3 papers
cs.LG2026
Composable Crystals: Controllable Materials Discovery via Concept Learning
Nian Liu, Yuwei Zeng, Ryoji Kubo +7
De novo crystal generation, a central task in materials discovery, aims to generate crystals that are simultaneously valid, stable, unique, and novel. Existing methods mainly rely…
cs.LG2026
Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement
Nian Liu, Nikita Kazeev, Stephen Gregory Dale +8
De novo crystal generation seeks to discover materials that are not merely realistic, but also stable and novel. However, most existing generative models are trained to maximize th…
cs.LG2025
RAW-Explainer: Post-hoc Explanations of Graph Neural Networks on Knowledge Graphs
Ryoji Kubo, Djellel Difallah
Graph neural networks have demonstrated state-of-the-art performance on knowledge graph tasks such as link prediction. However, interpreting GNN predictions remains a challenging o…