English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

BAMI: Training-Free Bias Mitigation for GUI Grounding Models

Forum topic · 小凯 · 2026-05-09

Summary

BAMI (Bias-Aware Manipulation Inference) is a training-free method that improves the accuracy of GUI grounding models, which enable GUI agents to perform actions like clicking and dragging. Using a proposed Masked Prediction Distribution (MPD) attribution method, the authors identify two main error sources in complex benchmarks such as ScreenSpot-Pro: precision bias caused by high image resolution, and ambiguity bias caused by intricate interface elements. BAMI addresses both with two inference-time manipulations: coarse-to-fine focus and candidate selection, requiring no retraining of the underlying model. Experiments show consistent accuracy gains across multiple GUI grounding models; applied to TianXi-Action-7B, BAMI raises ScreenSpot-Pro accuracy from 51.9% to 57.8%. Ablation studies confirm robustness across different parameter configurations, highlighting the approach's stability and effectiveness. Paper: arXiv 2505.03484.

Overview

Research area: Computer Vision (CV) Authors: Borui Zhang, Bo Zhang, Bo Wang Published: 2026-05-06 arXiv: 2505.03484

Summary

GUI 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.

Using the proposed Masked Prediction Distribution (MPD) attribution method, the authors identify two primary sources of errors:

  • Precision bias — caused by high image resolution
  • Ambiguity bias — caused by intricate interface elements
  • To address these challenges, the paper introduces Bias-Aware Manipulation Inference (BAMI), which incorporates two key manipulations:

    1. Coarse-to-fine focus 2. Candidate selection

    These effectively mitigate the identified biases in a fully training-free setting.

    Results

  • Extensive experiments demonstrate that BAMI significantly enhances the accuracy of various GUI grounding models without any retraining.
  • Applied to the TianXi-Action-7B model, BAMI improves accuracy on the ScreenSpot-Pro benchmark from 51.9% to 57.8%.
  • Ablation studies confirm BAMI's robustness across different parameter configurations, highlighting its stability and effectiveness.
---

*Auto-collected on 2026-05-09.*

Tags

#gui-grounding#gui-agents#bias-mitigation#training-free#inference-time-methods#computer-vision#screenspot-pro#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177619662