一作ACL 2026Poster· Natural Language Processing
Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding
Wenkai Wang · Xiyun Li · Hongcan Guo · Wenhao Yu · Tianqing Fang · Haitao Mi · Dong Yu · Shengyu Zhang
摘要
Graphical User Interface (GUI) grounding requires mapping natural language instructions to precise pixel coordinates. However, due to visually homogeneous elements and dense layouts, models typically grasp semantic intent yet fail to achieve precise localization. While scaling sampling attempts (...