The widespread proliferation of online content has intensified concerns about clickbait, deceptive or exaggerated headlines designed to attract attention. While Large Language Models (LLMs) offer a promising avenue for addressing this issue, their effectiveness is often hindered by Sycophancy, a tendency to produce reasoning that matches users' beliefs over truthful ones, which deviates from instruction-following principles. Rather than treating sycophancy as a flaw to be eliminated, this work proposes a novel approach that initially harnesses this behavior to generate contrastive reasoning from opposing perspectives. Specifically, we design a Self-renewal Opposing-stance Reasoning Generation (SORG) framework that prompts LLMs to produce high-quality ''agree'' and ''disagree'' reasoning pairs for a given news title without requiring ground-truth labels. To utilize the generated reasoning, we develop a local Opposing Reasoning-based Clickbait Detection (ORCD) model that integrates three BERT encoders to represent the title and its associated reasoning. The model leverages contrastive learning, guided by soft labels derived from LLM-generated credibility scores, to enhance detection robustness. Experimental evaluations on three benchmark datasets demonstrate that our method consistently outperforms LLM prompting, fine-tuned smaller language models, and state-of-the-art clickbait detection baselines. Our code is available in https://github.com/126541/ORCD.

The questionable responses caused by knowledge hallucination may lead to LLMs' unstable ability in decision-making. However, it has never been investigated whether the LLMs' hallucination is possibly usable for generating negative reasoning to assist fake news detection. In this paper, we propose a novel supervised self-reinforced reasoning rectification approach - SR^3 that not only yields common reasonable reasoning for news but also forces LLMs to generate the wrong understandings of news via LLMs reflection for semantic consistency learning. Upon that, we construct a negative reasoning-based news learning model called - NRFE, which leverages positive or negative news-reasoning pairs for learning the semantic consistency between them. To avoid the impact of label-implicated reasoning, we deploy a student model - NRFE-D that only takes news content as input to inspect the performance of our method by distilling the knowledge from NRFE. The experimental results verified on three popular fake news datasets demonstrate the superiority of our method compared with three kinds of baselines including prompting-based LLMs, fine-tuning-based PLMs, and other representative fake news detection methods.

In this paper, we introduce GoodDrag, a novel approach to improve the stability and image quality of drag editing. Unlike existing methods that struggle with accumulated perturbations and often result in distortions, GoodDrag introduces an AlDD framework that alternates between drag and denoising operations within the diffusion process, effectively improving the fidelity of the result. We also propose an information-preserving motion supervision operation that maintains the original features of the starting point for precise manipulation and artifact reduction. In addition, we contribute to the benchmarking of drag editing by introducing a new dataset, Drag100, and developing dedicated quality assessment metrics, Dragging Accuracy Index and Gemini Score, utilizing Large Multimodal Models. Extensive experiments demonstrate that the proposed GoodDrag compares favorably against the state-of-the-art approaches both qualitatively and quantitatively. The source code and data are available at https://gooddrag.github.io.

The Industrial Internet of Things (IIoT) is a promising scenario for Industry 4.0, where the existence of rich scatterers can affect the quality of communication in the factory. In this paper, we investigate the multiple base stations (BSs) deployment problem based on the ray tracing (RT) method in IIoT scenarios considering coverage. We simplify the construction of IIoT scenarios by considering the geometric and channel characteristics to improve computational efficiency in RT simulation. Then, the BS deployment problem is formulated subject to the path loss and energy efficiency. The particle swarm optimization (PSO) algorithm with the surrogate model from RT simulation is proposed to solve the formulated problem. Moreover, the surrogate model is used to replace the all-time RT simulation in the PSO algorithm. The simulation results demonstrate that the proposed method effectively addresses BS deployment challenges in IIoT scenarios.

ABSTRACT Mobile devices are affected by limited energy and channel resources in the dynamic scenarios with high mobility and complexity, which will trigger the risks such as task failure or low offloading efficiency. This article proposes a multiuser and multiserver MEC network framework based on simultaneous wireless information and power transfer (a.k.a., SWIPT). We first consider multiple mobile devices with fixed task information in which the tasks can be either processed in‐local or offloaded to the MEC server for processing via uplink transmission. Our method also embraces a hierarchical demand‐weighted index (HDWI) and priority channel transmission scheduling rule, which can evaluate the status of device services and effectively conduct the hierarchical offloading of tasks. In this case, our model not only ensures the continuity of the service provided by mobile devices but also evaluates the relationship between energy consumption and device delay during the offloading process. Finally, we propose an efficient mobile device cost hierarchical offloading algorithm (MCHOA) to deal with the issues produced by the constructed multiobjective optimization mathematical model. MCHOA complies with the principle of HDWI and is combined with a multiobjective evolutionary algorithm based on decomposition to solve various mathematical tasks including obtaining the Pareto optimal curve regarding the average time consumption and the average energy consumption of devices. The experimental results show that MCHOA can simultaneously reduce time consumption and energy consumption costs by at least 13.3% and 37.5%, respectively. Our experiments also validate the superiority of the proposed algorithm and the application prospect of the model.

Typical legged locomotion controllers are designed or trained offline. This is in contrast to many animals, which are able to locomote at birth, and rapidly improve their locomotion skills with few real-world interactions. Such motor control is possible through oscillatory neural networks located in the spinal cord of vertebrates, known as Central Pattern Generators (CPGs). Models of the CPG have been widely used to generate locomotion skills in robotics, but can require extensive hand-tuning or offline optimization of inter-connected parameters with genetic algorithms. In this paper, we present a framework for the online optimization of the CPG parameters through Bayesian Optimization. We show that our framework can rapidly optimize and adapt to varying velocity commands and changes in the terrain, for example to varying coefficients of friction, terrain slope angles, and added mass payloads placed on the robot. We study the effects of sensory feedback on the CPG, and find that both force feedback in the phase equations, as well as posture control (Virtual Model Control) are both beneficial for robot stability and energy efficiency. In hardware experiments on the Unitree Go1, we show rapid optimization (in under 3 minutes) and adaptation of energy-efficient gaits to varying target velocities in a variety of scenarios: varying coefficients of friction, added payloads up to 15 kg, and variable slopes up to 10 degrees.