Scaling chemical language models reduces pretraining loss but yields only limited or saturating gains on downstream molecular property prediction tasks, exposing a disconnect between pretraining metrics and actual transfer performance.
Multi- modal Molecular Pretraining via Modality Blending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
How Well Do Large-Scale Chemical Language Models Transfer to Downstream Tasks?
Scaling chemical language models reduces pretraining loss but yields only limited or saturating gains on downstream molecular property prediction tasks, exposing a disconnect between pretraining metrics and actual transfer performance.