AI Paper Atlas

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

GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction

Hongxin Li, Yuntao Chen, Zhaoxiang Zhang

IJCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 1 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
apply coarse filtering to fine-tuning data (10.8M to 6.4M samples) (ablation)GoClick-L · Seven grounding benchmarks (average)accuracy: 71.6 -> 74.0Improved
apply fine filtering on top of coarse filtering (6.4M to 3.8M) (ablation)GoClick-L · Seven grounding benchmarks (average)accuracy: 74.0 -> 75.6Improved
remove outdated GUI pattern samples (ablation)GoClick-L · MOTIFaccuracy: 74.0 -> 76.8Improved
remove functionality referring-expression generation samples (ablation)GoClick-L · VWB EGaccuracy: 86.4 -> 90.2Improved
remove text REG samples (ablation)GoClick-L · FuncPredaccuracy: 62.2 -> 62.2No clear effect
remove brief description REG samples (ablation)GoClick-L · ScreenSpot-v2accuracy: 74.4 -> 74.0Hurt
use Florence-2 encoder-decoder instead of InternVL-2-1B decoder-only (ablation)GoClick-L · FuncPredaccuracy: 21.9 -> 69.5Improved
use Florence-2 encoder-decoder (0.8B) instead of Qwen2VL-2B decoder-only (ablation)GoClick-L · FuncPredaccuracy: 51.1 -> 69.5Improved
use Florence-2 0.8B instead of Qwen2VL-7B decoder-only (ablation)GoClick-L · FuncPredaccuracy: 56.1 -> 69.5Improved
use Florence-2 0.8B instead of Qwen2VL-7B decoder-only (ablation)GoClick-L · ScreenSpotaccuracy: 82.5 -> 78.5Hurt
scale GoClick from base (0.2B) to large (0.8B)GoClick-L · FuncPredaccuracy: 64.4 -> 69.5Improved
add GoClick grounding to Gemini-2-Flash-Exp plannerGemini-2-Flash-Exp planner · AITW overallStep SR: 29.5 -> 47.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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