Vision-Language Binding in In-Context Image Generation 事件

Vision-Language Binding in In-Context Image Generation arXiv:2605.24624v1 Announce Type: new Abstract: In-context image generation models such as FLUX.2 take a text prompt and an optional reference image as visual conditioning for the output. Internally, all three inputs -- text, reference image, and the noise tokens -- are concatenated and processed through a single attention stream, where all tokens can attend to one another. This leaves open how reference information flows through the model