venturebeat.com

Cohere’s first vision model Aya Vision is here with broad, multilingual understanding and open weights — but there’s a catch

Aya Vision 8B and 32B demonstrate best-in-class performance relative to their parameter size, outperforming much larger models.

Mar 4, 2025 - 19:10
 0
Cohere’s first vision model Aya Vision is here with broad, multilingual understanding and open weights — but there’s a catch
Flat AI illustration of happy man typing on a laptop in front of a large view of the Earth with word bubbles of different sizes and colors popping out from different regions representing different languages being spoken
Aya Vision 8B and 32B demonstrate best-in-class performance relative to their parameter size, outperforming much larger models.Read More
Read More

Tags:

Previous Article

Contextual AI’s new AI model crushes GPT-4o in accuracy — here’s why it matters

Next Article

49,000+ Access Management Systems Worldwide Configured With Massive Security Gaps

Related Posts

Supergiant Games battles back accusations it is working around SAG-AFTRA strike

Supergiant Games battles back accusations it is working...

Feb 21, 2025  0

Replit and Anthropic’s AI just helped Zillow build production software—without a single engineer

Replit and Anthropic’s AI just helped Zillow build prod...

Feb 17, 2025  0

A Stytch in time: Connected Apps untangles authorizatio...

Feb 19, 2025  0