SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Multimodal large language models (MLLMs) have made significant progress in understanding and interpreting mul- timedia content. However, their ability to generate me- dia remains limited. Recent approaches have attempted to bridge this gap by translating the hidden representations of token sequences into the embedding space of visual models or directly into raw image data. However, these methods often represent each image using multiple specialised to- kens which significantly increases the input length. This be- comes a major limitation for tasks such as graphic design generation where the ou

Read original source ↗ Open in workspace

recordType

paper

region

Global