2026-01-27
South China Morning Post
DeepSeek launches DeepSeek-OCR 2, an upgraded optical character recognition model that replaces OpenAI-developed CLIP framework with Alibaba's Qwen2-0.5b
Ben Jiang /South China Morning Post:
2025-06-21
The Verge
54 related
Meta unveils the $399+ Oakley Meta HSTN glasses, with Meta AI and the features of its Ray-Ban models, plus 3K video recording and double the battery life
Oakley's Meta smart glasses actually look better than the Ray-Bans, and they bring massive upgrades Steve Vegvari / iPhone in Canada : Oakley Meta HSTN Smart Glasses Launching July 11 in Canada Jay Bo...
2022-10-06
Jay Alammar
1 related
An illustrated guide showing how Stable Diffusion generates images from text using a CLIP-based text encoder, an image information creator, and an image decoder
Jay Alammar :
2021-08-16
New Yorker
Profile of @images_ai, a Twitter account launched by a music student in June, which uses neural networks, including OpenAI's CLIP, to generate surreal art
Kyle Chayka / New Yorker : Tweets: @newyorker , @renois , @newyorker , @chaykak , @chaykak , and @chaykak Tweets: @newyorker : .@images_ai, which offers a constant feed of surreal, sometimes beautifu...
2021-01-06
MIT Technology Review
11 related
OpenAI introduces two new GPT-3 models: CLIP, which classifies images into categories from arbitrary text, and DALL·E, which can generate images from text
With GPT-3, OpenAI showed that a single deep-learning model could be trained to use language in a variety of ways simply by throwing it vast amounts of text.
Loading articles...