Luo Lab（罗倚斯课题组）围绕张量方法、连续表示和 AI for Science 展开研究。我们关注如何用低秩结构、函数表示与神经模型处理高维复杂科学数据，特别是图像恢复、空间组学、地球物理反演和科学计算等场景。 Luo Lab focuses on tensor methods, continuous representations, and AI for Science. We study how low-rank structure, functional representations, and neural models can be used to model and recover high-dimensional scientific data in imaging, spatial omics, inversion, and scientific computing.
实验室由罗倚斯带领，依托西安交通大学数学与统计学院开展工作。我们的研究既重视理论，也重视实际问题中的表现：一方面探索张量分解、隐式神经表示、神经算子与优化机制，另一方面将这些方法落到多维数据恢复、尺度连续建模和 AI4Sci 的真实任务中。 Led by Yisi Luo at the School of Mathematics and Statistics, Xi'an Jiaotong University, the lab values both theory and real scientific utility. We work on tensor decomposition, implicit neural representations, neural operators, and optimization, while grounding these methods in multidimensional data recovery, continuous-scale modeling, and AI4Sci applications.
Tensor Methods and Low-Rank Modeling.
Continuous Representation and Neural Operators.
Scientific Data Recovery and Inversion.
and AI for Science.
Tensor Methods and Low-Rank Modeling.
Continuous Representation and Neural Operators.
Scientific Data Recovery and Inversion.
and AI for Science.
Yisi Luo
Scholar
yisiluo1221@foxmail.com
Research SnapshotResearch Snapshot
当前关注的问题Current themes- 低秩张量建模与张量函数表示，用于多维数据恢复与结构化学习。Low-rank tensor modeling and tensor function representations for multidimensional recovery and structured learning.
- 连续表示、隐式神经表示与任意尺度建模。Continuous representations, implicit neural representations, and arbitrary-scale modeling.
- 面向空间组学、全波形反演与科学图像处理的 AI4Sci 方法。AI4Sci methods for spatial omics, full-waveform inversion, and scientific imaging.
Xi'an, Shaanxi, China School of Mathematics and Statistics, Xi'an Jiaotong University
Xi'an, Shaanxi, China