---
title: "ILR-SMO: Iterative Latent Refinement for Robust Spatial Multi-Omics Integration"
authors:
  - "Anqi Yu"
  - "Xudong Xu"
  - "Jianzhi Lu"
  - "Yuqi Sun"
  - "Bingguo Chen"
  - "Chenxi Ma"
  - "Weimin Tan"
  - "Bo Yan"
doi: "10.24963/ijcai.2026/582"
url: "https://ijcai.org/proceedings/2026/582"
pdf: "https://ijcai.org/proceedings/2026/0582.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "5227-5235"
track: "Main Track"
keywords:
  - "Machine Learning: Multi-modal learning"
  - "Multidisciplinary Topics and Applications: Bioinformatics"
  - "Machine Learning: Clustering"
  - "Machine Learning: Multi-view learning"
---

# ILR-SMO: Iterative Latent Refinement for Robust Spatial Multi-Omics Integration

Anqi Yu, Xudong Xu, Jianzhi Lu, Yuqi Sun, Bingguo Chen, Chenxi Ma, Weimin Tan, Bo Yan

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 5227-5235. DOI: [10.24963/ijcai.2026/582](https://doi.org/10.24963/ijcai.2026/582)

## Abstract

Spatial multi-omics technologies jointly profile diverse molecular modalities with spatial context, providing a comprehensive view of cellular heterogeneity and tissue organization. To integrate spatial multi-omics data and identify spatial domains, a wide range of unsupervised methods has been proposed. However, recent approaches rely on single-step fusion, directly aggregating heterogeneous modalities into a shared representation, making embeddings sensitive to modality imbalance and measurement noise that are inherent to spatial multi-omics data, as well as unstable optimization under weak supervision. Here, we propose ILR-SMO (Iterative Latent Refinement for Spatial Multi-Omics), a unified self-supervised framework that reformulates multimodal integration as a stability-aware refinement process over a shared latent representation. Instead of single-step plain fusion, ILR-SMO progressively integrates modality-specific information through sequential updates, allowing information to be injected in a controlled manner. This incremental refinement enables later updates to correct or compensate for earlier deviations, resulting in more stable and robust representation learning under heterogeneous and noisy modalities. ILR-SMO further incorporates reliability-aware modality gating for adaptive modulation of modality contributions, and employs a joint objective to enforce spatial coherence while preventing representation collapse. Extensive experiments on five spatial multi-omics benchmarks demonstrate that ILR-SMO consistently outperforms seven state-of-the-art methods and exhibits strong robustness across diverse settings.