500AI
Back to researchers

Girish Sastry

Vision-language pretraining (CLIP)

Co-authored CLIP: a core reference for contrastive multimodal pretraining.

Highlights

OpenAICLIPMultimodalVision-language
Focus: Vision-language pretraining (CLIP)
Why it matters: Co-authored CLIP: a core reference for contrastive multimodal pretraining.
Start here
Learning Transferable Visual Models From Natural Language Supervisionpaper →

Research Areas

OpenAICLIPMultimodalVision-language
Girish Sastry - AI Researcher Profile | 500AI