Scholar
Chang Liu
Google Scholar ID: rYd0GEsAAAAJ
Microsoft Research AI for Science
Citations & Impact
Citations
3,587
H-index
22
i10-index
31
Publications
20
Co-authors
13
list available
Contact
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published several papers, including 'Potential Score Matching: Debiasing Molecular Structure Sampling with Potential Energy Guidance', 'Efficient and Scalatile Density Functional Theory Hamiltonian Prediction through Adaptive Sparsity', etc. Preprints include 'Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value', 'NatureLM: Deciphering the Language of Nature for Scientific Discovery', etc.
Research Experience
- Currently a senior researcher at Microsoft Research AI for Science (Asia branch). Previously worked in the Machine Learning Group at Microsoft Research Asia.
Education
- Received Ph.D. degree (cum laude) in 2019 from the TSAIL Group at the Department of Computer Science and Technology of Tsinghua University, supervised by Prof. Jun Zhu. Received B.Sc. degree in 2014 from the Department of Physics of Tsinghua University. Visited Prof. Lawrence Carin's group at Duke University from Oct. 2017 to Oct. 2018.
Background
- Currently a senior researcher at Microsoft Research AI for Science (Asia branch). Research interests focus on machine learning, including sampling methods (mainly in the context of Bayesian inference; e.g., variational inference, MCMC), generative models (e.g., diffusion models), and AI methods for molecular science problems (e.g., electronic structure, molecular dynamics, statistical mechanics).
