InstructMol: Multi-Modal Molecular Assistant
A multi-modal LLM aligning 2D molecular graphs with text via two-stage instruction tuning for drug discovery tasks.
Multimodal Models
Notes on vision-language models and multimodal architectures for chemistry. Covers models that integrate molecular images, text, and structured data.
MERMaid: Multimodal Reaction Mining
Vision-language pipeline extracting chemical reaction data from PDF figures and tables into structured knowledge graphs …
Multimodal Search in Chemical Documents
A multimodal search engine that integrates text passages, molecular diagrams, and reaction data to enable passage-level …
ChemVLM: Multimodal LLM for Chemistry
A 26B parameter multimodal LLM for chemistry, combining InternViT-6B and ChemLLM-20B for molecular structure …