# Learning Transferable Reaction Mechanisms from Visual Chemical Knowledge

arXiv: https://arxiv.org/abs/2609.33608 · HTML: https://mlsanity.com/paper/2609.33608/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents](https://mlsanity.com/paper/2410.10594/) (2024)
- [Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction](https://mlsanity.com/paper/1811.02633/) (2018)
- [ColPali: Efficient Document Retrieval with Vision Language Models](https://mlsanity.com/paper/2407.01449/) (2024)
- [A Graph to Graphs Framework for Retrosynthesis Prediction](https://mlsanity.com/paper/2003.12725/) (2020)
- [ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area](https://mlsanity.com/paper/2408.07246/) (2024)
- [RetroXpert: Decompose Retrosynthesis Prediction like a Chemist](https://mlsanity.com/paper/2011.02893/) (2020)
- [Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction](https://mlsanity.com/paper/2110.09681/) (2021)
- [MolScribe: Robust Molecular Structure Recognition with Image-To-Graph Generation](https://mlsanity.com/paper/2205.14311/) (2022)
- [A Generative Model For Electron Paths](https://mlsanity.com/paper/1805.10970/) (2018)
- [ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge](https://mlsanity.com/paper/2507.21990/) (2025)
- [Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction](https://mlsanity.com/paper/2106.07801/) (2021)
- [OpenChemIE: An Information Extraction Toolkit For Chemistry Literature](https://mlsanity.com/paper/2404.01462/) (2024)
- [Electron flow matching for generative reaction mechanism prediction obeying conservation laws](https://mlsanity.com/paper/2502.12979/) (2025)
- [GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation](https://mlsanity.com/paper/2501.08001/) (2025)
- [TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks](https://mlsanity.com/paper/2511.06283/) (2025)
- [ChemVLR: Prioritizing Reasoning in Perception for Chemical Vision-Language Understanding](https://mlsanity.com/paper/2604.06685/) (2026)
- [DeepMech: A Machine Learning Framework for Chemical Reaction Mechanism Prediction](https://mlsanity.com/paper/2509.15872/) (2025)
- [Learning Mechanistic Reasoning for Chemical Reactions with Large Language Models](https://mlsanity.com/paper/2607.12771/) (2026)

## Abstract (arXiv)

Reaction mechanisms describe the step-by-step transformations underlying chemical reactions and are central to reaction analysis and synthesis. Learning-based models have achieved strong performance on established mechanism-prediction benchmarks, but transferring them to unseen chemistry remains challenging. Such transfer is difficult because familiar mechanisms must be applied to unfamiliar molecular structures, and some target mechanisms may be poorly covered by the training data. To address these challenges, we introduce MechaVLM, a visual framework that combines transferable chemical representations with external mechanistic knowledge. It learns reusable visual features through multiscale chemical grounding and cross-rendering contrastive learning. For open-book prediction, MechaVLM retrieves a fixed set of precedents from 70,384 literature mechanism figures and re-reads relevant visual evidence as the molecular state evolves, directly using the figures without symbolic mechanism parsing. An atom-indexed language decoder then recursively generates executable electron edits to construct the complete mechanism. We further introduce MechBench, a challenging literature-derived benchmark with 2,184 mechanisms and 9,146 elementary steps. Across cross-dataset and literature-derived benchmarks, MechaVLM establishes strong zero-shot mechanism prediction. Its closed-book model alone improves Step/Pathway Top-1 by 12.50/13.93 percentage points on FlowER-to-ReactMech transfer, while external visual precedents unlock further gains on challenging OOD reactions. The learned representation also generalizes beyond mechanism prediction to atom mapping and reaction center prediction.