detecting machine-revised text that exhibits subtle lexical differences from the original human-generated text remains a challenge.Recent detection methods, including watermarking-based, logit-based, and trainingbased models, struggle to capture the finegrained semantic differences, especially for short texts.To address this issue, we propose Length-aware Momentum Contrastive Learning (LAMCL), a novel framework for multiscale machine-revised text detection that integrates two core modules.To enhance the discriminative semantic features, the Enhance Before Detection (EBD) module first fuses the original detected text with the counterpart processed by a Large Language Model (LLM), and then measures semantic consistency to distinguish between machine-revised and human-generated text.Meanwhile, based on the Momentum Contrastive Learning (MCL) framework, the Length-aware Weighting (LW) module leverages text length and label information for hard negative sampling, mitigating the ambiguity of short text attribution and boosting the robustness of representation learning.Experimental results demonstrate that our method outperforms the existing detectors in identifying multiscale machine-revised text across diverse practical scenarios, tasks, and LLMs.The code is available at https: //github.com/hangtze/LAMCL.

Achieving reliable cooperative control in multi-agent systems is often impeded by complex environmental disturbances, such as wind fields, which simultaneously affect the entire swarm. To address this, we propose a resource-efficient cooperative control framework that enables agents to collaboratively learn and cancel these shared uncertainties. In contrast to conventional static neural networks, we introduce a bio-inspired hybrid approximator that synergizes the interpretability of fuzzy logic with the temporal processing capabilities of spiking neurons. This architecture is specifically designed to capture time-varying aerodynamic disturbances more effectively than traditional methods. To facilitate collaboration, the framework employs a distributed estimator that fuses local data across the network, allowing agents to construct a unified model of the environment. The framework is implemented using an event-triggered communication policy that provably precludes Zeno behavior and significantly reduces network load. Simulation results validate the approach, demonstrating that the proposed method reduces the steady-state consensus error by an order of magnitude compared to non-cooperative baselines and reduces communication frequency by over 80% relative to time-triggered schemes, all while ensuring rigorous stability.

This paper presents a dynamic event-triggered unified performance adaptive control method for nonparametric strict-feedback nonlinear systems. In contrast to most existing static/dynamic event-driven controllers that only guarantee uniformly ultimately bounded tracking results, here by introducing an external auxiliary variable into the dynamic threshold strategy and using the robust technique with the integral function, not only the communication overhead is reduced and the Zeno phenomenon is precluded, but also the asymptotic zero-error tracking is achieved. The control design and stability analysis become quite complicated and challenging when the performance constraint is taken into account. By constructing a series of functional transformations in conjunction with the core information technique to handle the nonparametric uncertainty, the proposed controller is able to guarantee multiple prescribed performance characteristics by appropriately adjusting the key design parameter, eliminating the need to redesign the controller and reanalyze the stability. Finally, simulation results are conducted to demonstrate the effectiveness of the theoretical discussion.

The rapid advancement of medical dialog generation (MDG) techniques has enabled medical dialog systems (MDSs) to generate high-quality responses rich in medical expertise by integrating diverse medical information. However, they still encounter several challenges, including generic response generation, lack of semantic precision, and imprecise dialog topic extraction. This study aims to design a novel model to address these challenges simultaneously. Correspondingly, we propose the TRL-HMIE model, which represents transformer reinforcement learning (RL) for heterogeneous medical information extraction. In particular, we incorporate GPT-3 from transformer-related models as the reference language model. Our enhancements focused on three key aspects. First, we developed a conversation-topic classifier to precisely categorize conversation topics, supporting the conversation-topic locator module in generating reliable conversation topics. Second, the model employs a multihead attention mechanism to capture crucial information from the dialog context, facilitating the extraction of key dialog information and enhancing the accuracy of heterogeneous information extraction. Finally, the model integrates RL and a reward fusion mechanism, which, combined with its ability to handle multisource information and long dialog contexts, generates optimized rewards for the TRL-HMIE model, encouraging the production of doctor responses with precise semantics and dialog topics. The experimental results demonstrate that the proposed method achieves a 6.07% improvement over the benchmark model on the MedDG and MedDialog datasets. The experimental results demonstrate that the proposed method achieves a 6.07% improvement over the benchmark model on the MedDG and MedDialog datasets.

Spiking neural networks (SNNs) have captivated the attention worldwide owing to their compelling advantages in low power consumption, high biological plausibility, and strong robustness. However, the intrinsic latency associated with SNNs during inference poses a significant challenge, impeding their further development and application. This latency is caused by the need for spiking neurons to collect electrical stimuli and generate spikes only when their membrane potential exceeds a firing threshold. Considering the firing threshold plays a crucial role in SNN performance, this article proposes a self-driven adaptive threshold plasticity (SATP) mechanism, wherein neurons autonomously adjust the firing thresholds based on their individual state information using unsupervised learning rules, of which the adjustment is triggered by their own firing events. SATP is based on the principle of maximizing the information contained in the output spike rate distribution of each neuron. This article derives the mathematical expression of SATP and provides extensive experimental results, demonstrating that SATP effectively reduces SNN inference latency, further reduces the computation density while improving computational accuracy, so that SATP facilitates SNN models to be with low latency, sparse computing, and high accuracy.

Person re-identification (Re-ID) is to retrieve a particular person captured by different cameras, which is of great significance for security surveillance and pedestrian behavior analysis. However, due to the large intra-class variation of a person across cameras, e.g., occlusions, illuminations, viewpoints, and poses, Re-ID is still a challenging task in the field of computer vision. In this paper, to attack the issues concerning with intra-class variation, we propose a coarse-to-fine Re-ID framework with the incorporation of auxiliary-domain classification (ADC) and second-order information bottleneck (2O-IB). In particular, as an auxiliary task, ADC is introduced to extract the coarse-grained essential features to distinguish a person from miscellaneous backgrounds, which leads to the effective coarse- and fine-grained feature representations for Re-ID. On the other hand, to cope with the redundancy, irrelevance, and noise contained in the Re-ID features caused by intra-class variations, we integrate 2O-IB into the network to compress and optimize the features, without increasing additional computation overhead during inference. Experimental results demonstrate that our proposed method significantly reduces the neural network output variance of intra-class person images and achieves the superior performance to state-of-the-art methods.