• Alibaba introduced two new AI models, Qwen-VL and Qwen-VL-Chat.
• The models are open source, which means they can be used by researchers, educators, and businesses worldwide.
• Qwen-VL can effectively respond to open-ended questions.

Alibaba introduced a new artificial intelligence model that surpasses their previous products in terms of understanding images and engaging in more advanced conversations. This move reflects the intensifying global competition for dominance in AI technology.

The Chinese tech giant unveiled two models, namely Qwen-VL and Qwen-VL-Chat, both of which will be open source. This means that researchers, educators, and businesses worldwide can utilize these models to develop their own AI applications without the need to train their individual systems, which saves both time and resources.

Alibaba’s Qwen-VL can effectively respond to open-ended questions related to various images and produce descriptive captions for pictures. On the other hand, Qwen-VL-Chat is designed for more intricate interactions, such as analyzing multiple image inputs and providing answers through multiple rounds of questioning. Its capabilities encompass tasks like crafting narratives and generating images based on user-input photos, as well as solving visual mathematical problems.

For instance, if presented with an image of a hospital sign in Chinese, the AI can interpret the image and answer queries about specific hospital departments’ locations.

Traditionally, generative AI has largely concentrated on generating text-based responses to human inputs. The latest iteration of OpenAI’s ChatGPT also possesses the capacity to comprehend images and formulate text-based responses, similar to the capabilities of Qwen-VL-Chat.

Also Read

Honor Magic Vs 2 receives certification for its 35W fast charging speeds

Honor is set to launch its Magic V2 globally at IFA Berlin....