SpectrumWorld: Artificial Intelligence Foundation for Spectroscopy

作者：Zhuo Yang, Jiaqing Xie, Shuaike Shen, Daolang Wang, Yeyun Chen, Ben Gao, Shuzhou Sun, Biqing Qi, Dongzhan Zhou, Lei Bai, Linjiang Chen, Shufei Zhang, Qinying Gu, Jun Jiang, Tianfan Fu, Yuqiang Li · 年份：2026 · DOI：10.1145/3770855.3818936 · 研究领域：Artificial intelligence、Computer science、Data science、Engineering、Software engineering、Management science、Engineering ethics

Deep learning holds immense promise for spectroscopy, yet research and evaluation in this emerging field often lack standardized formulations. To address this issue, we introduce SpectrumWorld, a unified infrastructure for AI-driven spectroscopy. SpectrumWorld consists of SpectrumLab, a pioneering unified platform designed to systematize and accelerate deep learning research in spectroscopy; SpectrumAnnotator, an annotation and curation module that generates high-quality benchmarks from limited seed data; and SpectrumVQA, a multi-layered benchmark suite covering 14 spectroscopic tasks and over 10 spectrum types, featuring spectra curated from over 1.2 million distinct chemical substances. Thorough empirical studies on SpectrumVQA with 23 cutting-edge multimodal LLMs reveal critical limitations of current approaches. We hope SpectrumWorld will serve as a crucial foundation for future advancements in deep learning-driven spectroscopy. Code is released at https://github.com/InternScience/SpectrumLab.