UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation
Large language models (LLMs) have demonstrated growing competence in web page generation. However, existing text-driven approaches rely on complex prompts that impose substantial demands on users and offer limited expressivity for page layout and cross-page visual coherence. Image-driven paradigms, which take UI screenshots as input, align more closely with real development workflows. However, current benchmarks focus primarily on visual fidelity and lack a systematic evaluation of the interaction capabilities in generated artifacts. To address this gap, we introduce UI2App, the first benchmar
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorGrace Man Chen →
UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation
- Linked via arxiv authorLitao Guo →
UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation
- Linked via arxiv authorYifan Wu →
UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation
- Linked via arxiv authorYiyu Chen →
UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation
- Linked via arxiv authorYenchi Tseng →
UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation
- Linked via arxiv authorSicheng Liu →
UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation
- Linked via arxiv authorYuyu Luo →
UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation
- Linked via arxiv authorYing-Cong Chen →
UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation