Lingshen He

lingshenhe AT pku.edu.cn

Ph.D. student

Peking University

Biography

I am a CS phd student at Peking University (PKU). Here I am lucky enough to work with Prof. Zhouchen Lin. Recently, my main research topics include equivariant deep learning and geometric deep learning, furthermore, I’m also interested in efficiency and transformer in the deep learning. It is well-come to contact me for collaboration.

Interests

Machine Learning
Equivariant Deep Learning

Education

Phd in Intelligence Science and Technology, 2019-2024

Peking University
BSc in Applied Physics (Yingcai Honer School), 2015-2019

University of Electronic Science and Technology of China

Publications @ZERO Lab

Neural ePDOs: Spatially Adaptive Equivariant Partial Differential Operator Based Networks. ICLR, 2023.

Endowing deep learning models with symmetry priors can lead to a considerable performance improvement. As an interesting bridge between …

Lingshen He , Yuxuan Chen , Zhenyang Shen , Yibo Yang , Zhouchen Lin

PDF

Efficient Equivariant Network. NeurIPS, 2021.

Convolutional neural networks (CNNs) have dominated the field of Computer Vision and achieved great success due to their built-in …

Lingshen He , Yuxuan Chen , Zhenyang Shen , Yiming Dong , Yisen Wang , Zhouchen Lin

PDF

Gauge Equivariant Transformer. NeurIPS, 2021.

Attention mechanism has shown great performance and efficiency in a lot of deep learning models, in which relative position encoding …

Lingshen He , Yiming Dong , Yisen Wang , Dacheng Tao , Zhouchen Lin

PDF

Implicit Euler Skip Connections: Enhancing Adversarial Robustness via Numerical Stability. ICML, 2020.

We explore the relationship between the adversarial robustness and numerical stability. Furthermore, we propose IE-Skips, which is a …

Mingjie Li , Lingshen He , Zhouchen Lin

PDF

PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions. ICML, 2020.

We employ PDOs as steerable filters to design a system equivariant to E(n). We use numerical schemes to discretize this system and …

Zhengyang Shen , Lingshen He , Zhouchen Lin , Jinwen Ma

Neural Ordinary Differential Equations with Envolutionary Weights. PRCV, 2019.

Neural networks have been very successful in many learning tasks, for their powerful ability to fit the data. Recently, to understand …

Lingshen He , Xingyu Xie , Zhouchen Lin

PDF supp