This paper presents a three-stage approach for transforming industrial requirement documents into executable control models using large language models (LLMs). The method consists of component extraction, system behavior structuring, and execution flow construction, each guided by prompt-based LLM reasoning. Instead of generating code directly, the large language model produces a structured representation with components, operations, and assumption–guarantee pairs that define logical dependencies. This intermediate model supports human-in-the-loop correction and is translated into control code using rule-based mapping. A case study on a signal-driven production line shows the approach achieves over 90% accuracy across all modeling stages with minimal manual intervention, demonstrating its potential for safe and efficient industrial automation modeling.

In this paper, we investigate the benefits of self-supervised learning (SSL) to downstream tasks of satellite images. Unlike common student academic projects, this work focuses on the advantages of the SSL for deployment-driven tasks which have specific scenarios with low or high-spatial resolution images. Our preliminary experiments demonstrate the robust benefits of the SSL trained by medium-resolution (10m) images to both low-resolution (100m) scene classification case (4.25%↑) and very high-resolution (5cm) aerial image segmentation case (1.96%↑), respectively.

Single image dehazing is a challenging vision problem aiming to provide clear images for downstream computer vision applications (e.g., semantic segmentation, object detection, and super resolution). Most existing methods leverage the physical scattering model or convolutional neural networks (CNNs) for haze removal, which however ignore the complementary advantages between each other. Especially lacking marginal and visual prior instructions, CNN-based methods still have gaps in details and color recovery. To solve these, we propose a Prior-based with Decoupling ability Dehazing GAN Network (PDD-GAN), which is based on PeleetNet and attached with an attention module (CBAM). The prior-based decoupling approach consists of two parts: high and low frequency filtering and HSV contrastive loss. We process the image via a band-stop filter and add it as the fourth channel of data (RGBFHL) to decouple the hazy image at the structural level. Besides, a novel prior loss with contrastive regularization is proposed at the visual level. Sufficient experiments are carried out to demonstrate that PDD-GAN outperforms state-of-the-art methods by up to 0.86db in PSNR. In particular, extensive experiments indicate that RGBFHL increases by 0.99db compared with the original three-channel data (RGB) and the extra HSV prior loss escalates by 2.0db. Above all, our PDD-GAN indeed has the decoupling ability and improves the dehazing results.