Luo, Shitong 罗世通

Peking University

Shitong Luo is a final year undergraduate student majoring in Data Science at Peking University. He is now a research intern at Wangxuan Institue of Computer Technology and Mila - Quebec AI Institute. He is interested in geometric data processing and geometric deep learning.

Email: luost AT


Minkai Xu* Shitong Luo* Yoshua Bengio Jian Peng Jian Tang (* indicates equal contribution)

Under review 2020

Inspired by the recent progress in deep generative models, in this paper, we propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph.

Shitong Luo Wei Hu

Under review 2020

We view points in point clouds as particles in a thermodynamic system in contact with a heat bath, which diffuse from the original distribution to a noise distribution. Point cloud generation thus amounts to learning the reverse diffusion process that transforms the noise distribution to the distribution of a desired shape.

A Probabilistic Model for Molecular Geometry Generation and Optimization

Shitong Luo

Machine Learning for Molecules Workshop, NeurIPS 2020

We propose a probabilistic model for molecular conformation generation and geometry optimization. The model takes molecular graphs as input and learns the distributions w.r.t. inter-atomic distances.

Differentiable Manifold Reconstruction for Point Cloud Denoising

Shitong Luo Wei Hu

ACM International Conference on Multimedia (ACM MM) 2020 Oral

We propose a novel point cloud denoising neural network that is aware of the underlying manifold structure of noisy point clouds. Experiments show that our method significantly outperforms state-of-the-art denoising methods under both synthetic noise and real world noise.

All publications