Vision-language model
A model that reads images together with text, answering questions about photos, documents and charts.
Also: VLM
A vision-language model usually joins a vision encoder to a language model with a small connecting network that turns image features into tokens the language model can read. LLaVA, released by researchers in 2023, showed this could be done cheaply with open models; Qwen-VL, Gemma 3, Llama 3.2 Vision and many others followed. Proprietary models such as GPT-4o, Claude and Gemini read images natively. They power document reading, accessibility tools and computer-use agents. They can still misread small text and miscount objects.