arXiv AI

From Terminology to Diagrams: Visual-Instruction Generation for Scientific Diagram Understanding

The paper introduces SciGram, a large-scale dataset of 194K scientific diagrams paired with 1.4M visual instructions generated through a terminology‑grounded pipeline that extracts domain concepts, synthesizes facts, and retrieves relevant diagrams. Models fine‑tuned on SciGram show significant gains on diagram‑centric benchmarks such as TQA, ScienceQA, and AI2D, and when combined with existing models like LLaVA OneVision, set new state‑of‑the‑art performance. The authors release both the dataset and trained models to support further research in scientific diagram understanding.

Hugging Face Trending Papers
Aug 13

Towards Physics-Faithful Generation of Scientific Diagrams

Text-to-image generation has reached photorealistic quality, yet state-of-the-art systems remain unreliable at producing scientific diagrams, whose value depends not on appearance but on physical faithfulness: correct force directions, valid coordinate systems, consistent thermodynamic states, and equations matching the depicted scenario. Trained on web imagery with physically shallow captions, generic models produce diagrams that look plausible but are physically wrong, harmful in education and scientific communication.

Hugging Face Trending Papers
Jun 29

SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation

While Text-to-Image (T2I) models have shown remarkable success in generating photorealistic visual content, they still struggle with the rigorous semantic alignment and logical reasoning required for scientific imagery. Inspired by Peirce's Semiotic Triad, we introduce Scientific Image Reasoning (SciIR), a comprehensive resource for training and evaluation of scientific image generation.

arXiv AI
Aug 24

MatMMExtract: An Open-Source Pipeline for Panel-Level Extraction of Grounded Image-Text Pairs from Materials Science Literature

MatMMExtract is an open‑source pipeline that disassembles compound scientific figures into individual sub‑panels and generates structured, grounded image‑text pairs using a large language model guided by a materials science taxonomy. Applied to 14,810 open‑access articles, it produced 391,606 panel‑level pairs with sub‑captions, a two‑level visualisation category (19 classes, 100+ subtypes), and scientific summaries. The project also introduces MaterialScope, a 2,811‑figure detection dataset, and demonstrates that Gemini 3.1 Flash Lite yields high‑quality annotations with low hallucination, while a dual‑encoder baseline outperforms zero‑shot CLIP on the resulting MatSciFig dataset.

By Subham Ghosh, Shubham Tiwari, Mohammad Ibrahim, Abhishek Tewari
arXiv AI
Aug 17

A Pathway to General-Purpose Scientific AI: Multimodal Comprehension of Scientific Images

arXiv:2608. 14075v1 Announce Type: new Abstract: Scientific figures and tables encode essential experimental evidence, yet remain difficult for digital libraries and multimodal AI systems to retrieve and interpret.

By Jennifer D'Souza, Fahad Ahmed, Cecilia Andrea Bustamante Andrade, Lina Frolova, Poorani Gnanasambandan, Dilshad Hussain, Muhammad Uzair Khan, Nkembeng Kevin Nkengfoa, Paul Praveen J., Fabio Priante, Sjoerd Franciscus van der Werf, Thomas Frederik Jan van Roeden
arXiv Computer Vision
3d ago

DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing

arXiv:2607.02290v2 Announce Type: replace Abstract: Recent image generation and editing models can produce visually appealing natural images, yet they remain unreliable when the target image is a kno...

By Zhaokai Wang, Mingxin Liu, Zirun Zhu, Ziqian Fan, Yiguo He, Mohan Zhang, Leyao Gu, Yan Li, Xiangyu Zhao, Ning Liao, Shaofeng Zhang, Xuanhe Zhou, Zhihang Zhong, Xue Yang
arXiv AI
2d ago

SCAFFOLD: A Large-Scale Structured Dataset of Computer Science Research Figures with Diagram QA and Chain-of-Thought Reasoning Traces

SCAFFOLD is a large-scale structured dataset of computer science research figures, each paired with captions, context, questions, answers, and chain-of-thought reasoning traces. It contains 157,387 figure–question pairs from 3,058 arXiv papers, with subsets of 36,797 and 12,000 pairs for medium and small-scale use. The dataset was created using layout detection, PDF parsing, and AI-assisted question generation, and was used to benchmark a vision‑language model (Qwen2.5‑VL‑3B‑Instruct).

By Ranjit Raut, Aarav Subedi, Sagun Rai, Sudan Jha
arXiv AI
Aug 5

CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded Reasoning

arXiv:2608. 02833v1 Announce Type: cross Abstract: Chart question answering (CQA) requires multimodal large language models (MLLMs) to integrate visual comprehension with logical reasoning, yet current models struggle with accurate visual grounding and coherent reasoning chains.

By Xuehang Guo, Pingyue Zhang, Ruiyi Zhang, Zhenhailong Wang, Hanrui Lyu, Heng Ji, Tong Sun, Qingyun Wang, Manling Li