Publications

1. 

   A Foundation Model for Non-Destructive Defect Identification from Vibrational Spectra

   Mouyang Cheng†,*, Chu-Liang Fu†, Bowen Yu†, Eunbi Rha, Abhijatmedhi Chotrattanapituk, Douglas L. Abernathy, Yongqiang Cheng, and Mingda Li*

   † Equal contribution. * Corresponding author.

   Matter Published Mar 2026 · arXiv May 2025

   DefectNet predicts the chemical identity and concentration of substitutional point defects directly from vibrational spectra, establishing vibrational spectroscopy as a non-destructive probe for defect quantification.

   arXiv Paper Details

1. 

   Reinforcement learning-guided optimization of critical current in high-temperature superconductors

   Mouyang Cheng†,*, Qiwei Wan†, Bowen Yu†, Eunbi Rha, Michael J. Landry, and Mingda Li*

   † Equal contribution. * Corresponding author.

   In review arXiv Oct 2025

   This work combines reinforcement learning with time-dependent Ginzburg-Landau simulations to autonomously optimize defect configurations for high-temperature superconductors.

   arXiv Details
2. 

   Enhancing Materials Discovery with Valence Constrained Design in Generative Modeling

   Mouyang Cheng†,*, Weiliang Luo†, Hao Tang†, Bowen Yu, Yongqiang Cheng, Weiwei Xie, Ju Li, Heather J. Kulik, and Mingda Li*

   † Equal contribution. * Corresponding author.

   In review arXiv Jul 2025

   CrysVCD integrates chemical valence constraints into a generative materials pipeline, improving chemical validity while supporting conditional discovery of stable functional materials.

   arXiv Details
3. 

   A Foundation Model for Non-Destructive Defect Identification from Vibrational Spectra

   Mouyang Cheng†,*, Chu-Liang Fu†, Bowen Yu†, Eunbi Rha, Abhijatmedhi Chotrattanapituk, Douglas L. Abernathy, Yongqiang Cheng, and Mingda Li*

   † Equal contribution. * Corresponding author.

   Matter Published Mar 2026 · arXiv May 2025

   DefectNet predicts the chemical identity and concentration of substitutional point defects directly from vibrational spectra, establishing vibrational spectroscopy as a non-destructive probe for defect quantification.

   arXiv Paper Details