arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

California Institute of Technology(加州理工学院)

2026-04-21 至 2026-04-21 共收录 4
2512.06987 2026-04-21 cs.LG cond-mat.mtrl-sci

OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction

OXtal:一种用于有机晶体结构预测的全原子扩散模型

Emily Jin, Andrei Cristian Nica, Mikhail Galkin, Jarrid Rector-Brooks, Kin Long Kelvin Lee, Santiago Miret, Frances H. Arnold, Michael Bronstein, Avishek Joey Bose, Alexander Tong, Cheng-Hao Liu

机构 * University of Oxford(牛津大学) Synteny Google(谷歌) Mila Université de Montréal(蒙特利尔大学) Caltech(加州理工学院) NVIDIA(英伟达) Lila AITHYRA FutureHouse Imperial College London(伦敦帝国学院)

AI总结 OXtal通过全原子扩散模型直接学习分子构象与周期性排列的联合分布,利用数据增强策略提升效率,实现对晶体结构的高精度预测,显著优于传统方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.17156 2026-04-21 cs.LG physics.comp-ph

Uncertainty Quantification in PINNs for Turbulent Flows: Bayesian Inference and Repulsive Ensembles

PINNs在湍流中的不确定性量化:贝叶斯推断与斥力集合

Khemraj Shukla, Zongren Zou, Theo Kaeufer, Michael Triantafyllou, George Em Karniadakis

机构 * Division of Applied Mathematics, Brown University(布朗大学应用数学系) Department of Computing and Mathematical Sciences, California Institute of Technology(加州理工学院计算与数学科学系) Department of Mechanical Engineering, Massachusetts Institute of Technology(麻省理工学院机械工程系)

AI总结 本文提出了一种概率扩展的PINN框架,结合贝叶斯方法、麦克斯韦-玻尔兹曼抽样和斥力深度集合,以提高湍流建模中的不确定性校准,通过Van der Pol振荡器和圆柱绕流测试案例验证了其有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.01015 2026-04-21 cs.LG math.DS math.FA

Upper Approximation Bounds for Neural Oscillators

神经振荡器的上近似界限

Zifeng Huang, Konstantin M. Zuev, Yong Xia, Michael Beer

机构 * organization= Institute for Risk Reliability, Leibniz University Hannover , addressline= Callinstraße 34 , city= Hannover , postcode= 30167 , country= Germany organization= Department of Civil Environmental Engineering, The Hong Kong Polytechnic University , addressline= Kowloon , city= Hong Kong , country= China organization= Department of Computing Mathematical Sciences, California Institute of Technology , city= Pasadena , state= California , country= United States organization= Guangdong-Hong Kong Joint Research Laboratory for Marine Infrastructure, The Hong Kong Polytechnic University , addressline= Kowloon , city= Hong Kong , country= China Environmental Engineering, University of Liverpool , city= Liverpool , postcode= L69 3GH , country= United Kingdom organization= International Joint Research Center for Resilient Infrastructure \& International Joint Research Center for Engineering Reliability Stochastic Mechanics, Tongji University , city= Shanghai , postcode= 200092 , country= China

AI总结 本文研究了由二阶常微分方程和多层感知机组成的神经振荡器,推导了其在近似因果连续算子和二阶动力系统中的上近似界限,并验证了收敛速率。

Comments 37 pages, 11 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.16842 2026-04-21 math.NA cs.LG cs.NA math.AP

Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches

奇点形成:理论、数值和机器学习方法的协同作用

Yixuan Wang

机构 * CALIFORNIA INSTITUTE OF TECHNOLOGY(加州理工学院)

AI总结 本文通过理论、数值和机器学习方法研究偏微分方程中的奇点形成问题,提出新的分析框架和数值方法,提升对复杂方程中奇点形成机制的理解与预测能力。

详情

展开后加载摘要…

URL PDF HTML 收藏