SciDiagBench is a new benchmark designed to evaluate scientific diagram generation in a way that mirrors human peer‑review practices. It provides a dataset of 165 diagrams from 10 domains, systematically classified into 11 distinct types such as graphical abstracts and technical roadmaps. The benchmark also introduces a preference‑guided calibration method that incorporates human preferences into type‑specific evaluation criteria, aiming to improve the reliability of automated assessments.
arXiv:2603. 29139v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have enabled agentic systems to translate natural-language intent into executable scientific visualization (SciVis) tasks.
SciFigBench is a new benchmark for evaluating Vision Language Models on scientific method figure understanding. It focuses on three fine‑grained capabilities—dense content perception, visual relation comprehension, and information‑flow tracing—using 4,352 curated figures and 40,670 QA pairs. The authors also introduce SciFigCue, a training‑free visual prompting module that improves performance on several tasks without updating model parameters.
arXiv:2606. 28406v1 Announce Type: new Abstract: Text-to-image and multimodal generative models are increasingly used to produce scientific figures such as mechanism diagrams, experimental-design schematics, conceptual frameworks, and graphical abstracts.
Structural fidelity is essential to scientific methodology diagrams. To communicate research logic, these diagrams must faithfully render components, directional relations, and textual annotations.
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.
arXiv:2607. 18091v1 Announce Type: cross Abstract: Structural fidelity is essential to scientific methodology diagrams.
arXiv:2607. 27084v1 Announce Type: cross Abstract: Scientific images are the core elements of presenting experimental conclusions, elaborating system architecture, and supporting comparative arguments in scientific papers.
PaperBanana-Interact is a multi-agent system designed to refine scientific diagrams through multi-turn human feedback. The authors introduce MTPaperBananaBench, a benchmark with 292 images and 3,518 user requirements, and a user simulator that generates natural language feedback at each turn. Experiments show that PaperBanana-Interact consistently improves diagram quality, outperforming baseline systems by 11.9–18.6 points and reducing forgetting by 3.7–6.2 points.
Scientific images are the core elements of presenting experimental conclusions, elaborating system architecture, and supporting comparative arguments in scientific papers. However, existing image quality assessment (IQA) methods are predominantly designed for natural photographs or AI-generated content, which cannot be directly applied to scientific papers.
arXiv:2601. 04390v2 Announce Type: replace Abstract: High-quality methodology figures are central to scientific communication, yet they remain difficult and time-consuming to create.
arXiv:2607. 15272v1 Announce Type: cross Abstract: Editing the figures in a research paper is a routine and time-consuming part of everyday research practice: authors relabel components, rearrange panels, and restyle visuals as they revise their manuscripts.
arXiv:2608. 09873v1 Announce Type: cross Abstract: We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains.