A multi-head cross-attention fusion of CGCNN and SciBERT embeddings improves predicted formation energy, band gap, Fermi energy, and energy above hull compared to the two vanilla models.
Crysmmnet: multimodal representation for crystal property prediction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MatMMFuse: Multi-Modal Fusion model for Material Property Prediction
A multi-head cross-attention fusion of CGCNN and SciBERT embeddings improves predicted formation energy, band gap, Fermi energy, and energy above hull compared to the two vanilla models.