Chirality emerges in SMILES translation models through an abrupt encoder-centered reorganization of representations after a long plateau, identified via checkpoint analysis and ablation.
Randomized SMILES strings improve the quality of molecular generative models.J
2 Pith papers cite this work, alongside 409 external citations. Polarity classification is still indexing.
2
Pith papers citing it
409
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
On chemistry SMILES with a fixed 165-token base, BPE and Unigram-LM produce near-disjoint vocabularies (Jaccard ≤0.161) and Unigram-LM emits 29–41% more tokens across 22 matched conditions.
citing papers explorer
-
From Syntax to Semantics: Unveiling the Emergence of Chirality in SMILES Translation Models
Chirality emerges in SMILES translation models through an abrupt encoder-centered reorganization of representations after a long plateau, identified via checkpoint analysis and ablation.
-
Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES
On chemistry SMILES with a fixed 165-token base, BPE and Unigram-LM produce near-disjoint vocabularies (Jaccard ≤0.161) and Unigram-LM emits 29–41% more tokens across 22 matched conditions.