Chang Liu

Associate Professor@Zhongguancun Academy·中国·OpenReview

研究方向

AI for science: machine-learning force field · density functional theory · quantum Monte Carlo · molecular structure sampling · statistical mechanics · Bayesian models · Bayesian neural networks · generative models · variational auto-encoders · generative adversarial nets · diffusion models · flow matching models · topic models · Bayesian inference · MCMC · variational inference · causality · structural equation models · structural causal models · identifiability

7.5

E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products

NeurIPS 2025Spotlight

7.5

Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular Systems

ICLR 2025Spotlight

6.6

Efficient and Scalable Density Functional Theory Hamiltonian Prediction through Adaptive Sparsity

合作者 (20)

Chang Liu

Quotient-Space Diffusion Models

Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value

FlexRibbon: Joint Sequence and Structure Pretraining for Protein Modeling

E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products

Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular Systems

Efficient and Scalable Density Functional Theory Hamiltonian Prediction through Adaptive Sparsity