QERNEL:一种可扩展的大型电子模型
QERNEL: a Scalable Large Electron Model
AI总结:
QERNEL通过结合FiLM参数条件和高效架构元素,以低计算成本提升表达能力,用于半导体莫尔异质双层中电子相互作用研究,发现量子液态与晶体态之间的突变相变。
摘要:
我们介绍了QERNEL,一种基础神经波函数,通过变分方法求解参数化多电子哈密顿量家族,并在参数空间内捕获其基态。QERNEL结合FiLM基于的参数条件与规模高效的架构元素——专家混合和分组查询注意力,显著提升了在低计算成本下的表达能力。我们将其应用于半导体莫尔异质双层中的相互作用电子,训练一个权重共享模型以处理最多150个电子的系统。通过求解受莫尔势深条件的多电子薛定谔方程,QERNEL捕获了量子液体和晶体态,并发现了两者之间的突变相变,表现为相互作用能量和电荷密度的突变变化。我们的工作为莫尔量子材料建立了基础模型,并为固体的大型电子模型提供了可扩展的架构。
英文摘要:
We introduce QERNEL, a foundational neural wavefunction that variationally solves families of parameterized many-electron Hamiltonians and captures their ground states throughout parameter space within a single model. QERNEL combines FiLM-based parameter conditioning with scale-efficient architectural elements -- mixture of experts and grouped-query attention, substantially improving expressivity at low computational cost. We apply QERNEL to interacting electrons in semiconductor moiré heterobilayers, training a single weight-shared model for systems of up to 150 electrons. By solving the many-electron Schrödinger equation conditioned on moiré potential depth, QERNEL captures both quantum liquid and crystal states and discovers the sharp phase transition between them, marked by abrupt changes in interaction energy and charge density. Our work establishes a foundation model for moiré quantum materials and a scalable architecture toward a Large Electron Model for solids.
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。