GradSCF
A Python framework for molecular and periodic electronic-structure calculations, differentiable numerical methods, and machine-learned models.
differentiable-programmingelectronic-structuremachine-learningquantum-chemistry
Yuan Jiao
Ph.D. Student
School of Advanced Interdisciplinary Sciences (SAIS)
University of Chinese Academy of Sciences (UCAS)
Institute of Physics, Chinese Academy of Sciences
I am a Ph.D. student at UCAS (School of Interdisciplinary Science and Technology), affiliated with the Institute of Physics, CAS, working on electronic structure theory and quantum many-body theory. My research focuses on AI-driven design of neural exchange-correlation functionals for excited-state calculations, efficient electronic structure methods, and the theoretical study of complex organic systems via many-body theory and geometric deep learning.
Research Interests
- AI-driven design of exchange-correlation functionals and optimization of electronic structure algorithms
- Transport and photophysical properties of organic semiconductors
- Vibe coding and creative applications of AI agents
News
- 2025-06 Paper published in Aggregate: "Size‐dependent Stability and Luminescence Property in Organic Aggregates"
- 2024-12 Started Ph.D. in Physics at UCAS, School of Advanced Interdisciplinary Sciences
- 2024-09 Started Ph.D. program at UCAS
Selected Publications
View all →-
Size‐dependent Stability and Luminescence Property in Organic Aggregates
Selected Projects
View all → GradTDDFT
JAX research toolkit for differentiable TDDFT: strict-JAX SCF, TDA/Casida TDDFT, Neural Network XC/RSH training, spectra, integrals, and CUDA J/K experiments.
deep-learningdifferentiable-programmingquantum-chemistry-programs
QHformer
SO(3)-Equivariant Hamiltonian Prediction with Hybrid Attention - A novel neural network for quantum chemistry
attention-mechanismequivariant-networkgraph-neural-networksquantum-chemistry
