AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Visual Test-time Scaling for GUI Agent Grounding

Tiange Luo, Lajanugen Logeswaran, Justin Johnson, Honglak Lee

ICCV 2025 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 23 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 RegionFocus to UI-TARS-72BUI-TARS-72B · ScreenSpot-Proaverage accuracy: 38.1 -> 50.2Improved
add RegionFocus to Qwen2.5-VL-72BQwen2.5-VL-72B · ScreenSpot-Proaverage accuracy: 47.8 -> 61.6Improved
add RegionFocus to UI-TARS-7BUI-TARS-7B · ScreenSpot-Proaverage accuracy: 35.7 -> 41.2Improved
add RegionFocus to Qwen2.5-VL-7BQwen2.5-VL-7B · ScreenSpot-Proaverage accuracy: 26.8 -> 32.1Improved
add RegionFocus to UI-TARS-72BUI-TARS-72B · WebVoyageroverall success rate: 44.1% -> 59.5%Improved
add RegionFocus to Qwen2.5-VL-72BQwen2.5-VL-72B · WebVoyageroverall success rate: 42.4% -> 52.7%Improved
add RegionFocus to UI-TARS-7BUI-TARS-7B · WebVoyageroverall success rate: 33.2% -> 44.7%Improved
add RegionFocus to Qwen2.5-VL-7BQwen2.5-VL-7B · WebVoyageroverall success rate: 32.5% -> 41.1%Improved
add RegionFocus to Qwen2.5-VL-7B on individual sitesQwen2.5-VL-7B · WebVoyager (Google Map)success rate: 30.2% -> 17.1%Hurt
use image-as-map instead of text-as-history for region history and aggregation (ablation)RegionFocus (UI-TARS-7B-DPO) · WebVoyager subsetsuccess rate: 37.2 -> 43.2Improved
derive fixed bounding boxes from predicted focal point instead of predicting regions directly (ablation)RegionFocus (UI-TARS-7B-DPO) · WebVoyager subsetsuccess rate: 28.1 -> 43.2Improved
replace fixed boxes with SAM-generated boxes (ablation)RegionFocus (UI-TARS-7B-DPO) · WebVoyager subsetsuccess rate: 43.2 -> 46.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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