Close
Cohere has launched Aya Vision, a multimodal AI model that excels in tasks such as image captioning, photo Q&A, text translation, and summarization in 23 languages. This model is available for free via WhatsApp, aiming to bridge the performance gap in AI across different languages and modalities. The release includes two versions, Aya Vision 32B and Aya Vision 8B, with the former outperforming larger models in visual understanding benchmarks.
Aya Vision utilizes synthetic annotations for training, allowing for efficient resource use while maintaining competitive performance. This approach aligns with industry trends where synthetic data is increasingly leveraged due to the scarcity of real-world data. Additionally, Cohere introduced AyaVisionBench, a benchmark suite designed to evaluate models' capabilities in vision-language tasks, addressing the current evaluation crisis in AI.
• Cohere's Aya Vision model performs multimodal tasks in 23 languages.
• Aya Vision outperforms larger models in visual understanding benchmarks.
Multimodal AI refers to models that can process and understand multiple types of data, such as text and images.
Synthetic annotations are AI-generated tags or labels used to train models, enhancing their understanding of data.
A benchmark suite is a set of tests designed to evaluate the performance of AI models on specific tasks.
Cohere is an AI startup focused on developing advanced AI models, including the newly released Aya Vision.
OpenAI is a leading AI research organization known for its development of advanced AI technologies and models.
2, which Aya Vision outperformed in benchmarks.
The Globe and Mail 11month
Insider Monkey on MSN.com 8month
Isomorphic Labs, the AI drug discovery platform that was spun out of Google's DeepMind in 2021, has raised external capital for the first time. The $600
How to level up your teaching with AI. Discover how to use clones and GPTs in your classroom—personalized AI teaching is the future.
Trump's Third Term? AI already knows how this can be done. A study shows how OpenAI, Grok, DeepSeek & Google outline ways to dismantle U.S. democracy.
Sam Altman today revealed that OpenAI will release an open weight artificial intelligence model in the coming months. "We are excited to release a powerful new open-weight language model with reasoning in the coming months," Altman wrote on X.
Log in
Sign Up
AI Tools - Popular
AI Tools - Categories
GPTs - Categories
AI for Jobs
Key AI Highlights in this Article
Key AI Terms Mentioned in this Article
Companies Mentioned in this Article
