Zuyi Huang¹, Yue Wang¹, Jia Liu², Haodong Yi¹, Lejun Ai¹, Min Chen^1,3,*, Salman A. AlQahtani⁴

CMC-Computers, Materials & Continua, Vol.87, No.1, 2026, DOI:10.32604/cmc.2025.074034 - 10 February 2026

Abstract The personalized fine-tuning of large language models (LLMs) on edge devices is severely constrained by limited computation resources. Although split federated learning alleviates on-device burdens, its effectiveness diminishes in few-shot reasoning scenarios due to the low data efficiency of conventional supervised fine-tuning, which leads to excessive communication overhead. To address this, we propose Language-Empowered Split Fine-Tuning (LESFT), a framework that integrates split architectures with a contrastive-inspired fine-tuning paradigm. LESFT simultaneously learns from multiple logically equivalent but linguistically diverse reasoning chains, providing richer supervisory signals and improving data efficiency. This process-oriented training allows more effective reasoning More >

Tomás Bernal-Beltrán¹, Ronghao Pan¹, José Antonio García-Díaz¹, María del Pilar Salas-Zárate², Mario Andrés Paredes-Valverde², Rafael Valencia-García^1,*

CMC-Computers, Materials & Continua, Vol.87, No.1, 2026, DOI:10.32604/cmc.2025.073629 - 10 February 2026

Abstract The malicious dissemination of hate speech via compromised accounts, automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern. Automatically detecting such content in Spanish is challenging due to linguistic complexity and the scarcity of annotated resources. In this paper, we compare two predominant AI-based approaches for the forensic detection of malicious hate speech: (1) fine-tuning encoder-only models that have been trained in Spanish and (2) In-Context Learning techniques (Zero- and Few-Shot Learning) with large-scale language models. Our approach goes beyond binary classification, proposing a comprehensive, multidimensional evaluation that labels each… More >

Jiaxi Wang¹, Wenbo Sun², Ziyuan Zhou¹, Shihua Wu¹, Jiang Xu¹, Shan Ji^3,*

CMC-Computers, Materials & Continua, Vol.87, No.1, 2026, DOI:10.32604/cmc.2025.073237 - 10 February 2026

Abstract Lightweight nodes are crucial for blockchain scalability, but verifying the availability of complete block data puts significant strain on bandwidth and latency. Existing data availability sampling (DAS) schemes either require trusted setups or suffer from high communication overhead and low verification efficiency. This paper presents ISTIRDA, a DAS scheme that lets light clients certify availability by sampling small random codeword symbols. Built on ISTIR, an improved Reed–Solomon interactive oracle proof of proximity, ISTIRDA combines adaptive folding with dynamic code rate adjustment to preserve soundness while lowering communication. This paper formalizes opening consistency and prove security… More >

Chih-Chieh Chang^*, Khairul Izyan Bin Anuar, Yu-Hwa Liu

CMC-Computers, Materials & Continua, Vol.87, No.1, 2026, DOI:10.32604/cmc.2025.073177 - 10 February 2026

Abstract Small datasets are often challenging due to their limited sample size. This research introduces a novel solution to these problems: average linkage virtual sample generation (ALVSG). ALVSG leverages the underlying data structure to create virtual samples, which can be used to augment the original dataset. The ALVSG process consists of two steps. First, an average-linkage clustering technique is applied to the dataset to create a dendrogram. The dendrogram represents the hierarchical structure of the dataset, with each merging operation regarded as a linkage. Next, the linkages are combined into an average-based dataset, which serves as… More >

Wenfeng Zheng¹, Guangyu Xu², Siyu Lu³, Junmin Lyu⁴, Feng Bao^5,*, Lirong Yin^6,*

CMES-Computer Modeling in Engineering & Sciences, Vol.146, No.1, 2026, DOI:10.32604/cmes.2025.075741 - 29 January 2026

Abstract Graph Neural Networks (GNNs), as a deep learning framework specifically designed for graph-structured data, have achieved deep representation learning of graph data through message passing mechanisms and have become a core technology in the field of graph analysis. However, current reviews on GNN models are mainly focused on smaller domains, and there is a lack of systematic reviews on the classification and applications of GNN models. This review systematically synthesizes the three canonical branches of GNN, Graph Convolutional Network (GCN), Graph Attention Network (GAT), and Graph Sampling Aggregation Network (GraphSAGE), and analyzes their integration pathways More >

Yuerou Feng, Panpan Tong, Shuwen Fu, Xiaofan Lu, Liquan Zheng, Jielan Lai^*, Renchun Lai^*

Oncology Research, Vol.34, No.2, 2026, DOI:10.32604/or.2025.072563 - 19 January 2026

Abstract Background: The efficacy of standard 5-fluorouracil (5-FU) chemotherapy for colorectal cancer is limited by drug resistance and adverse effects, prompting research into esketamine, a potent ketamine variant with analgesic, antidepressant, and recently discovered anti-tumor properties, to determine if it can enhance 5-FU’s chemosensitivity. This study investigates whether esketamine synergizes with 5-FU to enhance therapeutic efficacy in colorectal adenocarcinoma cell models. Methods: We performed functional assays to evaluate proliferation (CCK-8), migration (wound healing), invasion (Transwell), and apoptosis (flow cytometry) in colorectal adenocarcinoma cell lines treated with 5-FU alone or in combination with esketamine. Transcriptomic profiling was… More >

Girish Hariharan¹, Vinyas¹, Gowrishankar Mandya Chennegowda¹, Nitesh Kumar¹, Shiva Kumar¹, Deepak Doreswamy², Subraya Krishna Bhat^1,*

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.073772 - 12 January 2026

Abstract This study presents a framework involving statistical modeling and machine learning to accurately predict and optimize the mechanical and damping properties of hybrid granite–epoxy (G–E) composites reinforced with cast iron (CI) filler particles. Hybrid G–E composite with added cast iron (CI) filler particles enhances stiffness, strength, and vibration damping, offering enhanced performance for vibration-sensitive engineering applications. Unlike conventional approaches, this work simultaneously employs Artificial Neural Networks (ANN) for high-accuracy property prediction and Response Surface Methodology (RSM) for in-depth analysis of factor interactions and optimization. A total of 24 experimental test data sets of varying input… More >

Nikita Golovkin^1,2, Olesya Nikulenkova³, Vsevolod Pobezhimov¹, Alexander Nesmelov¹, Sergei Chvalun¹, Fedor Sorokin³, Arthur Krupnin^1,3,*

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.073161 - 12 January 2026

Abstract This study presents and verifies a hybrid methodology for reliable determination of parameters in structural rheological models (Zener, Burgers, and Maxwell) describing the viscoelastic behavior of polyurethane specimens manufactured using extrusion-based 3D printing. Through comprehensive testing, including cyclic compression at strain rates ranging from 0.12 to 120 mm/min (0%–15% strain) and creep/relaxation experiments (10%–30% strain), the lumped parameters were independently determined using both analytical and numerical solutions of the models’ differential equations, followed by cross-verification in additional experiments. Numerical solutions for creep and relaxation problems were obtained using finite element analysis, with the three-parameter Mooney-Rivlin… More > Graphic Abstract

Tao Geng¹, Shuaibing Li^1,*, Yunyun Yun¹, Yongqiang Kang¹, Hongwei Li², Junmin Zhu²

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.071644 - 12 January 2026

Abstract In order to address the challenges posed by complex background interference, high miss-detection rates of micro-scale defects, and limited model deployment efficiency in photovoltaic (PV) module defect detection, this paper proposes an efficient detection framework based on an improved YOLOv11 architecture. First, a Re-parameterized Convolution (RepConv) module is integrated into the backbone to enhance the model’s sensitivity to fine-grained defects—such as micro-cracks and hot spots—while maintaining high inference efficiency. Second, a Multi-Scale Feature Fusion Convolutional Block Attention Mechanism (MSFF-CBAM) is designed to guide the network toward critical defect regions by jointly modeling channel-wise and spatial… More >

Jin Lin^1,*, Bin Yu², Chao Chen¹, Jiezhen Cai¹, Yifan Wu², Cunping Wang³

Energy Engineering, Vol.123, No.1, 2026, DOI:10.32604/ee.2025.069310 - 27 December 2025

Abstract With the increasing integration of renewable energy, microgrids are increasingly facing stability challenges, primarily due to the lack of inherent inertia in inverter-dominated systems, which is traditionally provided by synchronous generators. To address this critical issue, Virtual Synchronous Generator (VSG) technology has emerged as a highly promising solution by emulating the inertia and damping characteristics of conventional synchronous generators. To enhance the operational efficiency of virtual synchronous generators (VSGs), this study employs small-signal modeling analysis, root locus methods, and synchronous generator power-angle characteristic analysis to comprehensively evaluate how virtual inertia and damping coefficients affect frequency… More > Graphic Abstract