Back to events
Model releaseCritical global significanceConfirmed confidence

OpenAI releases the CLIP vision-language model

OpenAI released CLIP, a vision-language model trained with natural-language supervision, together with its paper, code, and pretrained models.

Event details

OpenAI released CLIP on January 5, 2021. The model uses contrastive learning to align image and text representations and can perform zero-shot image classification using natural-language category names. OpenAI published the paper and code on the same day, and the repository provided access to pretrained models.

Why it matters

CLIP established a transferable shared representation for images and text, advanced zero-shot visual recognition, and became a common component in later image-generation and multimodal systems.

99/100Global significance score. Regional effects are recorded only when the evidence supports a meaningful difference.

Access notes

The paper, code, and pretrained models were publicly available.