X2-GNN: A Physical Message Passing Neural Network with Natural Generalization Ability to Large and Complex Molecules, J. Phys. Chem. Lett., 15 (2024), 12501-12512

Constructing Accurate and Efficient General-Purpose Atomistic Machine Learning Model with Transferable Accuracy for Quantum Chemistry,  J. Chem. Theor. Comput., 20 (21)(2024), 9500-9511

A Dataset Representativeness Metric and A Slicing Sampling Strategy for the Kennard-Stone Algorithm, Chem. J. Chin. Univ., 43(10)(2022), 20220397

Accurate Heats of Formation of Polycyclic Saturated Hydrocarbons Predicted by Using the XYG3 Type of Doubly Hybrid Functionals, J. Comput. Chem., 40(2019), 1113-1122

X1se: a combined method of density functional calculation and neural network correction for accurate prediction of heats of formation, Sci. Sin. Chim., 46(1)(2016), 38-50

How well can B3LYP heats of formation be improved by dispersion correction models? Theor. Chem. Acc., 135(2016), 44.

Improving B3LYP heats of formation with three‐dimensional molecular descriptors. J. Comput. Chem., 37(2016), 1175-1190

The X1 Family of Methods that Combines B3LYP with Neural Network Corrections for an Accurate Yet Efficient Prediction of Thermochemistry, Int. J. Quant. Chem., 115(2015), 1021-1031

Calculations of Ionization Energies and Electron Affinities for Atoms and Molecules: A Comparative Study with Different Methods Front. Chem. China, 6(4) (2011), 269-279

Theoretical Studies on Thermochemistry for Conversion of 5-Chloromethylfurfural into Valuable Chemicals, J. Phys. Chem. A, 115 (46) (2011), 13628–13641

Accurate Bond Dissociation Enthalpies by Using Doubly Hybrid XYG3 Functional, J. Comput. Chem., 32 (2011), 1824–1838

The X1s Method for Accurate Bond Dissociation Energies, ChemPhysChem, 11(2010), 2561-2567

Extending the reliability and applicability of B3LYP, Chem. Commun., 46(2010), 3057-3070. (Feature Article)

Trends in R-X Bond Dissociation Energies (R• =Me, Et, i-Pr, t-Bu, X• =H, Me, Cl, OH), J. Chem. Theory Comput., 6(5), (2010) 1447-1454

Accurate Prediction of Heats of Formation by a Combined Method of B3LYP and Neural–network Correction, J. Comput. Chem., 30(9), (2009) 1424-1444

Improving the B3LYP bond energies by using the X1 method, J. Chem. Phys., 129(2008) 164103

The X1 method for accurate and efficient prediction of heats of formation, J. Chem. Phys., 127(2007) 214105