Generative adversarial networks (GANs) have recently become a hot research topic;
however, they have been studied since 2014, and a large number of algorithms have been …

Generative Adversarial Networks (GANs) have achieved impressive results in various image
synthesis tasks, and are becoming a hot topic in computer vision research because of the …

Language Models (LMs) often cannot be deployed because of their potential to harm users
in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using …

Recent advances in large language models (LLMs) and the intensifying popularity of
ChatGPT-like applications have blurred the boundary of high-quality text generation …

In this paper we propose a new generative model of text, Step-unrolled Denoising
Autoencoder (SUNDAE), that does not rely on autoregressive models. Similarly to denoising …

Generating high-quality text with sufficient diversity is essential for a wide range of Natural
Language Generation (NLG) tasks. Maximum-Likelihood (MLE) models trained with teacher …

Hosting conversational responses on the official websites of products and services
companies is an essential marketing aspect. With Artificial Intelligence's help to make …

Autoregressive models using Transformers have emerged as the dominant approach for
music generation with the goal of synthesizing minute-long compositions that exhibit large …

Generative adversarial networks (GANs), a novel framework for training generative models
in an adversarial setup, have attracted significant attention in recent years. The two …

Can continuous diffusion models bring the same performance breakthrough on natural
language they did for image generation? To circumvent the discrete nature of text data, we …