paper-with-me

Papers

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

2026-08-14 · 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

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.

📄 PDF Abstract BibTeX arXiv:2608.14075

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Question AnsweringInformation Extraction

Similar Papers 제목 키워드 기반

SciMDR: Advancing Scientific Multimodal Document Reasoning

2026-03-12 · Ziyu Chen, Yilun Zhao, Chengye Wang, Rilyn Han 외 arxiv

Constructing scientific multimodal document reasoning datasets for foundation model training involves an inherent trade-off among scale, faithfulness, and realism. To address this challenge, we introduce the synthesize-a…

ICDAR 2026 Competition on Information Extraction from Atomic Layer Deposition/Etching (ALD/E) Scientific Figures

2026-07-29 · Fahad Ahmed, Sören Auer, Jennifer D'Souza arxiv

Scientific figure comprehension and reasoning using multimodal AI requires integrating visual perception with domain-specific reasoning to extract meaningful knowledge, often not presented in the text of a research publi…

Information Extraction

Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models

2024-03-01 · Lei LI, Yuqi Wang, Runxin Xu, Peiyi Wang 외

Large vision-language models (LVLMs) excel across diverse tasks involving concrete images from natural scenes. However, their ability to interpret abstract figures, such as geometry shapes and scientific plots, remains l…

BenchmarkingMathematical ReasoningQuestion Answering

SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification

2025-06-18 · Chengye Wang, Yifei Shen, Zexi Kuang, Arman Cohan 외

We introduce SciVer, the first benchmark specifically designed to evaluate the ability of foundation models to verify claims within a multimodal scientific context. SciVer consists of 3,000 expert-annotated examples over…

Claim VerificationRAGRetrieval-augmented Generation

SciTS: Scientific Time Series Understanding and Generation with LLMs

2025-09-26 · Wen Wu, Ziyang Zhang, Liwei Liu, Xuenan Xu 외 arxiv

The scientific reasoning ability of large language models (LLMs) has recently attracted significant attention. Time series, as a fundamental modality in scientific data, presents unique challenges that are often overlook…