A Pathway to General-Purpose Scientific AI: Multimodal Comprehension of Scientific Images
Authors: 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
Organizations: Data Science and Digital Libraries, TIB Leibniz Information Centre for Science and Technology, Hannover, Germany · Department of Applied Physics and Science Education, Eindhoven University of Technology, Eindhoven, Netherlands · Department of Biology, Chemistry, and Pharmacy, Freie Universität Berlin, Berlin, Germany · HEJ Research Institute of Chemistry, International Center for Chemical and Biological Sciences, University of Karachi, Karachi, Pakistan · School of Interdisciplinary Engineering and Sciences, National University of Sciences and Technology, Islamabad, Pakistan · Department of Chemistry, University of Warwick, Coventry, United Kingdom · Department of Physics, PSG College of Technology, Coimbatore, Tamil Nadu, India · Department of Chemistry and Materials Science, Aalto University, Helsinki, Finland
Scientific figures and tables encode essential experimental evidence, yet remain difficult for digital libraries and multimodal AI systems to retrieve and interpret. The ALD/E-ImageMiner benchmark and ICDAR 2026 Competition on Information Extraction from Atomic Layer Deposition/Etching Scientific Figures provide 1,951 figures from 205 publications, expert-annotated for classification, data table extraction, summarization, and visual question answering. In these companion proceedings, we present a forward-looking perspective on how the benchmark can guide future scientific-image challenges. We examine how its tasks probe capabilities from visual and quantitative reading to domain-grounded reasoning and evidential justification, and how Bloom-informed question design can support deeper scientific understanding. We propose "scientific conceptual understanding from images" as a long-term benchmark objective, with future directions including broader domains and figure types, contextual and cross-document synthesis, hypothesis evaluation, provenance, uncertainty, counterfactual grounding, and open-ended multimodal research. This perspective connects the ICDAR 2026 challenge to a broader agenda for machine-actionable scientific visual knowledge and verifiable multimodal scientific AI.
Figures & tables
Figure 1: Reproduced from Figure 3 in Mattinen et al., Van der Waals epitaxy of continuous thin films of 2D materials using atomic layer deposition in low temperature and low vacuum conditions [ 20 ] . The ALD/E-ImageMiner classification annotations identify (a) a molecular structure diagram, (b) a polar chart (rose chart), (c–d) spectra charts, and (e) a stacked spectra chart. The figure also supports domain-grounded questions concerning epitaxial growth, crystallographic orientation, and disorder in PbI 2 films grown on sapphire.
Panel
x
y
Width
Height
(a)
15
55
597
392
(b)
623
40
508
436
(c)
17
493
374
286
(d)
393
488
363
290
(e)
778
492
360
286
Table 1: Panel-level bounding boxes for Figure 1 .