相关论文: Local Prompt Adaptation for Style-Consistent Multi…

Personalizing visual generative models to meet specific user needs has gained increasing attention, yet current methods like Low-Rank Adaptation (LoRA) remain impractical due to their demand for task-specific data and lengthy optimization.…

Prompt learning has been widely adopted to efficiently adapt vision-language models (VLMs) like CLIP for various downstream tasks. Despite their success, current VLM-based facial expression recognition (FER) methods struggle to capture…

Large-scale Text-to-Image (T2I) diffusion models demonstrate significant generation capabilities based on textual prompts. Based on the T2I diffusion models, text-guided image editing research aims to empower users to manipulate generated…

Despite recent progress, reinforcement learning (RL)-based fine-tuning of diffusion models often struggles with generalization, composability, and robustness against reward hacking. Recent studies have explored prompt refinement as a…

Contrastive Language-Image Pre-training (CLIP), which excels at abstracting open-world representations across domains and modalities, has become a foundation for a variety of vision and multimodal tasks. However, recent studies reveal that…

Foundation models enable prompt-based classifiers for zero-shot and few-shot learning. Nonetheless, the conventional method of employing fixed prompts suffers from distributional shifts that negatively impact generalizability to unseen…

Controllable video generation has emerged as a versatile tool for autonomous driving, enabling realistic synthesis of traffic scenarios. However, existing methods depend on control signals at inference time to guide the generative model…

Pre-trained vision-language models like CLIP have remarkably adapted to various downstream tasks. Nonetheless, their performance heavily depends on the specificity of the input text prompts, which requires skillful prompt template…

Diffusion-based text-to-image (T2I) models have made remarkable progress in generating photorealistic and semantically rich images. However, when the target concepts lie in low-density regions of the training distribution, these models…

Generative recommendation represents each item as a semantic ID, i.e., a sequence of discrete tokens, and generates the next item through autoregressive decoding. While effective, existing autoregressive models face two intrinsic…

Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts…

In text-to-image generation tasks, the advancements of diffusion models have facilitated the fidelity of generated results. However, these models encounter challenges when processing text prompts containing multiple entities and attributes.…

Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks. Different from the traditional representation learning that is based…

Personalizing a large-scale pretrained Text-to-Image (T2I) diffusion model is challenging as it typically struggles to make an appropriate trade-off between its training data distribution and the target distribution, i.e., learning a novel…

Diffusion models emerged as a leading approach in text-to-image generation, producing high-quality images from textual descriptions. However, attempting to achieve detailed control to get a desired image solely through text remains a…

Recently, diffusion models have exhibited superior performance in the area of image inpainting. Inpainting methods based on diffusion models can usually generate realistic, high-quality image content for masked areas. However, due to the…

Continual Test-Time Adaptation (CTTA) aims to adapt the source model to continually changing unlabeled target domains without access to the source data. Existing methods mainly focus on model-based adaptation in a self-training manner, such…

Prompt design plays a crucial role in text-to-video (T2V) generation, yet user-provided prompts are often short, unstructured, and misaligned with training data, limiting the generative potential of diffusion-based T2V models. We present…

Large Language Models (LLMs) have shown outstanding performance across a variety of tasks, partly due to advanced prompting techniques. However, these techniques often require lengthy prompts, which increase computational costs and can…

With the growing popularity of personalized human content creation and sharing, there is a rising demand for advanced techniques in customized human image generation. However, current methods struggle to simultaneously maintain the fidelity…