AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

VisionMath: Vision-Form Mathematical Problem-Solving

Zongyang Ma, Yuxin Chen, Ziqi Zhang, Zhongang Qi, Chunfeng Yuan, Shaojie Zhu, Chengxiang Zhuo, Bing Li, Ye Liu, Zang Li, Ying Shan, Weiming Hu

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 0 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 the mathematical OCR stage (ablation)VisionMath · Vision-MathVerse overallaccuracy (%): 37.5 -> 41.1Improved
add the mathematical OCR stage (ablation)VisionMath · VisionMath-Bench Plane Geometryaccuracy (%): 37.2 -> 39.0Improved
add the mathematical OCR stage (ablation)VisionMath · VisionMath-Bench Algebraaccuracy (%): 31.3 -> 34.3Improved
add figure captioning in stage 2 (ablation)VisionMath · Vision-MathVerse overallaccuracy (%): 36.7 -> 38.2Improved
add mathematical educational video learning in stage 2 (ablation)VisionMath · Vision-MathVerse overallaccuracy (%): 36.7 -> 39.8Improved
combine figure captioning and educational video learning (ablation)VisionMath · Vision-MathVerse overallaccuracy (%): 39.8 -> 41.1Improved
add figure captioning in stage 2 (ablation)VisionMath · VisionMath-Bench Plane Geometryaccuracy (%): 37.0 -> 38.0Improved
add educational video learning (ablation)VisionMath · VisionMath-Bench Solid Geometryaccuracy (%): 32.2 -> 34.6Improved
add Chinese vision-form data to English-only tuning (ablation)VisionMath · VisionMath-Bench Plane Geometryaccuracy (%): 24.0 -> 39.0Improved
add English vision-form data to Chinese-only tuning (ablation)VisionMath · Vision-MathVerse overallaccuracy (%): 26.1 -> 41.1Improved
add English data to Chinese-only tuning (ablation)VisionMath · VisionMath-Bench Plane Geometryaccuracy (%): 38.2 -> 39.0Mixed
add Chinese data to English-only tuning (ablation)VisionMath · Vision-MathVerse overallaccuracy (%): 39.2 -> 41.1Improved

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