English

RWKV-UI: UI Understanding with Enhanced Perception and Reasoning

Computer Vision and Pattern Recognition 2025-02-07 v1 Human-Computer Interaction

Abstract

Existing Visual Language Modelsoften struggle with information loss and limited reasoning abilities when handling high-resolution web interfaces that combine complex visual, textual, and interactive elements. These challenges are particularly evident in tasks requiring webpage layout comprehension and multi-step interactive reasoning. To address these challenges, we propose RWKV-UI, a Visual Language Model based on the RWKV architecture, specifically designed to handle high-resolution UI images. During model training, we introduce layout detection as a visual prompt to help the model better understand the webpage layout structures. Additionally, we design a visual prompt based on the Chain-of-Thought(CoT) mechanism, which enhances the model's ability to understand and reason about webpage content through reasoning chains. Experimental results show that RWKV-UI demonstrates significant performance improvements in high-resolution UI understanding and interactive reasoning tasks.

Keywords

Cite

@article{arxiv.2502.03971,
  title  = {RWKV-UI: UI Understanding with Enhanced Perception and Reasoning},
  author = {Jiaxi Yang and Haowen Hou},
  journal= {arXiv preprint arXiv:2502.03971},
  year   = {2025}
}

Comments

10 pages, 5figures, conference

R2 v1 2026-06-28T21:34:38.956Z