Tag
radford
2 verified claims carrying this tag. Each has 2+ primary sources and an HMAC-SHA256 signature.
CLIP (Contrastive Language-Image Pretraining) introduced in paper: Learning Transferable Visual Models From Natural Language Supervision (Radford et al., 2021).
85a3ca745eaf4ee0 · 2 sources · 100% confidence
GPT-2 introduced in paper: Language Models are Unsupervised Multitask Learners (Radford et al., 2019).
859551dc078c46f8 · 2 sources · 100% confidence