Home » Notes » Computational Chemistry

Chemical Language Models

Notes on language models for chemistry, from text-to-text translation (SMILES to IUPAC) to vision-language models integrating molecular images and text.
Computational Chemistry
Diagram showing Struct2IUPAC workflow: molecular structure (SMILES) passing through Transformer to generate IUPAC name, with round-trip verification loop

Struct2IUPAC: Transformers for SMILES to IUPAC

A Transformer-based model for translating between SMILES strings and IUPAC names, trained on 47M PubChem examples, …

Computational Chemistry
Transformer encoder-decoder architecture processing InChI string character-by-character to produce IUPAC chemical name

Translating InChI to IUPAC Names with Transformers

Sequence-to-sequence Transformer translating InChI identifiers to IUPAC names with 91% accuracy on organic compounds.

Computational Chemistry
ChemVLM architecture showing molecular structure and text inputs flowing through vision encoder and language model into multimodal LLM for chemical reasoning

ChemVLM: Multimodal LLM for Chemistry

A 26B parameter multimodal LLM for chemistry, combining InternViT-6B and ChemLLM-20B for molecular structure …