Recently, diffusion models have been proven to perform remarkably well in text-to-image synthesis tasks in a number of studies, immediately presenting new study opportunities for image generation. Google’s Imagen follows this research trend and outperforms DALLE2 as the best model for text-to-image generation. However, Imagen merely uses a T5 language model for text processing, which cannot ensure learning the semantic information of the text. Furthermore, the Efficient UNet leveraged by Imagen is not the best choice in image processing. To address these issues, we propose the Swinv2-Imagen, a novel text-to-image diffusion model based on a Hierarchical Visual Transformer and a Scene Graph incorporating a semantic layout. In the proposed model, the feature vectors of entities and relationships are extracted and involved in the diffusion model, effectively improving the quality of generated images. On top of that, we also introduce a Swin-Transformer-based UNet architecture, called Swinv2-Unet, which can address the problems stemming from the CNN convolution operations. Extensive experiments are conducted to evaluate the performance of the proposed model by using three real-world datasets, i.e. MSCOCO, CUB and MM-CelebA-HQ. The experimental results show that the proposed Swinv2-Imagen model outperforms several popular state-of-the-art methods.

This paper introduces an LLM-Enhanced Agent-Based Influence Diffusion Simulation (LLM-AIDSim) framework that integrates large language models (LLMs) into agent-based modelling to simulate influence diffusion in social networks. The proposed framework enhances traditional influence diffusion models by allowing agents to generate language-level responses, providing deeper insights into user agent interactions. Our framework addresses the limitations of probabilistic models by simulating realistic, context-aware user behaviours in response to public statements. Using real-world news topics, we demonstrate the effectiveness of LLM-AIDSim in simulating topic evolution and tracking user discourse, validating its ability to replicate key aspects of real-world information propagation. Our experimental results highlight the role of influence diffusion in shaping collective discussions, revealing that, over time, diffusion narrows the focus of conversations around a few dominant topics. We further analyse regional differences in topic clustering and diffusion behaviours across three cities, Sydney, Auckland, and Hobart, revealing how demographics, income, and education levels influence topic dominance. This work underscores the potential of LLM-AIDSim as a decision-support tool for strategic communication, enabling organizations to anticipate and understand public sentiment trends.

Social influence modelling and maximization appear significant in various domains, such as e-business, marketing, and social computing. Most existing studies focus on how to maximize positive social impact to promote product adoptions based on static network snapshots. Such approaches can only increase influence in a social network in short-term, but cannot generate sustainable or long-term effects. In this research work, we study on how to maintain long-term influence in a social network and propose an agent-based influence maintenance model, which can select influential nodes based on the current status in dynamic social networks in multiple times. Within the context of our investigation, the experimental results indicate that multiple-time seed selection is capable of achieving more constant impact than that of one-shot selection. We claim that influence maintenance is crucial for supporting, enhancing and assisting long-term goals in business development. The proposed approach can automatically maintain long-lasting impact and achieve influence maintenance.