SciForma: Structure-Faithful Generation of Scientific Diagrams
Structural fidelity is essential to scientific methodology diagrams. To communicate research logic, these diagrams must faithfully render components, directional relations, and textual annotations. Since a single error, such as a reversed arrow or an unreadable equation, can invalidate the entire figure, structural fidelity is inherently conjunctive: correctness on one axis cannot compensate for failure on another. Current open-source models fail to satisfy this criterion. Supervised fine-tuning (SFT) learns plausible layouts but cannot reliably ensure structural correctness, while scalar rewa
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.
- PossiblePossibly related (embedding) · 45%EY re-envisions RAG around multimodal knowledge graphs to improve accuracy - SiliconANGLE →
- FuzzyOverlapping authors or contributors · 62%mudler/LocalAI →
“Shared author/contributor keys: guo”
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: luo”
- LinkedLinked via arxiv author · 85%Yuxuan Luo →
“SciForma: Structure-Faithful Generation of Scientific Diagrams”
- LinkedLinked via arxiv author · 85%Kaipeng Zhang →
“SciForma: Structure-Faithful Generation of Scientific Diagrams”
- LinkedLinked via arxiv author · 85%Xinjie Zhang →
“SciForma: Structure-Faithful Generation of Scientific Diagrams”
- LinkedLinked via arxiv author · 85%Xun Guo →
“SciForma: Structure-Faithful Generation of Scientific Diagrams”
- LinkedLinked via arxiv author · 85%Zhouhui Lian →
“SciForma: Structure-Faithful Generation of Scientific Diagrams”