# CROP: Integrating Topological and Spatial Structures via Cross-View Prefixes for Molecular LLMs

arXiv: https://arxiv.org/abs/2508.06917 · HTML: https://mlsanity.com/paper/2508.06917/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 58 references that are in the map.
- First posted on arXiv 9 Aug 2025.

## Builds on (most cited first, 27 of 27)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View](https://mlsanity.com/paper/1909.03211/) (2019)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [GemNet: Universal Directional Graph Neural Networks for Molecules](https://mlsanity.com/paper/2106.08903/) (2021)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [Pre-training Molecular Graph Representation with 3D Geometry](https://mlsanity.com/paper/2110.07728/) (2021)
- [ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction](https://mlsanity.com/paper/2106.06130/) (2021)
- [Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing](https://mlsanity.com/paper/2212.10789/) (2022)
- [A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language](https://mlsanity.com/paper/2209.05481/) (2022)
- [Not too little, not too much: a theoretical analysis of graph (over)smoothing](https://mlsanity.com/paper/2205.12156/) (2022)
- [BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations](https://mlsanity.com/paper/2310.07276/) (2023)
- [Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective](https://mlsanity.com/paper/2306.06615/) (2023)
- [InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery](https://mlsanity.com/paper/2311.16208/) (2023)
- [GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text](https://mlsanity.com/paper/2308.06911/) (2023)
- [MolXPT: Wrapping Molecules with Text for Generative Pre-training](https://mlsanity.com/paper/2305.10688/) (2023)
- [DrugChat: Towards Enabling ChatGPT-Like Capabilities on Drug Molecule Graphs](https://mlsanity.com/paper/2309.03907/) (2023)
- [DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming](https://mlsanity.com/paper/2406.19101/) (2024)
- [SECap: Speech Emotion Captioning with Large Language Model](https://mlsanity.com/paper/2312.10381/) (2023)
- [MolTC: Towards Molecular Relational Modeling In Language Models](https://mlsanity.com/paper/2402.03781/) (2024)
- [Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models](https://mlsanity.com/paper/1706.06689/) (2017)
- [HamNet: Conformation-Guided Molecular Representation with Hamiltonian Neural Networks](https://mlsanity.com/paper/2105.03688/) (2021)
- [Pre-train and Learn: Preserve Global Information for Graph Neural Networks](https://mlsanity.com/paper/1910.12241/) (2019)

## Abstract (arXiv)

Recent advances in molecular science have been propelled significantly by large language models (LLMs). However, their effectiveness is limited when relying solely on molecular sequences, which fail to capture the complex structures of molecules. Beyond sequence representation, molecules exhibit two complementary structural views: the first focuses on the topological relationships between atoms, as exemplified by the graph view; and the second emphasizes the spatial configuration of molecules, as represented by the image view. The two types of views provide unique insights into molecular structures. To leverage these views collaboratively, we propose the CROss-view Prefixes (CROP) to enhance LLMs' molecular understanding through efficient multi-view integration. CROP possesses two advantages: (i) efficiency: by jointly resampling multiple structural views into fixed-length prefixes, it avoids excessive consumption of the LLM's limited context length and allows easy expansion to more views; (ii) effectiveness: by utilizing the LLM's self-encoded molecular sequences to guide the resampling process, it boosts the quality of the generated prefixes. Specifically, our framework features a carefully designed SMILES Guided Resampler for view resampling, and a Structural Embedding Gate for converting the resulting embeddings into LLM's prefixes. Extensive experiments demonstrate the superiority of CROP in tasks including molecule captioning, IUPAC name prediction and molecule property prediction.