AI Paper Atlas

Research map / 3D vision / 3D generation

MVP: Multiple View Prediction Improves GUI Grounding

Yunzhu Zhang, Zeyu Pan, Zhengwen Zeng, Shuheng Shen, Changhua Meng, Linchao Zhu

CVPR 2026 · 3D vision › 3D generation · approach: 2D-to-3D pretrained representations · 9 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 attention-guided views instead of border padding (ablation)MVP · ScreenSpot-Pro (GTA1-7B ablation, 4 views)accuracy (%): 57.3 -> 61.7Improved
add border padding multi-view inference over single image (ablation)MVP baseline · ScreenSpot-Pro (GTA1-7B ablation, 4 views)accuracy (%): 49.8 -> 57.3Improved
use clustering instead of averaging coordinates (ablation)MVP · ScreenSpot-Pro (GTA1-7B ablation, 4 views)accuracy (%): 46.6 -> 61.7Improved
use clustering instead of random selection (ablation)MVP · ScreenSpot-Pro (GTA1-7B ablation, 4 views)accuracy (%): 55.7 -> 61.7Improved
add 2x view resizing (ablation)MVP · ScreenSpot-Pro (GTA1-7B ablation, 4 views)accuracy (%): 59.1 -> 61.7Improved
use comma token as attention query instead of instruction tokens (ablation)MVP · ScreenSpot-Pro (GTA1-7B ablation, 4 views)accuracy (%): 60.5 -> 61.7Improved
use comma token instead of im_end token as query (ablation)MVP · ScreenSpot-Pro (GTA1-7B ablation, 4 views)accuracy (%): 33.3 -> 61.7Improved
increase number of views beyond 4 (ablation)MVP · ScreenSpot-Pro (GTA1-7B ablation, 4 views)accuracy (%)No clear effect
replace clustering with trained selector (GTA1-7B) (ablation)MVP · ScreenSpot-Pro (GTA1-7B ablation, 4 views)accuracy (%): 61.7 -> 62.8Mixed
replace clustering with trained selector (Qwen3VL-8B) (ablation)MVP · ScreenSpot-Pro (Qwen3VL-8B-Instruct, selector ablation)accuracy (%): 65.5 -> 65.3No clear effect
add MVP to UI-TARS-1.5-7BUI-TARS-1.5-7B · ScreenSpot-Proaccuracy (%): 41.9 -> 56.1Improved
add MVP to Qwen3VL-32B-InstructQwen3VL-32B-Instruct · ScreenSpot-Proaccuracy (%): 55.3 -> 74.0Improved

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