提出科学对齐新标准，揭示视觉模型在台风研究中依赖表面特征而非物理规律。
The Perception-Physics Paradox: Probing Scientific Alignment with TC-Bench
- 通过结构同构性要求表征唯一对应物理系统，构建可验证的科学对齐框架。
- 在TC-Bench数据集上发现现有模型在强风条件下性能骤降，暴露视觉捷径问题。
- 适合关注科学推理、因果可解释性的研究人员使用。
尽管视觉基础模型（VFMs）在卫星图像预测任务上表现优异，其性能可能源于视觉相关性而非底层结构不变性，导致仅凭感知的分布外准确率无法反映真实科学价值。我们称此现象为‘感知-物理悖论’。为此，提出将科学对齐作为科学领域表征学习的隐式目标。通过结构同构性——要求潜在表示在仿射重参数化下唯一识别物理系统——构建可验证的科学对齐原则，并形成系统化的探针协议以检验物理与因果可解释性。为实现该框架，我们发布了TC-Bench，一个全球性、可复现的热带气旋研究基准数据集，配备自动化构建流程。实验表明，当前的VFMs依赖视觉捷径，在强风环境下性能急剧下降，说明科学对齐并非规模扩增的自然产物。
原文摘要 · Abstract (English)
While Vision Foundation Models (VFMs) excel at predictive tasks on satellite imagery, their performance can arise from visual correlations rather than underlying structural invariants, making even perception-based out-of-distribution accuracy a poor proxy for scientific utility. As a result, models may look correct without reasoning correctly, a discrepancy we term the Perception-Physics Paradox. To address this gap, we introduce scientific alignment as an implicit objective for representation learning in scientific domains. We study a principled, testable aspect of scientific alignment through structural isomorphism, which requires latent representations to uniquely identify physical systems up to a linear reparameterization. This perspective induces a hierarchy of necessary conditions and yields a systematic probing protocol for physical and causal interpretability. To operationalize this framework, we release TC-Bench, a global, reproducible benchmark dataset with an automated construction pipeline for tropical cyclone research, and show that current VFMs rely on visual shortcuts that collapse in intense regimes, indicating that scientific alignment does not arise as a natural byproduct of scaling alone.
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。