MolGram integrates a conditional n-gram memory module into molecular language models to address locality gaps in SMILES tokenization, improving performance on generation, forward prediction, and retrosynthesis while outperforming 3x larger baselines.
arXiv preprint arXiv:2507.17448 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A systematic review of LLM applications in process systems engineering finds genuine utility for natural-language tasks but persistent challenges for real-time execution, constraint satisfaction, and safety guarantees.
RETROSPECT reports 55.00% top-1 and 86.18% top-10 accuracy on USPTO-50K with a ChemAlign Transformer plus LambdaMART reranker reaching 59.4% top-1 on candidate pools using proposal scores and template statistics.
citing papers explorer
-
Augmenting Molecular Language Models with Local $n$-gram Memory
MolGram integrates a conditional n-gram memory module into molecular language models to address locality gaps in SMILES tokenization, improving performance on generation, forward prediction, and retrosynthesis while outperforming 3x larger baselines.
-
Large Language Models in Process Systems Engineering: Opportunities, Architectures, and Industrial Deployment Challenges
A systematic review of LLM applications in process systems engineering finds genuine utility for natural-language tasks but persistent challenges for real-time execution, constraint satisfaction, and safety guarantees.
-
RETROSPECT: RETROsynthesis via Sequential Prediction, and Chemically Transformed-ranking
RETROSPECT reports 55.00% top-1 and 86.18% top-10 accuracy on USPTO-50K with a ChemAlign Transformer plus LambdaMART reranker reaching 59.4% top-1 on candidate pools using proposal scores and template statistics.