Papers

Enabling single-observation decomposition of multi-phase X-ray diffraction patterns via generative deep learning

This paper proposes multi-phase pattern decomposition method for X-ray diffraction measurement by using generative deep learning. Published in npj computational materials, 2026.

Optimal spectroscopic measurement design: Bayesian framework for rational data acquisition

This paper proposes optimal experimental design method for spectroscopy measurement by using Bayesian framework. Published in Machine Learning: Science and Technology, 2025.

Rethinking the role of frames for SE(3)-invariant crystal structure modeling

This paper proposes dynamic atom-wise frames aligned with attention-based interatomic interactions on the structure, rather than with the structure itself. Published in ICLR 2025.

Transformer as a Neural Knowledge Graph

Propose a transformer-based neural knowledge graph to integrate contextual knowledge into contrastive learning between crystal structures and linguistic physical properties. Published in AI4MAT-ICLR-2025.

Rational partitioning of spectral feature space for effective clustering of massive spectral image data

This paper proposes new clustering method for massive spectral image data. Published in Scientific Reports, 2024.