研究人员开发了一种新颖的方法，通过学习玻姆轨迹上的得分函数来求解含时薛定谔方程。该方法利用神经网络参数化得分函数，并最小化自洽的Fisher散度，有效地将实时量子动力学重塑为由得分驱动的归一化流。该框架已在波包分裂和非谐振动方面得到验证，有可能将量子力学与现代生成建模工具相结合。 AI
影响 将生成建模技术与量子动力学相结合，有望加速量子物理学研究。
排序理由 这是一篇研究论文，详细介绍了使用玻姆轨迹上的得分匹配求解含时薛定谔方程的新颖方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2604.25137v1 Announce Type: cross Abstract: We solve the time-dependent Schr\"odinger equation by learning the score function, the gradient of the log-probability density, on Bohmian trajectories. In Bohm's formulation of quantum mechanics, particles follow deterministic pa…
We solve the time-dependent Schrödinger equation by learning the score function, the gradient of the log-probability density, on Bohmian trajectories. In Bohm's formulation of quantum mechanics, particles follow deterministic paths under the classical potential supplemented by a …
We solve the time-dependent Schrödinger equation by learning the score function, the gradient of the log-probability density, on Bohmian trajectories. In Bohm's formulation of quantum mechanics, particles follow deterministic paths under the classical potential supplemented by a …