Deep semi-supervised learning is a fast-growing field with a range of practical applications.
This paper provides a comprehensive survey on both fundamentals and recent advances in …

Text watermarking algorithms are crucial for protecting the copyright of textual content.
Historically, their capabilities and application scenarios were limited. However, recent …

Large language models have been shown to achieve remarkable performance across a
variety of natural language tasks using few-shot learning, which drastically reduces the …

We introduce SPEAR-TTS, a multi-speaker text-to-speech (TTS) system that can be trained
with minimal supervision. By combining two types of discrete speech representations, we …

Programming is a powerful and ubiquitous problem-solving tool. Systems that can assist
programmers or even generate programs themselves could make programming more …

We consider the problem of predicting a protein sequence from its backbone atom
coordinates. Machine learning approaches to this problem to date have been limited by the …

Hallucinated translations can severely undermine and raise safety issues when machine
translation systems are deployed in the wild. Previous research on the topic focused on …

This paper explores a simple method for improving the zero-shot learning abilities of
language models. We show that instruction tuning--finetuning language models on a …

Abstract We present Multiscale Vision Transformers (MViT) for video and image recognition,
by connecting the seminal idea of multiscale feature hierarchies with transformer models …

Existing work in translation demonstrated the potential of massively multilingual machine
translation by training a single model able to translate between any pair of languages …