# Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning

arXiv: https://arxiv.org/abs/2510.23640 · HTML: https://mlsanity.com/paper/2510.23640/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 53 references that are in the map.
- First posted on arXiv 24 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Directional Message Passing for Molecular Graphs](https://mlsanity.com/paper/2003.03123/) (2020)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction](https://mlsanity.com/paper/2010.09885/) (2020)
- [Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development](https://mlsanity.com/paper/2102.09548/) (2021)
- [Pre-training Molecular Graph Representation with 3D Geometry](https://mlsanity.com/paper/2110.07728/) (2021)
- [Large-Scale Chemical Language Representations Capture Molecular Structure and Properties](https://mlsanity.com/paper/2106.09553/) (2021)
- [3D Infomax improves GNNs for Molecular Property Prediction](https://mlsanity.com/paper/2110.04126/) (2021)
- [ChemBERTa-2: Towards Chemical Foundation Models](https://mlsanity.com/paper/2209.01712/) (2022)
- [Molecular representation learning with language models and domain-relevant auxiliary tasks](https://mlsanity.com/paper/2011.13230/) (2020)
- [Accelerating high-throughput virtual screening through molecular pool-based active learning](https://mlsanity.com/paper/2012.07127/) (2020)
- [FP-GNN: a versatile deep learning architecture for enhanced molecular property prediction](https://mlsanity.com/paper/2205.03834/) (2022)
- [Molecular machine learning with conformer ensembles](https://mlsanity.com/paper/2012.08452/) (2020)
- [Uni-Mol2: Exploring Molecular Pretraining Model at Scale](https://mlsanity.com/paper/2406.14969/) (2024)
- [MolKD: Distilling Cross-Modal Knowledge in Chemical Reactions for Molecular Property Prediction](https://mlsanity.com/paper/2305.01912/) (2023)
- [Pre-trained Molecular Language Models with Random Functional Group Masking](https://mlsanity.com/paper/2411.01401/) (2024)
- [The impact of conformer quality on learned representations of molecular conformer ensembles](https://mlsanity.com/paper/2502.13220/) (2025)

## Built on by (most cited first, 2 of 2)

- [Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding](https://mlsanity.com/paper/2602.02742/) (2026)
- [Scaling-Aware Adapter for Structure-Grounded LLM Reasoning](https://mlsanity.com/paper/2602.02780/) (2026)

## Abstract (arXiv)

Multimodal molecular models often suffer from 3D conformer unreliability and modality collapse, limiting their robustness and generalization. We propose MuMo, a structured multimodal fusion framework that addresses these challenges in molecular representation through two key strategies. To reduce the instability of conformer-dependent fusion, we design a Structured Fusion Pipeline (SFP) that combines 2D topology and 3D geometry into a unified and stable structural prior. To mitigate modality collapse caused by naive fusion, we introduce a Progressive Injection (PI) mechanism that asymmetrically integrates this prior into the sequence stream, preserving modality-specific modeling while enabling cross-modal enrichment. Built on a state space backbone, MuMo supports long-range dependency modeling and robust information propagation. Across 29 benchmark tasks from Therapeutics Data Commons (TDC) and MoleculeNet, MuMo achieves an average improvement of 2.7% over the best-performing baseline on each task, ranking first on 22 of them, including a 27% improvement on the LD50 task. These results validate its robustness to 3D conformer noise and the effectiveness of multimodal fusion in molecular representation. The code is available at: github.com/selmiss/MuMo.