Keqiang Yan
Postdoctoral Researcher at Princeton University
New Jersey, United States
Summary
🤩
Rockstar🎓
Top SchoolKeqiang Yan is a research scientist specializing in AI for Science with seven years of experience applying predictive and generative models, LLMs, and agents to materials, molecular, and protein modeling. He transitioned from a PhD in Computer Science at Texas A&M to postdoctoral research at Princeton and now works at ByteDance Seed, combining academic rigor with industry-driven impact. His open-source contributions include extending graph deep learning tooling—adding data loaders and reworking GraphAF components for benchmarks on ZINC250k and QM9—indicating hands-on expertise in model engineering and dataset preparation. Keqiang’s background spans top-tier research internships (MSR AI4Science) and cross-disciplinary training from Peking University, enabling him to bridge foundational ML research and practical AI-driven discovery.
7 years of coding experience
4 years of employment as a software developer
理学学士, 智能科学与技术, 理学学士, 智能科学与技术 at 北京大学博士, Computer Science, 博士, Computer Science at 美国德克萨斯A&M大学
Github Skills (16)
data-preprocessing10
data-loading10
pytorch10
3d-graphics10
dataprep10
deep-learning10
preprocessing10
python10
machine-learning-models10
preprocess10
3d10
graphing9
grapher9
graph9
pandas8
Programming languages (2)
Github contributions (5)
divelab/DIG
Feb 2021 - Jul 2022
A library for graph deep learning research
Role in this project:
Data Scientist / ML Engineer
Data Scientist / ML EngineerContributions:57 commits, 42 pushes, 1 comment in 1 year 4 months
Contributions summary:Keqiang primarily focused on adding data loading functionalities and modifying code related to GraphAF (Graph Auto-Flow) within the repository. Specifically, they added data loaders for processing ZINC250k and QM9 datasets. Furthermore, they updated and rewrote code related to GraphAF, including changes to the model architecture and optimization components, and added benchmark files, demonstrating efforts towards model development and evaluation. These contributions suggest involvement in model training, evaluation, and potentially data preparation within a graph deep learning research context.
explainable-mlpytorchdataminingdeep-learninggraph-deep-learning
YKQ98/KeqiangYan.github.io
Aug 2018 - Mar 2020
Contributions:9 pushes, 1 branch in 1 year 7 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.