English(EN) Physics-Aligned Electronic Ground-State Learning Improves Generalization

新的物理对齐方法提高了MLIP的泛化能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-08 04:00

研究人员开发了新的方法，即正交归一损失（OrthoNormal-Loss, ON-Loss）和格拉斯曼受限占据轨道训练（Grassmann Restricted Occupied-Orbital Training, GROOT），以提高机器学习原子间势（MLIPs）的泛化能力。这些技术通过强制执行物理约束，使学习目标与Kohn-Sham密度泛函理论（KS-DFT）保持一致。在实验中，这些方法显著降低了能量和力的平均绝对误差，优于先前最先进的密度GSM，并证明了在反应化学任务中的有效性。 AI

影响提高了MLIP在药物和材料开发中的泛化能力。

排序理由研究论文，详细介绍了机器学习原子间势的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 7 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍了机器学习原子间势的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Eike S. Eberhard, Xaver Kainz, Viktor Kotsev, Abdulrahman Aldossary, Stephan G\"unnemann · 2026-10-08 04:00

物理对齐电子基态学习提升泛化能力

arXiv:2610.10298v1 Announce Type: new Abstract: Machine-learned interatomic potentials (MLIPs) excel at in-distribution tasks, accelerating drug and material development, yet they struggle to generalize out-of-distribution. We propose to push the cost-accuracy Pareto frontier by …

本文如何被排名

报道来源 [1]

物理对齐电子基态学习提升泛化能力

相关实体

相关话题