share_log

阿里云通义千问开源首个多模态推理模型QVQ

Alibaba Cloud's Tongyi Qianwen has released the first open-source multimodal inference model QVQ.

Breakings ·  11:07

On December 25, Alibaba Cloud Tongyi Qianwen released the industry's first open-source multimodal reasoning model QVQ-72B-Preview. QVQ demonstrated unexpectedly strong visual understanding and reasoning capabilities, particularly excelling in solving complex reasoning problems in mathematics, physics, and science. Various evaluation metrics indicate that QVQ surpasses the previous visual understanding model "open-source king" Qwen2-VL, with overall performance comparable to that of full-version reasoning models such as OpenAI o1 and Claude 3.5 Sonnet. (All-weather Technology)

The translation is provided by third-party software.


The above content is for informational or educational purposes only and does not constitute any investment advice related to Futu. Although we strive to ensure the truthfulness, accuracy, and originality of all such content, we cannot guarantee it.
    Write a comment