Aya Vision
Multilingual, Multimodal AI from Cohere
About
The page is a blog post from Cohere, announcing 'Aya Vision', a new state-of-the-art open-weights vision model developed by Cohere For AI. This model aims to bridge the gap in multilingual and multimodal AI performance, excelling across 23 languages and various modalities. It performs tasks such as image captioning, visual question answering, text generation, and translating text/images into natural language. The post highlights Aya Vision's superior performance against leading open-weight models, emphasizing its efficiency and scalability through algorithmic breakthroughs like synthetic annotations and multimodal model merging. Cohere is releasing Aya Vision as 8B and 32B open-weights models on platforms like Kaggle and Hugging Face, and also provides free access via WhatsApp. The initiative is part of Cohere's broader commitment to multilingual AI research and invites researchers to collaborate through grants and an open science community.
Categories & Tags
Color Palette
White
#FFFFFF
Dark Grey / Black
#212121
Cohere Blue
#0066FF
Light Grey
#F5F5F5
Typography
Sans-serif
Headings and Body Text
Design Review
Similar Products
Clear for Slack
Clear messages get answered quicker
Griply 2026
Achieve your goals with a goal-oriented task manager
vibecoder.date
Find who you vibe with, git commit to love
HappyMail
We made email simple again
Blober.io
The easiest way to transfer files between cloud providers.
Supaguard
Scan, Detect & Protect Your Supabase Data
Timelines Time Tracking 4
Track your time to achieve your New Year resolutions.
SoftReveal — Reveal less. Engage more.
Hide Content, Reveal on Click
CalPal
The notebook calculator that thinks for you (now with AI).
Reword
Rewrite messages without leaving your workflow
Radial
Your shortcuts, one gesture away
MoovAI
Launch viral AI ads & pro social content in minutes