Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ
Although multimodal large language models (MLLMs) have shown substantial potential in visual understanding and graphic code generation, editing scientific figures through code presents a greater challenge: a model must jointly recover visual structure, ground the requested change, generate compilable code, and preserve all unrelated content. While existing TikZ benchmarks mainly focus on figure reconstruction and generation, few systematically evaluate instruction-guided scientific figure editing with compilable code. We introduce Edit2TikZ, a comprehensive benchmark for scientific figure edit
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: zhou”
- FuzzyOverlapping authors or contributors · 62%mlflow/mlflow →
“Shared author/contributor keys: ruan”
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzySimilar title/name (fuzzy) · 59%jeinlee1991/chinese-llm-benchmark →
“Fuzzy title match (0.73): “Edit2TikZ: A Comprehensive and Challenging Benchmark for Sci” ≈ “jeinlee1991/chinese-llm-benchmark””
- LinkedLinked via arxiv author · 85%Zongyun Zhang →
“Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ”
- LinkedLinked via arxiv author · 85%Jiacheng Ruan →
“Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ”
- LinkedLinked via arxiv author · 85%Xian Gao →
“Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ”
- LinkedLinked via arxiv author · 85%Ruizhu Zhou →
“Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ”