Giraffe: A Mapping Architecture from Hidden Text Representations to Visual Embeddings for Efficient Graphic Design

The paper introduces Giraffe, a new mapping architecture that converts hidden text token representations into visual embeddings for graphic design tasks. It uses a single [IMG] token per image and two shallow MLP blocks—one for training and one for inference—to compress and expand embeddings, trained with six loss functions. The approach achieves strong performance in both image‑to‑design and text‑to‑design generation while remaining lightweight.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• rag
• multimodal