Related papers: GRAN-TED: Generating Robust, Aligned, and Nuanced …
Recently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has provided a unified point of view on these techniques allowing…
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…
Personalized text-to-image generation has attracted unprecedented attention in the recent few years due to its unique capability of generating highly-personalized images via using the input concept dataset and novel textual prompt. However,…
Music generation has attracted growing interest with the advancement of deep generative models. However, generating music conditioned on textual descriptions, known as text-to-music, remains challenging due to the complexity of musical…
The development of unified multimodal large language models (MLLMs) is fundamentally challenged by the granularity gap between visual understanding and generation: understanding requires high-level semantic abstractions, while image…
Large-scale diffusion generative models are greatly simplifying image, video and 3D asset creation from user-provided text prompts and images. However, the challenging problem of text-to-4D dynamic 3D scene generation with diffusion…
We present ENTED, a new framework for blind face restoration that aims to restore high-quality and realistic portrait images. Our method involves repairing a single degraded input image using a high-quality reference image. We utilize a…
Despite recent progress, vision-language encoders struggle with two core limitations: (1) weak alignment between language and dense vision features, which hurts tasks like open-vocabulary semantic segmentation; and (2) high token counts for…
Self-supervised representation learning on text-attributed graphs, which aims to create expressive and generalizable representations for various downstream tasks, has received increasing research attention lately. However, existing methods…
Diffusion models have exhibited substantial success in text-to-image generation. However, they often encounter challenges when dealing with complex and dense prompts involving multiple objects, attribute binding, and long descriptions. In…
Ubiquitous image transmission in emerging applications brings huge overheads to limited wireless resources. Since that text has the characteristic of conveying a large amount of information with very little data, the transmission of the…
Visual generative models based on latent space have achieved great success, underscoring the significance of visual tokenization. Mapping images to latents boosts efficiency and enables multimodal alignment for scaling up in downstream…
Text-to-image personalization aims to teach a pre-trained diffusion model to reason about novel, user provided concepts, embedding them into new scenes guided by natural language prompts. However, current personalization approaches struggle…
Fine-grained information on translation errors is helpful for the translation evaluation community. Existing approaches can not synchronously consider error position and type, failing to integrate the error information of both. In this…
We present a novel perspective on learning video embedders for generative modeling: rather than requiring an exact reproduction of an input video, an effective embedder should focus on synthesizing visually plausible reconstructions. This…
Diffusion models have emerged as a powerful paradigm for generation, obtaining strong performance in various continuous domains. However, applying continuous diffusion models to natural language remains challenging due to its discrete…
In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. While generative models provide a consistent network architecture between…
Text-to-Image generation has evolved from basic image synthesis into a frequently used core capability in professional creative workflows, where simple text-image alignment can no longer satisfy users' pressing demands for faithful…
Vision-language tracking has gained increasing attention in many scenarios. This task simultaneously deals with visual and linguistic information to localize objects in videos. Despite its growing utility, the development of vision-language…
In this paper, we introduce a novel dIffusion language modEl pre-training framework for text generation, which we call GENIE. GENIE is a large-scale pretrained diffusion language model that consists of an encoder and a diffusion-based…