Teaching Molecular Dynamics to a Non-Autoregressive Ionic Transport Predictor
将分子动力学教给一个非自回归的离子输运预测器
机构 * School of Mathematics and Computing (Computational Science and Engineering)(数学与计算学院(计算科学与工程)) ; Yonsei University(延世大学) ; Korea Institute of Science and Technology(韩国科学技术院) ; Nanoscience and Technology(纳米科学与技术)
AI总结 本文提出一种非自回归学习框架,通过辅助模态学习处理原子轨迹,实现快速准确的离子输运预测,比自回归模型快200倍且减少误差。
Comments International Conference on Machine Learning (ICML 2026) (to appear) (Please cite our conference version.)