Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens
ByT5 model for massively multilingual grapheme-to-phoneme conversion
T5: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Hierarchical Text-Conditional Image Generation with CLIP Latents
eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers
mT5: A massively multilingual pre-trained text-to-text transformer
ByT5: Towards a token-free future with pre-trained byte-to-byte models
Wikipedia Bibliography: