AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams

Weihao Bo, Shan Zhang, Yanpeng Sun, Jie Liu, Yongke Yao, Jinhao Du, Wei He, KAI ZOU, Zechao Li, Jingdong Wang

ECCV 2026 · Vision-language and multimodal › Visual question answering · approach: Open-domain multimodal QA · 3 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
provide diagram objects as context for editing (ablation)all six agentic models · Diagram-MMU D2C-E miniF1avg preserve: gains 4.1-10.6Improved
provide diagram objects as context for editing (ablation)all six agentic models · Diagram-MMU D2C-E miniF1avg edit: gains 3.3-7.1Improved
provide diagram objects as context for parsing (ablation)Gemini-3.0 Pro, Qwen3-VL-8B · Diagram-MMU D2C-P miniF1avg: -2.0 and -6.1Hurt
provide diagram objects as context for parsing (ablation)Claude-4.6 Opus, Gemini-3.1 Pro · Diagram-MMU D2C-P miniCrystalBLEU: +0.3 and +1.4Improved
provide diagram objects as context for question answering (ablation)GPT-5.2 · Diagram-MMU DQA miniAccuracy: -7.3Hurt
add TikZ search tool for parsing (ablation)Gemini-3.1 Pro · Diagram-MMU D2C-P miniF1avg: -4.3Hurt
add TikZ search tool (ablation)Claude-4.6 Opus · Diagram-MMU D2C-P miniF1avg: +2.2Improved
generate TikZ code first, then edit (ablation)Claude-4.6 Opus, GPT-5.2 · Diagram-MMU D2C-E miniF1avg preserve/edit: +2.5/+2.6 and +2.5/+3.5Improved
generate TikZ code first, then answer (ablation)Claude-4.6 Opus · Diagram-MMU DQA miniAccuracy: +3.8Improved
generate TikZ code first, then answer (ablation)other models · Diagram-MMU DQA miniAccuracy: -1.3 to -3.2Hurt
plan tool use with objects for parsing (ablation)Claude-4.6 Opus · Diagram-MMU D2C-P miniF1avg/CBLEU: +5.1/+2.8Improved
plan tool use with objects for parsing (ablation)Gemini-3.1 Pro, Qwen3-VL-8B · Diagram-MMU D2C-P miniF1avg/CBLEU: -5.0/-4.5 and -5.6/-6.4Hurt

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