South China Morning Post CENTER (0.0) Reliability: 7.5/10

DeepSeek unveils multimodal AI model that uses visual perception to compress text input

✍️ Wency Chen 📅 October 21, 2025 08:00 AM 🕐 Scraped: October 21, 2025

Summary: New release continues Chinese start-up’s efforts to raise AI models’ efficiency, while driving down the costs of building and using them.

DeepSeek on Monday released a new multimodal artificial intelligence model that can handle large and complex documents with significantly fewer tokens – the smallest unit of text that a model processes – by using visual perception as a compre

📰

Continue Reading on South China Morning Post

This preview shows approximately 15% of the article. Read the full story on the publisher's website to support quality journalism.

Read Full Article →

How do you feel about this article?

Read Original Article →

📝 Article Information

Author

Wency Chen

Original Publisher

🌍 South China Morning Post

CENTER Bias (0.0)

Published Date

October 21, 2025 at 08:00 AM

ℹ️

Disclaimer

ArkforgeAI.com - Newsource is a news aggregation platform. We do not create, write, or produce original news content. All articles are sourced from their respective publishers and remain the property of their original creators. We analyze and aggregate news from multiple sources to provide diverse perspectives across the political spectrum.

The content displayed here is for informational purposes only. For the complete and original article, please visit the source's website using the "Read Original Article" link above.

Desktop Only