智谱AI近日开源了其在VLM领域的最新工作——CogAgent。CogAgent是一款基于CogVLM改进的模型，特别擅长GUI理解和导航。这款视觉语言模型拥有180亿参数规模，其中CogAgent-18B拥有110亿视觉参数和70亿语言参数。这一举措将进一步推动人工智能技术的发展和应用。
CogAgent的开放源代码将使更多人能够访问和使用这款强大的视觉语言模型，激发更多创新和研究。这款模型具有出色的GUI理解和导航能力，有望在各种场景中发挥作用，如智能客服、虚拟助手等。
智谱AI此次开源CogAgent，展示了其在人工智能领域的技术实力和创新精神。未来，智谱AI将继续探索更多先进技术，为我国人工智能产业发展贡献力量。
英文翻译：
News Title: Zhipu AI Opensources Visual Language Model CogAgent
Keywords: Zhipu AI, Open Source, Visual Language Model
News Content:
Zhipu AI has recently opened the source code of its latest work in the VLM field – CogAgent. CogAgent is an improved model based on CogVLM, specializing in GUI understanding and navigation. The visual language model has a scale of 18 billion parameters, with CogAgent-18B having 11 billion visual parameters and 7 billion language parameters. This move will further promote the development and application of artificial intelligence technology.
The open-source code of CogAgent will make it easier for more people to access and use this powerful visual language model, stimulating more innovation and research. The model’s excellent GUI understanding and navigation capabilities will likely play a role in various scenarios, such as intelligent customer service, virtual assistants, etc.
By opening up CogAgent, Zhipu AI has demonstrated its technical strength and innovative spirit in the field of artificial intelligence. In the future, Zhipu AI will continue to explore more advanced technologies and contribute to the development of China’s artificial intelligence industry.
【来源】https://mp.weixin.qq.com/s/KpAuOjJ6w5KVEK_wWGpqQw
Views: 1