News Gist .News

Articles | Politics | Finance | Stocks | Crypto | AI | Technology | Science | Gaming | PC Hardware | Laptops | Smartphones | Archive

Cohere Claims Its New Aya Vision AI Model Is Best-In-Class

Cohere for AI has launched Aya Vision, a multimodal AI model that performs a variety of tasks, including image captioning and translation, which the lab claims surpasses competitors in performance. The model, available for free through WhatsApp, aims to bridge the gap in language performance for multimodal tasks, leveraging synthetic annotations to enhance training efficiency. Alongside Aya Vision, Cohere introduced the AyaVisionBench benchmark suite to improve evaluation standards in vision-language tasks, addressing concerns about the reliability of existing benchmarks in the AI industry.

See Also