Postdoc in Computer Science
Department of Computer Science
Princeton University
D.E. Shaw Research Doctoral & Postdoctoral Fellow
Address: Princeton, NJ, 08544
Email: yankeqiang98@gmail.com
I am currently a Postdoc researcher in the Department of Computer Science, Princeton University, working with Dr. Adji Bousso Dieng. I obtained my bachelor’s degree from Peking University in 2020, advised by Prof. Jiaying Liu, and my Ph.D. degree in Computer Science from Texas A&M University, supervised by Dr. Shuiwang Ji.
My research focuses on scientific machine learning (ML) and AI for science. I use science to guide AI/ML development and develop AI/ML to accelerate scientific discovery. Specifically, I develop new geometric deep learning methods including Large Language Models (LLMs) guided by physical laws (e.g. symmetry, group theory, equivariance, etc.) to speed up scientific discovery in various fields, including biology, chemistry, drug discovery, and materials science.
Besides publishing top-tier papers, I am also active in open challenges, benchmark competitions for scientific discovery, and open-source communities. I am a member of the #3 team on the Open Catalyst Challenge, the lead of the #1 team on Matbench formation energy (ComFormer ICLR24), and a contributor to the popular open-source libraries including DIG and AIRS, with a total of more than 2.4K stars on github.
The Large Language Models have great potential to bring more innovations and breakthroughs for AI empowered Scientific Discovery. Our long-term objective is to develop powerful, knowledgable, and reliable agents and systems to help speed up the discovery process.
[07/2025] Our paper Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems has been accepted to Foundations and Trends in Machine Learning!
[04/2025] I received Graduate Research Excellence Award from TAMU CSE, one per year
[04/2025] Invited talk at University of Utah School of Computing.
[03/2025] Invited talk at GaTech CSE department.
[03/2025] Invited talk at UPenn CIS department.
[03/2025] Invited talk at UT Austin ME department.
[09/2024] Our paper Invariant Tokenization for Language Model Enabled Crystal Materials Generation has been accepted to NeurIPS 2024!
[05/2024] Our paper A Space Group Symmetry Informed Network for O(3) Equivariant Crystal Tensor Prediction has been accepted to ICML 2024!
[03/2024] Our paper JARVIS-LeaderBoard has been accepted to Npj Computational Materials!
[03/2024] I received the D.E. Shaw Research Doctoral and Posdoctoral Fellowship!
[01/2024] Our paper Complete and Efficient Graph Transformers for Crystal Material Property Prediction has been accepted to ICLR 2024!
[11/2023] Our paper A Latent Diffusion Model for Protein Structure Generation has been accepted to LoG 2023!
[11/2023] Our paper Examining graph neural networks for crystal structures: limitations and opportunities for capturing periodicity has been accepted to Science Advances!
[05/2023] Our paper Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction has been accepted to ICML 2023!
[09/2022] Our paper Periodic Graph Transformers for Crystal Material Property Predictionh has been accepted to NeurIPS 2022!
[12/2021] We won the 3rd place of Open Catalyst Challenge 2021!
[09/2021] Our paper DIG: A Turnkey Library for Diving into Graph Deep Learning Research has been accepted to JMLR!
[04/2021] Our paper GraphDF: A Discrete Flow Model for Molecular Graph Generation has been accepted to ICML 2021!
[04/2021] Our paper GraphEBM: Molecular Graph Generation with Energy-Based Models has been accepted to EBM Workshop at ICLR 2021!
Graduate Research Excellence, TAMU CSE, one per year, 2025
D.E. Shaw Research Doctoral & Postdoctoral Fellowship, 2024
NeurIPS Travel Award, 2022
Texas A&M University Travel Award, 2022, 2023, 2024
3rd Place of Open Catalyst Challenge, 2021
Excellent Graduate, Peking University, 2020
Excellent Research Award, Peking University, 2019