Deep generative models are a class of techniques that train deep neural networks to model
the distribution of training samples. Research has fragmented into various interconnected …

The twenty-first century is presenting humankind with unprecedented environmental and
medical challenges. The ability to design novel proteins tailored for specific purposes would …

Denoising diffusion probabilistic models (DDPMs)[Ho et al. 2021] have shown impressive
results on image and waveform generation in continuous state spaces. Here, we introduce …

We present a unified transformer, ie, Show-o, that unifies multimodal understanding and
generation. Unlike fully autoregressive models, Show-o unifies autoregressive and …

Ancient history relies on disciplines such as epigraphy—the study of inscribed texts known
as inscriptions—for evidence of the thought, language, society and history of past …

Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise
toxic language which hinders their safe deployment. We investigate the extent to which …

When scaled to hundreds of billions of parameters, pretrained language models such as
GPT-3 (Brown et al., 2020) achieve remarkable few-shot performance. However, enormous …

Abstract⚠ This paper contains prompts and model outputs that are offensive in nature. When
trained on large, unfiltered crawls from the Internet, language models pick up and reproduce …

The cognitive capabilities of children develop during the early years of their life. Research
shows that learning a foreign language helps develop cognitive skills. Moreover, learning a …

Rapid progress in machine learning for natural language processing has the potential to
transform debates about how humans learn language. However, the learning environments …