molecular-simulation

论文提出 Magnolia，一个面向计算化学的持久记忆 AI 智能体框架，采用三层记忆系统（会话、项目、跨项目规则），整合对接、分子动力学与量子化学计算流程；在四个案例中验证了记忆机制显著提升任务检查通过率。

NEMORA 是一种将 Fast Multipole Method 推广为可学习等变算子的新方法，用于在等变图神经网络中建模长程原子间相互作用，具备线性时间与内存复杂度，可处理数十万原子体系，并在长程基准测试上将力和能量误差降低一个至三个数量级。

This article describes the automated optimization of the MBX molecular simulation program using compiler vectorization and parallel computation to enhance performance through SIMD instructions.

This paper introduces Equivariant Sheaf Neural Networks (ESNN), which learn directed geometric transport on graphs to enhance equivariant message passing for physical systems while preserving exact Euclidean symmetry.