Recent text-to-image generative models have demonstrated an unparalleled ability to generate diverse and creative imagery guided by a target text prompt.
Pre-trained language models have attracted increasing attention in the biomedical domain, inspired by their great success in the general natural language domain.
Ranked #1 on Question Answering on PubMedQA
To reproduce the success of text-to-image (T2I) generation, recent works in text-to-video (T2V) generation employ large-scale text-video dataset for fine-tuning.
The cost of vision-and-language pre-training has become increasingly prohibitive due to end-to-end training of large-scale models.
Ranked #1 on Image Retrieval on COCO
We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image.
The expressive power of Graph Neural Networks (GNNs) has been studied extensively through the Weisfeiler-Leman (WL) graph isomorphism test.
By learning the latent representations of audio signals and their compositions without modeling the cross-modal relationship, AudioLDM is advantageous in both generation quality and computational efficiency.
Furthermore, we propose a latent-mapping algorithm in the latent space to convert the amateur vocal tone to the professional one.