相关论文: Rethinking Prompt Design for Inference-time Scalin…

Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter -- and data -- efficient way, by learning the ``soft prompts'' to condition frozen…

The rapid development of large language models is transforming software development. Beyond serving as code auto-completion tools in integrated development environments, large language models increasingly function as foundation models…

Visual Prompt Tuning (VPT) has emerged as a parameter-efficient fine-tuning paradigm for vision transformers, with conventional approaches utilizing dataset-level prompts that remain the same across all input instances. We observe that this…

Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on hand-engineered prompts, recent works learn prompts using the…

Large Language Models (LLMs) exhibit remarkable proficiency in addressing a diverse array of tasks within the Natural Language Processing (NLP) domain, with various prompt design strategies significantly augmenting their capabilities.…

Creative generation is the synthesis of new, surprising, and valuable samples that reflect user intent yet cannot be envisioned in advance. This task aims to extend human imagination, enabling the discovery of visual concepts that exist in…

Pre-trained language models have shown excellent results in few-shot learning scenarios using in-context learning. Although it is impressive, the size of language models can be prohibitive to make them usable in on-device applications, such…

Generative sequence modeling faces a fundamental tension between the expressivity of Transformers and the efficiency of linear sequence models. Existing efficient architectures are theoretically bounded by shallow, single-step linear…

Text-to-image generation models are powerful but difficult to use. Users craft specific prompts to get better images, though the images can be repetitive. This paper proposes a Prompt Expansion framework that helps users generate…

Despite substantial progress in text-to-image generation, achieving precise text-image alignment remains challenging, particularly for prompts with rich compositional structure or imaginative elements. To address this, we introduce Negative…

In text-to-image generation, different initial noises induce distinct denoising paths with a pretrained Stable Diffusion (SD) model. While this pattern could output diverse images, some of them may fail to align well with the prompt.…

Autoregressive multimodal large language models have recently gained popularity for image generation, driven by advances in foundation models. To enhance alignment and detail, newer approaches employ chain-of-thought (CoT) reasoning,…

The quality of text-to-image generation is continuously improving, yet the boundaries of its applicability are still unclear. In particular, refinement of the text input with the objective of achieving better results - commonly called…

Diffusion models have emerged as a dominant approach for text-to-image generation. Key components such as the human preference alignment and classifier-free guidance play a crucial role in ensuring generation quality. However, their…

Screenshot-to-code generation aims to translate user interface screenshots into executable frontend code that faithfully reproduces the target layout and style. Existing multimodal large language models perform this mapping directly from…

Recent developments in large language models (LLM) and generative AI have unleashed the astonishing capabilities of text-to-image generation systems to synthesize high-quality images that are faithful to a given reference text, known as a…

Text-to-image generation has recently emerged as a viable alternative to text-to-image retrieval, driven by the visually impressive results of generative diffusion models. Although query performance prediction is an active research topic in…

Visual Generative AI models have demonstrated remarkable capability in generating high-quality images from user inputs like text prompts. However, because these models have billions of parameters, they risk memorizing certain parts of the…

Vision-language models such as CLIP learn a generic text-image embedding from large-scale training data. A vision-language model can be adapted to a new classification task through few-shot prompt tuning. We find that such a prompt tuning…

Large pre-trained vision-language models have shown great prominence in transferring pre-acquired knowledge to various domains and downstream tasks with appropriate prompting or tuning. Existing prevalent tuning methods can be generally…