DeepSeek releases DeepSeek-OCR 2, AI can "see" an image in the same logical order as humans.

On the 27th, DeepSeek released the brand new DeepSeek-OCR 2 model, which adopts the innovative DeepEncoder V2 approach, enabling AI to dynamically rearrange different parts of an image based on its meaning, rather than simply scanning mechanically from left to right.

This approach simulates the logical process that humans follow when observing a scene. As a result, the model outperforms traditional vision-language models in handling images with complex layouts (such as documents or charts), achieving more intelligent and causally-reasoned visual understanding.

More updates coming soon...

Risk Disclosure and Disclaimer ClauseThe market has risks, and investment should be conducted with caution. This article does not constitute personal investment advice and does not take into account the special investment goals, financial situation, or needs of individual users. Users should consider whether any opinions, viewpoints, or conclusions in this article are suitable for their specific situation. Any investment based on this article is at your own risk.