InstructMol integrates a pre-trained molecular graph encoder (MoleculeSTM) with a Vicuna-7B LLM using a linear projector. It employs a two-stage training process (alignment pre-training followed by task-specific instruction tuning with LoRA) to excel at property prediction, description generation, and reaction analysis.
MERMaid leverages fine-tuned vision models and VLM reasoning to mine chemical reaction data from PDF figures and tables, handling context inference and coreference resolution to build high-fidelity knowledge graphs with 87% end-to-end accuracy.
MOFFlow is the first deep generative model tailored for Metal-Organic Framework (MOF) structure prediction. It utilizes Riemannian flow matching on SE(3) to assemble rigid building blocks (metal nodes and organic linkers), achieving significantly higher accuracy and scalability than atom-based methods on large systems.
This paper presents a multimodal search system that facilitates passage-level retrieval of chemical reactions and molecular structures by linking diagrams, text, and reaction records extracted from scientific PDFs.
OCSAug leverages Denoising Diffusion Probabilistic Models (DDPM) and the RePaint algorithm with custom masking to generate synthetic hand-drawn chemical structure images, significantly improving OCSR performance on benchmarks like DECIMER.
STOUT V2.0 uses Transformers trained on ~1 billion SMILES-IUPAC pairs to accurately translate chemical structures into systematic names (and vice-versa), outperforming its RNN predecessor.
STOUT (SMILES-TO-IUPAC-name translator) uses neural machine translation to convert chemical line notations to IUPAC names and vice versa, achieving ~90% BLEU score. It addresses the lack of open-source tools for algorithmic IUPAC naming.
This paper proposes a Transformer-based approach (Struct2IUPAC) to convert chemical structures to IUPAC names, challenging the dominance of rule-based systems. Trained on ~47M PubChem examples, it achieves near-perfect accuracy using a round-trip verification step with OPSIN.
This study presents a sequence-to-sequence Transformer model that translates InChI identifiers into IUPAC names character-by-character. Trained on 10 million PubChem pairs, it achieves 91% accuracy on organic compounds, performing comparably to commercial software.
Introduces AtomLenz, an OCSR tool that combines object detection with a molecular graph constructor. Features a novel weakly supervised training scheme (ProbKT*) to learn atom-level localization from SMILES-only data, achieving state-of-the-art results on hand-drawn images.
ChemReco automates the recognition of hand-drawn chemical structures using a synthetic data pipeline and an EfficientNet+Transformer architecture, achieving 96.90% accuracy on C-H-O molecules.
A 2025 AAAI paper introducing ChemVLM, a domain-specific multimodal LLM (26B parameters) that achieves state-of-the-art performance on chemical OCR, reasoning benchmarks, and molecular understanding tasks by combining vision and language models trained on curated chemistry data.