Alibaba launches AI model that can understand images and have more complex conversations

Alibaba has launched two new artificial intelligence models, Qwen-VL and Qwen-VL-Chat, which can understand images and carry out complex conversations. The models will be open source, allowing researchers, academics, and companies worldwide to use them to create their own AI apps without needing to train their own systems. Qwen-VL can respond to open-ended queries related to different images and generate picture captions, while Qwen-VL-Chat can handle more complex interactions, such as comparing multiple image inputs and answering several rounds of questions.

The models are built upon Alibaba's large language model, Tongyi Qianwen, and are part of the company's efforts to reignite growth in its cloud division as it prepares to go public. The company has also open sourced two other AI models this month. Despite not earning any licensing fees, the open-source distribution is expected to help Alibaba attract more users for its AI model.

Key takeaways

Alibaba has launched two new artificial intelligence models, Qwen-VL and Qwen-VL-Chat, which can understand images and carry out complex conversations.
The new models are open source, allowing researchers, academics, and companies worldwide to use them to create their own AI apps without needing to train their own systems.
Qwen-VL-Chat can perform tasks such as writing stories, creating images based on user inputs, and solving mathematical equations shown in a picture.
The new models are built upon Alibaba's large language model called Tongyi Qianwen and are part of the company's strategy to attract more users to its AI model as it prepares to go public.

Alibaba launches AI model that can understand images and have more complex conversations

Key takeaways

Discussion (0)