SciForma: Structure-Faithful Generation of Scientific Diagrams

Hugging Face Daily Papers Papers
scientific-diagrams structural-fidelity preference-optimization open-source generation evaluation

Summary

Introduces SciForma, a framework for generating scientific methodology diagrams with high structural fidelity, using multi-dimensional conjunctive preference optimization (M-DPO) and a structural inventory to ensure correctness across component, arrow, and text axes. The 9B model surpasses open-source baselines and GPT-Image-1.5 on benchmark evaluations.

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 reward-based post-training obscures which structural dimension has failed. To address this, we introduce SciForma, a framework for the structure faithful generation of scientific methodology diagrams. Specifically, SciForma decomposes diagram quality into three structural axes: Component, Arrow, and Text, guided by a structural inventory. Built on this foundation, we curate SciFormaData-700K for structured training and SciFormaBench-2K for logic-verified evaluation. To close the gap left by SFT, we develop Multi-Dimensional Conjunctive Preference Optimization (M-DPO), which enforces simultaneous correctness across all axes and adaptively routes gradients to the most deficient dimension in post-training. The same structural inventory also enables iterative editing at inference time to correct residual errors. This combination allows SciForma-9B to exceed all open-source baselines and GPT-Image-1.5 on both SciFormaBench-2K and AIBench, bringing open scientific diagram generation close to proprietary-level structural fidelity. Our code and data will be available at: https://github.com/microsoft/SciForma.
Original Article
View Cached Full Text

Cached at: 07/22/26, 06:41 AM

Paper page - SciForma: Structure-Faithful Generation of Scientific Diagrams

Source: https://huggingface.co/papers/2607.18091

Abstract

Structuralfidelityisessentialtoscientificmethodologydiagrams.Tocommunicateresearchlogic,thesediagramsmustfaithfullyrendercomponents,directionalrelations,andtextualannotations.Sinceasingleerror,suchasareversedarroworanunreadableequation,caninvalidatetheentirefigure,structuralfidelityisinherentlyconjunctive:correctnessononeaxiscannotcompensateforfailureonanother.Currentopen-sourcemodelsfailtosatisfythiscriterion.Supervisedfine-tuning(SFT)learnsplausiblelayoutsbutcannotreliablyensurestructuralcorrectness,whilescalarreward-basedpost-trainingobscureswhichstructuraldimensionhasfailed.Toaddressthis,weintroduceSciForma,aframeworkforthestructurefaithfulgenerationofscientificmethodologydiagrams.Specifically,SciFormadecomposesdiagramqualityintothreestructuralaxes:Component,Arrow,andText,guidedbyastructuralinventory.Builtonthisfoundation,wecurateSciFormaData-700KforstructuredtrainingandSciFormaBench-2Kforlogic-verifiedevaluation.ToclosethegapleftbySFT,wedevelopMulti-DimensionalConjunctivePreferenceOptimization(M-DPO),whichenforcessimultaneouscorrectnessacrossallaxesandadaptivelyroutesgradientstothemostdeficientdimensioninpost-training.Thesamestructuralinventoryalsoenablesiterativeeditingatinferencetimetocorrectresidualerrors.ThiscombinationallowsSciForma-9Btoexceedallopen-sourcebaselinesandGPT-Image-1.5onbothSciFormaBench-2KandAIBench,bringingopenscientificdiagramgenerationclosetoproprietary-levelstructuralfidelity.Ourcodeanddatawillbeavailableat:https://github.com/microsoft/SciForma.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2607\.18091

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.18091 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.18091 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.18091 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

PhyDrawGen: Physically Grounded Diagram Generation from Natural Language

arXiv cs.AI

PhyDrawGen is a neuro-symbolic pipeline that generates physically accurate diagrams from natural language by combining LLM-based scene understanding with a deterministic constraint solver and a VLM-based verify loop, outperforming existing models on a benchmark of physics problems.