Beike Yu, Dafang Wang^*

CMES-Computer Modeling in Engineering & Sciences, Vol.146, No.1, 2026, DOI:10.32604/cmes.2026.076439 - 29 January 2026

Abstract Scalable simulation leveraging real-world data plays an essential role in advancing autonomous driving, owing to its efficiency and applicability in both training and evaluating algorithms. Consequently, there has been increasing attention on generating highly realistic and consistent driving videos, particularly those involving viewpoint changes guided by the control commands or trajectories of ego vehicles. However, current reconstruction approaches, such as Neural Radiance Fields and 3D Gaussian Splatting, frequently suffer from limited generalization and depend on substantial input data. Meanwhile, 2D generative models, though capable of producing unknown scenes, still have room for improvement in terms… More >

Xianrui Lyu, Xiaodan Ren^*

CMES-Computer Modeling in Engineering & Sciences, Vol.146, No.1, 2026, DOI:10.32604/cmes.2025.074388 - 29 January 2026

Abstract Inverse design of advanced materials represents a pivotal challenge in materials science. Leveraging the latent space of Variational Autoencoders (VAEs) for material optimization has emerged as a significant advancement in the field of material inverse design. However, VAEs are inherently prone to generating blurred images, posing challenges for precise inverse design and microstructure manufacturing. While increasing the dimensionality of the VAE latent space can mitigate reconstruction blurriness to some extent, it simultaneously imposes a substantial burden on target optimization due to an excessively high search space. To address these limitations, this study adopts a Variational… More >

Yan Kong¹, Xinpeng Guo², Chih-Hsien Hsia^3,4,*

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.071269 - 12 January 2026

Abstract With the development of technology, diffusion model-based solvers have shown significant promise in solving Combinatorial Optimization (CO) problems, particularly in tackling Non-deterministic Polynomial-time hard (NP-hard) problems such as the Traveling Salesman Problem (TSP). However, existing diffusion model-based solvers typically employ a fixed, uniform noise schedule (e.g., linear or cosine annealing) across all training instances, failing to fully account for the unique characteristics of each problem instance. To address this challenge, we present Graph-Guided Diffusion Solvers (GGDS), an enhanced method for improving graph-based diffusion models. GGDS leverages Graph Neural Networks (GNNs) to capture graph structural information… More >

Pengwei Guo¹, Xiao Tan^2,3,*, Yiming Liu⁴

Structural Durability & Health Monitoring, Vol.20, No.1, 2026, DOI:10.32604/sdhm.2025.071317 - 08 January 2026

Abstract Crack detection accuracy in computer vision is often constrained by limited annotated datasets. Although Generative Adversarial Networks (GANs) have been applied for data augmentation, they frequently introduce blurs and artifacts. To address this challenge, this study leverages Denoising Diffusion Probabilistic Models (DDPMs) to generate high-quality synthetic crack images, enriching the training set with diverse and structurally consistent samples that enhance the crack segmentation. The proposed framework involves a two-stage pipeline: first, DDPMs are used to synthesize high-fidelity crack images that capture fine structural details. Second, these generated samples are combined with real data to train… More >

Chuang-Chieh Lin¹, Yung-Shen Huang², Shih-Yeh Chen^2,*

CMC-Computers, Materials & Continua, Vol.86, No.2, pp. 1-19, 2026, DOI:10.32604/cmc.2025.072890 - 09 December 2025

Abstract With the rapid development of generative artificial intelligence (GenAI), the task of story visualization, which transforms natural language narratives into coherent and consistent image sequences, has attracted growing research attention. However, existing methods still face limitations in balancing multi-frame character consistency and generation efficiency, which restricts their feasibility for large-scale practical applications. To address this issue, this study proposes a modular cloud-based distributed system built on Stable Diffusion. By separating the character generation and story generation processes, and integrating multi-feature control techniques, a caching mechanism, and an asynchronous task queue architecture, the system enhances generation… More >

Qiang Zhang¹, Shuo Feng¹, Shanxiong Chen², Teng Wan¹, Ying Qi^1,*

CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-22, 2026, DOI:10.32604/cmc.2025.068247 - 10 November 2025

Abstract Human motion modeling is a core technology in computer animation, game development, and human-computer interaction. In particular, generating natural and coherent in-between motion using only the initial and terminal frames remains a fundamental yet unresolved challenge. Existing methods typically rely on dense keyframe inputs or complex prior structures, making it difficult to balance motion quality and plausibility under conditions such as sparse constraints, long-term dependencies, and diverse motion styles. To address this, we propose a motion generation framework based on a frequency-domain diffusion model, which aims to better model complex motion distributions and enhance generation… More >

Xiaolong Li, Hui Chen, Yingwen Liu, Peng Yang^*

Frontiers in Heat and Mass Transfer, Vol.23, No.6, pp. 1767-1788, 2025, DOI:10.32604/fhmt.2025.070537 - 31 December 2025

Abstract Hazardous gas intrusion in tightly sealed and geometrically complex confined spaces, such as armored tanks, poses a critical threat to occupant health. The intricate internal structure of these systems may lead to non-intuitive pollutant transport pathways. However, the spatial and temporal evolution of these structures, as well as the intrinsic mechanisms of the purification systems, remain poorly elucidated. In this study, a high-fidelity, transient three-dimensional computational fluid dynamics (CFD) model was developed to simulate the leakage and dispersion of carbon monoxide (CO) and nitrogen dioxide (NO₂) using the RNG k-ε turbulence model. Scenarios with and without… More > Graphic Abstract

Arshad Riaz^1,*, Misbah Ilyas¹, Muhammad Naeem Aslam², Safia Akram³, Sami Ullah Khan⁴, Ghaliah Alhamzi⁵

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.3, pp. 3481-3509, 2025, DOI:10.32604/cmes.2025.072513 - 23 December 2025

Abstract Peristaltic transport of non-Newtonian nanofluids with double diffusion is essential to biological engineering, microfluidics, and manufacturing processes. The authors tackle the key problem of Sisko nanofluids under double diffusion convection with thermal radiations and electroosmotic effects. The study proposes a solution approach by using Morlet-Wavelet Neural Networks that can effectively solve this complex problem by their superior ability in the capture of nonlinear dynamics. These convergence analyses were calculated across fifty independent runs. Theil’s Inequality Coefficient and the Mean Squared Error values range from 10⁻⁷ to 10⁻⁵ and 10⁻⁷ to 10⁻¹⁰, respectively. These values showed the proposed More >

Akramjon Y. Boboev^1,*, Ulugbek R. Karimberdiev¹, Sardor R. Kadirov², Nuritdin Y. Yunusaliyev¹

Chalcogenide Letters, Vol.22, No.11, pp. 951-957, 2025, DOI:10.15251/CL.2025.2211.951

Abstract This paper investigates the possibility of growing solid solutions of the composition (Ge₂)_1−x−y(GaAs_1−δBi_δ)_x(ZnSe)_y on silicon substrates using a germanium (Ge) buffer layer. The optimal conditions for obtaining a structurally high-quality epitaxial layer have been determined. In the study, the solid solution was obtained by liquid-phase epitaxy from a bismuth-containing melt solution. Epitaxial growth was carried out in a palladiumpurified hydrogen atmosphere at a cooling rate of 1 ÷ 1.5°C/min in the temperature range 750 ÷ 650°C. Experimental data showed that the growth of the epitaxial film significantly depends on the size of the gap between the… More >

Mengna Cheng¹, Hao Guo², Feng Cao², Jie Gong¹, Fengshuang Du^1,*

FDMP-Fluid Dynamics & Materials Processing, Vol.21, No.10, pp. 2629-2650, 2025, DOI:10.32604/fdmp.2025.070344 - 30 October 2025

Abstract Produced water reinjection is a common strategy in offshore oilfield operations, yet the presence of solid particles in produced water can lead to localized formation pressure buildup, increasing the risk of rock fracturing and leakage. In this study, we present an integrated experimental and numerical investigation to quantify the effects of particle migration on formation pressure and the spatial diffusion of injected water. Dynamic plugging experiments were performed to systematically examine the influence of injection rate and injection volume on core permeability. Results demonstrate that higher injection rates substantially reduce permeability, and the derived relationship More >