构建微世界模拟基准与模型，让视频生成更真实还原微观生物过程。
MicroVerse: A Preliminary Exploration Toward a Micro-World Simulation
- 提出多层级评估框架MicroWorldBench，覆盖459项专家标注标准。
- 现有模型在微尺度上违反物理规律，时间不一致且偏离专家标准。
- 训练出专用于微尺度的MicroVerse模型，可准确生成复杂生物机制。
视频生成技术的进步为宏观动态系统仿真开辟了新路径，但其在微观现象中的应用仍处于探索阶段。微尺度模拟在药物发现、类器官芯片及疾病机制研究中潜力巨大，也适用于教育与交互可视化。本文提出MicroWorldBench——一个基于多层级评分体系的微尺度模拟评估基准，包含459项由专家标注的唯一评估标准，覆盖器官级过程、细胞动态和亚细胞分子互作等任务类型，以及科学真实性、视觉质量、指令遵循度等维度。评估发现当前最先进的视频生成模型在微尺度模拟中表现不佳，存在违反物理定律、时间不一致及与专家标准不符等问题。为此，我们构建了高质量、专家验证的MicroSim-10K模拟数据集，并在此基础上训练出专为微尺度设计的MicroVerse视频生成模型。该模型能准确复现复杂的微尺度生物机制。本工作首次提出‘微世界模拟’概念并展示其可行性，为生物、教育与科学可视化领域提供新范式。数据与代码已公开于https://github.com/FreedomIntelligence/MicroVerse。
原文摘要 · Abstract (English)
Recent advances in video generation have opened new avenues for macroscopic simulation of complex dynamic systems, but their application to microscopic phenomena remains largely unexplored. Microscale simulation holds great promise for biomedical applications such as drug discovery, organ-on-chip systems, and disease mechanism studies, while also showing potential in education and interactive visualization. In this work, we introduce MicroWorldBench, a multi-level rubric-based benchmark for microscale simulation tasks. MicroWorldBench enables systematic, rubric-based evaluation through 459 unique expert-annotated criteria spanning multiple microscale simulation task (e.g., organ-level processes, cellular dynamics, and subcellular molecular interactions) and evaluation dimensions (e.g., scientific fidelity, visual quality, instruction following). MicroWorldBench reveals that current SOTA video generation models fail in microscale simulation, showing violations of physical laws, temporal inconsistency, and misalignment with expert criteria. To address these limitations, we construct MicroSim-10K, a high-quality, expert-verified simulation dataset. Leveraging this dataset, we train MicroVerse, a video generation model tailored for microscale simulation. MicroVerse can accurately reproduce complex microscale mechanism. Our work first introduce the concept of Micro-World Simulation and present a proof of concept, paving the way for applications in biology, education, and scientific visualization. Our work demonstrates the potential of educational microscale simulations of biological mechanisms. Our data and code are publicly available at https://github.com/FreedomIntelligence/MicroVerse
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。