Chinese e-commerce company Alibaba Group has launched a new artificial intelligence model that, according to representatives of the organization, is capable of solving more complex problems than Alibaba’s previous projects. The model comes in two versions: Qwen-VL and Qwen-VL-Chat.
According to CNBC, the Chinese IT giant is releasing an open source AI model. This means that researchers and companies around the world will be able to study Qwen-VL and Qwen-VL-Chat and use the neural network to create their own AI applications.
Alibaba said that Qwen-VL can respond to queries related to various images and generate image captions.
At the same time, according to the creators of the neural network, Qwen-VL-Chat is designed for “more complex interaction.” The model is capable of comparing multiple images, describing them, and even solving the mathematical equations displayed on the image. Also, artificial intelligence can create personalized images based on photographs.
For example, a chatbot can answer questions about the location of specific hospital departments based on a map of the hospital in Chinese.
The post compares Qwen-VL and Qwen-VL-Chat with the ChatGPT-4 neural network, which also has the function of recognizing images and responding to image queries. Alibaba’s latest two models are based on a large language model (LLM) from a company called Tongyi Qianwen released in spring 2023.
Photo: Ascannio / Shutterstock
Author:
Ahmed Sadulayev
Source: RB
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
