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

2026-07-29

AI Summary

This work addresses the challenge of extracting critical structured information from scientific images in atomic layer deposition and etching (ALD/E) research, which is often inaccessible through text alone. To this end, we introduce Sci-ImageMiner—the first multi-task benchmark specifically designed for ALD/E scientific image understanding—encompassing four end-to-end tasks: image classification, captioning, data extraction, and visual question answering. Built upon expert annotations and validated through a community challenge that attracted 68 participating teams submitting 1,263 results, the benchmark reveals that while state-of-the-art multimodal models perform well on classification and captioning, they exhibit significant limitations in data extraction and scientific reasoning. These findings underscore the necessity of integrating visual perception with domain-specific knowledge to advance scientific image understanding.

Abstract

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 publication. The Sci-ImageMiner benchmark dataset, accompanied by a community-driven competition, raises the bar over prior scientific competitions by curating a comprehensive, expert-annotated dataset across four end-to-end complementary tasks. The competition attracted 68 active participants and 1,263 public/private submissions from 9th January 2026 to 8th April 2026. Our results show that state-of-the-art multimodal models perform well on classification and summarization tasks but struggle with data extraction and scientific reasoning, particularly in visual question-answering. These findings reveal key limitations and highlight challenges and opportunities for improving domain-aware multimodal AI systems. Overall, the Sci-ImageMiner benchmark and competition establish a rigorous platform for advancing research in scientific figure comprehension and reasoning and demonstrate the potential of state-of-the-art approaches for a challenging and complex research area.

Problem

• scientific figure comprehension
• information extraction
• multimodal AI
• visual question answering
• domain-specific reasoning

Innovation

• multimodal AI
• scientific figure comprehension
• domain-specific reasoning
• benchmark dataset
• visual question answering