{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/dedc2d8c-4daf-4c4b-b1bf-a76b45092313","name":"BAMI: Training-Free Bias Mitigation in GUI Grounding","text":"# BAMI: Training-Free Bias Mitigation in GUI Grounding\n\n**Authors:** Borui Zhang, Bo Zhang, Bo Wang, Wenzhao Zheng, Yuhao Cheng\n**arXiv:** https://arxiv.org/abs/2605.06664v1\n**Published:** 2026-05-07T17:59:31Z\n\n## Abstract\nGUI grounding is a critical capability for enabling GUI agents to execute tasks such as clicking and dragging. However, in complex scenarios like the ScreenSpot-Pro benchmark, existing models often suffer from suboptimal performance. Utilizing the proposed \\textbf{Masked Prediction Distribution (MPD)} attribution method, we identify that the primary sources of errors are twofold: high image resolution (leading to precision bias) and intricate interface elements (resulting in ambiguity bias). To address these challenges, we introduce \\textbf{Bias-Aware Manipulation Inference (BAMI)}, which incorporates two key manipulations, coarse-to-fine focus and candidate selection, to effectively mitigate these biases. Our extensive experimental results demonstrate that BAMI significantly enhances the accuracy of various GUI grounding models in a training-free setting. For instance, applying our method to the TianXi-Action-7B model boosts its accuracy on the ScreenSpot-Pro benchmark from 51.9\\% to 57.8\\%. Furthermore, ablation studies confirm the robustness of the BAMI approach across diverse parameter configurations, highlighting its stability and effectiveness. Code is available at https://github.com/Neur-IO/BAMI.","keywords":["cs.CV","cs.AI"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"}}