arXiv:2509.12159v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models have demonstrated exceptional performance in UI2Code tasks, significantly enhancing website development efficiency. However, these tasks incur substantially higher computational overhead than traditional code generation due to the large number of input image tokens and extensive output code tokens required. Our comprehensive study identifies significant redundancies in both image and code tokens that exacerbate computational complexity and hinder focus on key UI elements, resulting in excessively lengthy
Source: arXiv cs.AI — read the full report at the original publisher.