A frozen ImageNet vision model reading 2D molecular drawings outperforms a quantum-descriptor tabular model for C-N coupling yield prediction, and cross-attention fusion gives 5.27% RMSE.
Attention is all you need.Adv
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generic Vision and Cross-Attention for Reaction Yield Prediction
A frozen ImageNet vision model reading 2D molecular drawings outperforms a quantum-descriptor tabular model for C-N coupling yield prediction, and cross-attention fusion gives 5.27% RMSE.