VIALS: A Benchmark for Visual Interpretation of Artifacts in the Life Sciences
2026-08-21 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors created VIALS, a test with 161 questions about various scientific images used by life scientists, like microscope pictures and gel blots. They found that current advanced AI models struggle to understand these specialized images, even though they can describe everyday photos well. Scientists who know the field find these tasks easy, showing that AI still lacks the domain knowledge and reasoning abilities needed for professional science work. This means AI tools won't be very helpful in real science labs until they can interpret these images correctly.
visual question-answeringgel blotsmicroscopy imagesplasmid mapsflow cytometry plotsvision-language modelsdomain knowledgevisual reasoningbiotech workflowsscientific image interpretation
Authors
Elaine Lau, Thanuka Udumulla, Lee Izhaki-Tavor, Francisco Guzmán, Nicholas Magazine, Jonas Mueller
Abstract
In professional life sciences workflows, scientists routinely interpret visual artifacts (gel blots, microscopy images, plasmid maps, flow cytometry plots, molecular structures, ...) to inform research decisions. We introduce VIALS, a visual question-answering benchmark with 161 such interpretation tasks, spanning the types of artifacts examined throughout experimental workflows in the biotech industry (rather than polished figures from publications and textbooks). While frontier vision-language models can now fluently describe natural images, we find that they are unable to accurately interpret these scientific images, reflecting limitations in domain knowledge and domain-specific visual reasoning capabilities. In contrast, scientists with relevant domain expertise find these visual interpretation tasks straightforward. AI that cannot similarly interpret such images will have limited utility in professional life sciences workflows, where such artifacts are central to how scientists reason, communicate, and make decisions.