To prevent misinformation and social issues arising from trustworthy-looking content generated by LLMs, it is crucial to develop efficient and reliable methods for identifying the source of texts. Previous approaches have demonstrated exceptional performance in detecting texts fully generated by LLMs. However, these methods struggle when confronting more advanced LLM output or text with adversarial multi task machine-revision, especially in the black-box setting, where the generating model is unknown. To address this challenge, grounded in the hypothesis that human writing possesses consistent, distinctive stylistic patterns, we propose Human Language Preference Detection (HLPD). HLPD employs a reward‐based alignment process, Human Language Preference Optimization (HLPO), to shift the scoring model’s token distribution toward human‐like writing, making the model more sensitive to human writing, therefore enhancing the identification of machine-revised text. We test HLPD in an adversarial multi‑task evaluation framework that leverages a five‑dimensional prompt generator and multiple advanced LLMs to create diverse revision scenarios. When detecting texts revised by GPT-series models, HLPD achieves a 15.11% relative improvement in AUROC over ImBD, surpassing Fast-DetectGPT by 45.56%. When evaluated in texts generated by advanced LLMs, HLPD achieves the highest average AUROC, exceeding ImBD by 5.53% and Fast-DetectGPT by 34.14%.

Symbiotic radio (SR) is a promising technology designed to meet the increasing demand for spectrum-efficient communication. However, the small size of backscatter devices (BDs), which are typically equipped with a single antenna, poses challenges in achieving sufficient diversity or spatial multiplexing, thereby hindering the advancement of SR. To address this issue, we introduce fluid antennas (FAs) into SR, enabling devices to dynamically adjust their positions to create a favorable wireless environment and overcome spatial constraints, thereby achieving significant diversity gains. In this paper, we investigate the uplink performance of FA-assisted SR (FA-SR). First, we propose a novel collaborative cancellation channel estimation scheme based on least squares regression (CC-LSR) for scenarios with imperfect channel state information (CSI). We then derive tight lower bound expressions for the channel capacity under both perfect and imperfect CSI cases and formulate the corresponding weighted sum channel capacity (WSCC) optimization problems. The positions of the FAs and the combining vectors are jointly optimized to maximize the lower bound of the WSCC. To solve these problems, we develop joint optimization methods for both perfect and imperfect CSI scenarios using chaotic sequence-based adaptive particle swarm optimization (CSA-PSO). Nevertheless, the high computational complexity of joint optimization poses challenges for practical implementation. To this end, we propose a progressive optimization framework (POF) tailored to both perfect and imperfect CSI scenarios, in which the original problem is divided into three subproblems that are progressively solved to find locally optimal solutions. Numerical results demonstrate that POF significantly reduces computational complexity with minimal performance loss compared to joint optimization methods, particularly under imperfect CSI conditions.

With the acceleration of urbanization, climate change, and population growth, the global electricity demand shows a significant upward trend. Accurate short-term load forecasting (STLF) plays a vital role in optimizing the operation of the electrical distribution system. Although recent deep learning-based short-term load forecasting models have shown significant advantages, achieving accurate load forecasting remains a daunting challenge as power load demand is affected by many external environmental factors and the inherent defects of traditional forecasting models such as recurrent neural networks (RNNs) and support vector machine (SVM). In order to tackle this challenge, this paper proposes a transformer-based short-term load forecasting model. It takes loads in distributed feeders as forecasting objects and makes full use of the self-attention mechanism to capture the long-term dependency and complex nonlinear characteristics of load data. Experimental results show that the model performs well in processing complex time-series data and load fluctuations in different seasons. It has strong generalization ability and provides a new solution for forecasting distribution feeder load.

Recent weakly supervised semantic segmentation (WSSS) methods strive to incorporate contextual knowledge to improve the completeness of class activation maps (CAM). In this work, we argue that the knowledge bias between instances and contexts affects the capability of the prototype to sufficiently understand instance semantics. Inspired by prototype learning theory, we propose leveraging prototype awareness to capture diverse and fine-grained feature attributes of instances. The hypothesis is that contextual prototypes might erroneously activate similar and frequently co-occurring object categories due to this knowledge bias. Therefore, we propose to enhance the prototype representation ability by mitigating the bias to better capture spatial coverage in semantic object regions. With this goal, we present a Context Prototype-Aware Learning (CPAL) strategy, which leverages semantic context to enrich instance comprehension. The core of this method is to accurately capture intra-class variations in object features through context-aware prototypes, facilitating the adaptation to the semantic attributes of various instances. We design feature distribution alignment to optimize prototype awareness, aligning instance feature distributions with dense features. In addition, a unified training framework is proposed to combine label-guided classification supervision and prototypes-guided self-supervision. Experimental results on PASCAL VOC 2012 and MS COCO 2014 show that CPAL significantly improves off-the-shelf methods and achieves state-of-the-art performance. The project is available at https://github.com/Barrett-python/CPAL.

The safety of autonomous vehicles (AV) has been a long-standing top concern, stemming from the absence of rare and safety-critical scenarios in the long-tail naturalistic driving distribution. To tackle this challenge, a surge of research in scenario-based autonomous driving has emerged, with a focus on generating high-risk driving scenarios and applying them to conduct safety-critical testing of AV models. However, limited work has been explored on the reuse of these extensive scenarios to iteratively improve AV models. Moreover, it remains intractable and challenging to filter through gigantic scenario libraries collected from other AV models with distinct behaviors, attempting to extract transferable information for current AV improvement. Therefore, we develop a continual driving policy optimization framework featuring Closed-Loop Individualized Curricula (CLIC), which we factorize into a set of standardized sub-modules for flexible implementation choices: AV Evaluation, Scenario Selection, and AV Training. CLIC frames AV Evaluation as a collision prediction task, where it estimates the chance of AV failures in these scenarios at each iteration. Subsequently, by re-sampling from historical scenarios based on these failure probabilities, CLIC tailors individualized curricula for downstream training, aligning them with the evaluated capability of AV. Accordingly, CLIC not only maximizes the utilization of the vast pre-collected scenario library for closed-loop driving policy optimization but also facilitates AV improvement by individualizing its training with more challenging cases out of those poorly organized scenarios. Experimental results clearly indicate that CLIC surpasses other curriculum-based training strategies, showing substantial improvement in managing risky scenarios, while still maintaining proficiency in handling simpler cases.