Bowen Yu

Publications

Selected

  1. DefectNet workflow demonstration

    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
  2. Integrated workflow for XPCS, theory, and domain-adaptive machine learning in grain-boundary dynamics

    Probing Non-Equilibrium Grain Boundary Dynamics with XPCS and Domain-Adaptive Machine Learning

    Mouyang Cheng†,*, Bowen Yu†, Chu-Liang Fu, Nina Andrejevic, Matthias T. Agne, Riley Hanus, Qiwei Wan, Nathan C. Drucker, Thanh Nguyen, Andrei Fluerasu, Lutz Wiegart, Xiaoqian M Chen, Daniel Pajerowski, Yongqiang Cheng, Joshua J Turner, G. Jeffrey Snyder, and Mingda Li*

    † Equal contribution. * Corresponding author.

    In review arXiv May 2026

    This work pairs X-ray photon correlation spectroscopy with semi-supervised domain adaptation to quantify slow, non-equilibrium grain-boundary dynamics in nanocrystalline silicon.

    arXiv Details

All publications

  1. Integrated workflow for XPCS, theory, and domain-adaptive machine learning in grain-boundary dynamics

    Probing Non-Equilibrium Grain Boundary Dynamics with XPCS and Domain-Adaptive Machine Learning

    Mouyang Cheng†,*, Bowen Yu†, Chu-Liang Fu, Nina Andrejevic, Matthias T. Agne, Riley Hanus, Qiwei Wan, Nathan C. Drucker, Thanh Nguyen, Andrei Fluerasu, Lutz Wiegart, Xiaoqian M Chen, Daniel Pajerowski, Yongqiang Cheng, Joshua J Turner, G. Jeffrey Snyder, and Mingda Li*

    † Equal contribution. * Corresponding author.

    In review arXiv May 2026

    This work pairs X-ray photon correlation spectroscopy with semi-supervised domain adaptation to quantify slow, non-equilibrium grain-boundary dynamics in nanocrystalline silicon.

    arXiv Details
  2. RL-guided critical current workflow demonstration

    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
  3. CrysVCD workflow demonstration

    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
  4. DefectNet workflow demonstration

    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