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
Recent text-to-image generative models have demonstrated an unparalleled ability to generate diverse and creative imagery guided by a target text prompt.
By incorporating the vision features in both stages, the model is able to generate effective rationales that contribute to answer inference.
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
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.
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.
By fitting a bridge-shaped curve to the illumination map distribution, both regions are suppressed and two tasks are bridged naturally.
In this paper, we answer these questions by first defining the human-level quality based on the statistical significance of subjective measure and introducing appropriate guidelines to judge it, and then developing a TTS system called NaturalSpeech that achieves human-level quality on a benchmark dataset.
Ranked #1 on Text-To-Speech Synthesis on LJSpeech
Despite recent success in large language model (LLM) reasoning, LLMs struggle with hierarchical multi-step reasoning tasks like generating complex programs.
Ranked #1 on Code Generation on APPS