Related papers: Rethinking Prompt Design for Inference-time Scalin…
While large-scale datasets have driven significant progress in Text-to-Video (T2V) generative models, these models remain highly sensitive to input prompts, demonstrating that prompt design is critical to generation quality. Current methods…
The goal of this paper is to enhance Text-to-Audio generation at inference, focusing on generating realistic audio that precisely aligns with text prompts. Despite the rapid advancements, existing models often fail to achieve a reliable…
With AI-generated content becoming ubiquitous across the web, social media, and other digital platforms, it is vital to examine how such content are inspired and generated. The creation of AI-generated images often involves refining the…
Effectively adapting powerful pretrained foundation models to diverse tasks remains a key challenge in AI deployment. Current approaches primarily follow two paradigms:discrete optimization of text prompts through prompt engineering, or…
Recent text-to-image (T2I) generators can synthesize realistic images, but still struggle with compositional prompts involving multiple objects, counts, attributes, and relations. We introduce EPIC (Efficient Predicate-Guided Inference-Time…
While modern text-to-image (T2I) models excel at generating images from intricate prompts, they struggle to capture the key details when the inputs are descriptive paragraphs. This limitation stems from the prevalence of concise captions…
Inference-time scaling through multiple sample generation in combination with Process- or Outcome-Reward Model (PRM or ORM) re-ranking has proven effective for text-based reasoning in large language models. This paper investigates whether…
We investigate the efficacy of visual prompting to adapt large-scale models in vision. Following the recent approach from prompt tuning and adversarial reprogramming, we learn a single image perturbation such that a frozen model prompted…
Aligning text-to-image generation with user intent remains challenging, as users frequently provide ambiguous inputs and struggle with model idiosyncrasies. We propose Adaptive Prompt Elicitation (APE), a technique that adaptively poses…
Content creators often aim to create personalized images using personal subjects that go beyond the capabilities of conventional text-to-image models. Additionally, they may want the resulting image to encompass a specific location, style,…
TIPO (Text-to-Image Prompt Optimization) introduces an efficient approach for automatic prompt refinement in text-to-image (T2I) generation. Starting from simple user prompts, TIPO leverages a lightweight pre-trained model to expand these…
Text-to-image models are powerful for producing high-quality images based on given text prompts, but crafting these prompts often requires specialized vocabulary. To address this, existing methods train rewriting models with supervision…
Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications, and continue to fascinate researchers across fields for…
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…
Image restoration aims to reconstruct degraded images, e.g., denoising or deblurring. Existing works focus on designing task-specific methods and there are inadequate attempts at universal methods. However, simply unifying multiple tasks…
In this paper, we present PRISM, a Promptable and Robust Interactive Segmentation Model, aiming for precise segmentation of 3D medical images. PRISM accepts various visual inputs, including points, boxes, and scribbles as sparse prompts, as…
Personalized image generation via text prompts has great potential to improve daily life and professional work by facilitating the creation of customized visual content. The aim of image personalization is to create images based on a…
Prompt engineering is still the primary way for users of generative text-to-image models to manipulate generated images in a targeted way. Based on treating the model as a continuous function and by passing gradients between the image space…
Prompt tuning for vision-language models such as CLIP involves optimizing the text prompts used to generate image-text pairs for specific downstream tasks. While hand-crafted or template-based prompts are generally applicable to a wider…
The evolution of prompt learning methodologies has driven exploration of deeper prompt designs to enhance model performance. However, current deep text prompting approaches suffer from two critical limitations: Over-reliance on constrastive…