2025 · Published
Host-Guided Crystal Structure Generation
Conditional generative models for placing atoms inside symmetrized host structures, combining diffusion-based inpainting with foundation potentials for materials discovery.
View project ↗Research projects
Generative materials models, scientific machine learning, and open tools for microscopy.
Materials discovery & machine learning
Generative models and data-centric methods for materials discovery and atomistic analysis.
2024 · Published
Generative Inpainting for Intercalation Materials
An SE(3)-equivariant score model that predicts intercalant positions in host crystals for energy-storage materials design.
View project ↗
2022 · Research
Data-Centric Structure Identification
Graph neural networks and feature engineering for accurate, efficient local crystal-structure identification in atomistic simulations.
DeepSTEM research series
Machine-learning methods for processing, interpreting, and extracting scientific insight from atomic-resolution microscopy data.
2024 · Research
AI-Assisted Chemical Mapping in Atomic-Resolution STEM
An end-to-end workflow for image restoration, atom localization, and intensity-based chemical assignment in complex two-dimensional materials.
Read project →
2024 · Research
Learning Local Structure in Monolayer Amorphous Carbon
Rotation-invariant representation learning for discovering interpretable local structural features in noisy atomic-resolution images.
Read project →
2024 · Research
Machine-Learning Denoising for Vibrational STEM-EELS
Machine-learning denoising for three-dimensional vibrational STEM-EELS spectrum-image data.
Read project →