← Back to Model Beat
5Models·Oct 21

DeepSeek unveils AI model that uses visual perception to compress text input - South China Morning Post

DeepSeek unveils AI model that uses visual perception to compress text input South China Morning Post

Covered by 2 sources

Related stories

ModelsGemini achieves gold-medal level at the International Collegiate Programming Contest World FinalsOct 24ModelsIntroducing Veo 3.1 and advanced creative capabilitiesOct 23ModelsImage editing in Gemini just got a major upgradeOct 23ModelsIntroducing the Gemini 2.5 Computer Use modelOct 23