{"type":"ScholarlyArticle","title":"ILR-SMO: Iterative Latent Refinement for Robust Spatial Multi-Omics Integration","authors":[{"name":"Anqi Yu","slug":"anqi-yu","given":"Anqi","family":"Yu","affiliation":""},{"name":"Xudong Xu","slug":"xudong-xu","given":"Xudong","family":"Xu","affiliation":""},{"name":"Jianzhi Lu","slug":"jianzhi-lu","given":"Jianzhi","family":"Lu","affiliation":""},{"name":"Yuqi Sun","slug":"yuqi-sun","given":"Yuqi","family":"Sun","affiliation":""},{"name":"Bingguo Chen","slug":"bingguo-chen","given":"Bingguo","family":"Chen","affiliation":""},{"name":"Chenxi Ma","slug":"chenxi-ma","given":"Chenxi","family":"Ma","affiliation":""},{"name":"Weimin Tan","slug":"weimin-tan","given":"Weimin","family":"Tan","affiliation":""},{"name":"Bo Yan","slug":"bo-yan","given":"Bo","family":"Yan","affiliation":""}],"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.","doi":"10.24963/ijcai.2026/582","url":"https://ijcai.org/proceedings/2026/582","pdf":"https://ijcai.org/proceedings/2026/0582.pdf","markdown":"https://ijcai.org/proceedings/2026/582.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/582","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Machine Learning","track":"Main Track","number":582,"pages":{"first":5227,"last":5235},"keywords":["Machine Learning: Multi-modal learning","Multidisciplinary Topics and Applications: Bioinformatics","Machine Learning: Clustering","Machine Learning: Multi-view learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}