Related papers: SUR-adapter: Enhancing Text-to-Image Pre-trained D…
Neural language models (LMs) have been extensively trained on vast corpora to store factual knowledge about various aspects of the world described in texts. Current technologies typically employ knowledge editing methods or specific prompts…
The recently rising markup-to-image generation poses greater challenges as compared to natural image generation, due to its low tolerance for errors as well as the complex sequence and context correlations between markup and rendered image.…
Cross-lingual knowledge transfer, especially between high- and low-resource languages, remains challenging in natural language processing (NLP). This study offers insights for improving cross-lingual NLP applications through the combination…
Images produced by text-to-image diffusion models might not always faithfully represent the semantic intent of the provided text prompt, where the model might overlook or entirely fail to produce certain objects. Existing solutions often…
The emergence of diffusion models has significantly advanced image synthesis. The recent studies of model interaction and self-corrective reasoning approach in large language models offer new insights for enhancing text-to-image models.…
Personalizing generative models offers a way to guide image generation with user-provided references. Current personalization methods can invert an object or concept into the textual conditioning space and compose new natural sentences for…
Large-scale pre-trained diffusion models have been extensively adopted for real-world image Super-Resolution because of their powerful generative priors through textual guidance. However, when super-resolving high-resolution images with…
Visual-textual correlations in the attention maps derived from text-to-image diffusion models are proven beneficial to dense visual prediction tasks, e.g., semantic segmentation. However, a significant challenge arises due to the input…
Semantic communications mark a paradigm shift from bit-accurate transmission toward meaning-centric communication, essential as wireless systems approach theoretical capacity limits. The emergence of generative AI has catalyzed generative…
Diffusion models have emerged as a powerful paradigm for modern generative modeling, demonstrating strong potential for large language models (LLMs). Unlike conventional autoregressive (AR) models that generate tokens sequentially,…
In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach…
Image restoration is a classic low-level problem aimed at recovering high-quality images from low-quality images with various degradations such as blur, noise, rain, haze, etc. However, due to the inherent complexity and non-uniqueness of…
Recently, the impressive generative capabilities of diffusion models have been demonstrated, producing images with remarkable fidelity. Particularly, existing methods for the 3D object generation tasks, which is one of the fastest-growing…
Text entry is an essential task in our day-to-day digital interactions. Numerous intelligent features have been developed to streamline this process, making text entry more effective, efficient, and fluid. These improvements include…
Recent advancement in text-to-image models (e.g., Stable Diffusion) and corresponding personalized technologies (e.g., DreamBooth and LoRA) enables individuals to generate high-quality and imaginative images. However, they often suffer from…
Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…
Recent advancements in text-to-image generation using diffusion models have significantly improved the quality of generated images and expanded the ability to depict a wide range of objects. However, ensuring that these models adhere…
We present Prompt Diffusion, a framework for enabling in-context learning in diffusion-based generative models. Given a pair of task-specific example images, such as depth from/to image and scribble from/to image, and a text guidance, our…
Semantic communication is expected to be one of the cores of next-generation AI-based communications. One of the possibilities offered by semantic communication is the capability to regenerate, at the destination side, images or videos…
Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…