Denoising diffusion models have emerged as a powerful tool for various image generation
and editing tasks, facilitating the synthesis of visual content in an unconditional or input …

As one of the most popular and sought-after generative models in the recent years, diffusion
models have sparked the interests of many researchers and steadily shown excellent …

Generating instructional images of human daily actions from an egocentric viewpoint serves
as a key step towards efficient skill transfer. In this paper, we introduce a novel problem …

This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with
around 200,000 edits. Unlike prior approaches relying on attribute guidance or human …

DALL-E and Sora have gained attention by producing implausible images, such as"
astronauts riding a horse in space." Despite the proliferation of text-to-vision models that …

The rapid advancement of large language models (LLMs) and multimodal learning has
transformed digital content creation and manipulation. Traditional visual editing tools require …

In this paper, we focus on the task of instruction-based image editing. Previous works like
InstructPix2Pix, InstructDiffusion, and SmartEdit have explored end-to-end editing. However …

Large language models (LLMs) constitute a paradigm shift in Natural Language Processing
and Artificial Intelligence. In this thesis, I explore the integration of creative capabilities into …

Modern high-performance computing (HPC) systems rely extensively on parallel
architectures, including multicore CPUs and GPUs, to fulfill the ever-growing computational …

This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with
around 200,000 edits. Unlike prior approaches relying on attribute guidance or human …