CogVLM
CogVLM is a large-scale vision-language foundation model developed by researchers at Tsinghua University and Zhipu AI. It bridges the gap between visual and language understanding by incorporating a trainable visual expert module into the transformer architecture. CogVLM is designed to perform a wide range of vision-language tasks, including image captioning, visual question answering, and multimodal chat. The model is notable for its ability to handle complex visual reasoning and detailed image descriptions while maintaining strong language capabilities. It is open-source and available for research and commercial use under the Apache 2.0 license.
Transparency Score
Weighted across four pillars · updated February 12, 2026
Capabilities
Vendor Information
Complete information about the vendor/provider of this AI application
EU AI Act Provider Information
Get insights into risk by running assessments on this AI application.
Work at Zhipu AI (Z.ai)? Claim this listing to correct or complete the data.
EU Alternatives
Discover EU-based alternatives for this AI application.
Ready to manage AI applications?
Track, assess, and govern your AI applications with Anove.