AI Paper Atlas

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

AAAI 2026 · Large language models › AI and society · approach: Data commons and human baselines · 6 citations (OpenAlex)

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 changedWhereMeasuredEffect
add geometry modality (ablation)AutoGameUI · GAMEUI testF1: 42.0 -> 88.1Improved
add semantics modality (ablation)AutoGameUI · GAMEUI testF1: 87.2 -> 88.1Improved
add textual content modality (ablation)AutoGameUI · GAMEUI testF1: 87.5 -> 88.1Improved
use GCA instead of vanilla cross-attention (ablation)AutoGameUI · GAMEUI testF1: 86.0 -> 88.1Improved
add rendering constraints (ablation)AutoGameUI · GAMEUI testPER: 0.63 -> 0.19Improved
add hierarchical constraints (ablation)AutoGameUI · GAMEUI testPER: 0.23 -> 0.19Improved
add hierarchical matching (top-down) (ablation)AutoGameUI with regularization · GAMEUI testtime per GameUI: timeout >10s -> 1.83 sImproved
add regularization on top of hierarchical matchingAutoGameUI · GAMEUI testF1: 87.6 -> 88.1Improved
train stage 1 on GAMEUI instead of RICOAutoGameUI stage 1 · GAMEUI testF1: 83.2 -> 85.0Improved
add second-stage GCA modelAutoGameUI · GAMEUI testF1: 85.0 -> 87.6Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy