Research map / Large language models / AI and society
AutoGameUI: Constructing High-Fidelity GameUI via Multimodal Correspondence Matching
Zhongliang Tang, Qingrong Cheng, Mengchen Tan, Yongxiang Zhang, Fei Xia
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add geometry modality (ablation) | AutoGameUI · GAMEUI test | F1: 42.0 -> 88.1 | Improved |
| add semantics modality (ablation) | AutoGameUI · GAMEUI test | F1: 87.2 -> 88.1 | Improved |
| add textual content modality (ablation) | AutoGameUI · GAMEUI test | F1: 87.5 -> 88.1 | Improved |
| use GCA instead of vanilla cross-attention (ablation) | AutoGameUI · GAMEUI test | F1: 86.0 -> 88.1 | Improved |
| add rendering constraints (ablation) | AutoGameUI · GAMEUI test | PER: 0.63 -> 0.19 | Improved |
| add hierarchical constraints (ablation) | AutoGameUI · GAMEUI test | PER: 0.23 -> 0.19 | Improved |
| add hierarchical matching (top-down) (ablation) | AutoGameUI with regularization · GAMEUI test | time per GameUI: timeout >10s -> 1.83 s | Improved |
| add regularization on top of hierarchical matching | AutoGameUI · GAMEUI test | F1: 87.6 -> 88.1 | Improved |
| train stage 1 on GAMEUI instead of RICO | AutoGameUI stage 1 · GAMEUI test | F1: 83.2 -> 85.0 | Improved |
| add second-stage GCA model | AutoGameUI · GAMEUI test | F1: 85.0 -> 87.6 | Improved |
Closest papers by meaning
- The Undergraduate Games Corpus: A Dataset for Machine Perception of Interactive Media (AAAI 2021 · similarity 0.85)
- Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs (CVPR 2026 · similarity 0.84)
- GameDevBench: Evaluating Agentic Capabilities Through Game Development (ICML 2026 · similarity 0.83)
- UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction (ICML 2025 · similarity 0.83)
- CANVAS: A Benchmark for Vision-Language Models on Tool-Based User Interface Design (AAAI 2026 · similarity 0.82)
- EasyCraft: A Robust and Efficient Framework for Automatic Avatar Crafting (CVPR 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
