这篇论文展示了生成模型能从原始对撞数据中自动学习标准模型的结构，不需要模拟样本，连共振峰和质量都能自己学到。
ShellFlow是一个基于Transformer的生成模型，在5个数量级的不变质量范围（亚GeV到TeV）上学会了标准模型结构。它使用黎曼条件流匹配，在每个粒子的壳流形上生成，训练数据来自ATLAS Open Data的约10^9个真实pp对撞事件。模型仅用壳条件和不变质量公式作为物理先验，即学习到了双轻子共振（J/ψ、Υ、Z）在PDG位置、轻子Weinberg角、W和顶夸克质量，以及粒子间相关性。
Learning Standard Model structure from LHC data with Riemannian flow matching
In this work we demonstrate that a single transformer-based generative model can capture Standard Model structure spanning five decades of invariant mass, from the sub-GeV regime to the TeV continuum, a range that no single Monte Carlo sample covers. To achieve this we design \textsc{ShellFlow}, a Riemannian conditional flow matching model that, given the recorded event composition, generates each particle on its on-shell manifold. Its only physics priors are the on-shell condition and the invariant-mass formula. The model is trained on $\sim 10^{9}$ real $pp$ collision events from the ATLAS Open Data 13~TeV release and told nothing else. From a single training run, the model learns to reproduce all of the following: intra-particle kinematics, the dilepton resonances ($J/ψ$, $Υ$, $Z$) at their PDG positions, the leptonic Weinberg angle, the $W$ and top-quark masses, and inter-particle correlations that enter no training objective. A substantial fraction of the Standard Model is thus learnable directly from recorded collision data.