arXiv 2512.108672025-12-12cs.CV

从宏观到微观：通过视觉-语言模型在分子上基准测试微观空间智能

From Macro to Micro: Benchmarking Microscopic Spatial Intelligence on Molecules via Vision-Language Models

Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学北京校区人工智能学院）；Beijing Key Laboratory of Research on Large Models and Intelligent Governance（北京大型模型与智能治理研究重点实验室）；Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE（下一代智能搜索与推荐工程研究中心）；Dept. of Comp. Sci. & Tech., Tsinghua University（清华大学计算机科学与技术系）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）；SKL-ESPC & SEPKL-AERM, College of Environmental Sciences and Engineering, Peking University（环境科学与工程学院，北京大学）；MAIS, Institute of Automation, Chinese Academy of Sciences（自动化研究所，中国科学院）；DAMO Academy, Alibaba Group, Hangzhou, China（阿里巴巴集团 DAMO Academy，中国杭州）；Hupan Lab, Hangzhou, China（杭州实验室）

Zongzhao Li, Xiangzhe Kong, Jiahui Su, Zongyang Ma, Mingze Li, Songyou Li, Yuelin Zhang, Yu Rong, Tingyang Xu, Deli Zhao, Wenbing Huang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出MiSI-Bench基准测试框架，评估视觉-语言模型在分子微观空间智能任务中的表现，发现微调模型在空间转换任务上超越人类，但需整合领域知识以推动科学AGI发展。

摘要：

本文引入了微观空间智能（MiSI）的概念，即感知和推理关于不可见微观实体的空间关系的能力，这是科学发现的基础。为了评估视觉-语言模型（VLMs）在此领域的潜力，我们提出了一个系统性的基准框架MiSI-Bench。该框架包含超过163,000个问题-答案对和587,000张图像，源自约4,000种分子结构，涵盖九个互补任务，评估能力从基本的空间转换到复杂的相互关系识别。实验结果表明，当前最先进的VLMs在该基准上显著低于人类水平。然而，经过微调的7B模型表现出显著潜力，即使在空间转换任务上超越人类，而其在科学基础任务如氢键识别上的表现不佳，凸显了整合显式领域知识以实现科学AGI的必要性。数据集可在https://huggingface.co/datasets/zongzhao/MiSI-bench获取。

英文摘要：

This paper introduces the concept of Microscopic Spatial Intelligence (MiSI), the capability to perceive and reason about the spatial relationships of invisible microscopic entities, which is fundamental to scientific discovery. To assess the potential of Vision-Language Models (VLMs) in this domain, we propose a systematic benchmark framework MiSI-Bench. This framework features over 163,000 question-answer pairs and 587,000 images derived from approximately 4,000 molecular structures, covering nine complementary tasks that evaluate abilities ranging from elementary spatial transformations to complex relational identifications. Experimental results reveal that current state-of-the-art VLMs perform significantly below human level on this benchmark. However, a fine-tuned 7B model demonstrates substantial potential, even surpassing humans in spatial transformation tasks, while its poor performance in scientifically-grounded tasks like hydrogen bond recognition underscores the necessity of integrating explicit domain knowledge for progress toward scientific AGI. The datasets are available at https://huggingface.co/datasets/zongzhao/MiSI-bench.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。