# CALM: Interpretable Cross-Modal Alignment for Biomarker Discovery from Unpaired Data

arXiv: https://arxiv.org/abs/2607.01656 · HTML: https://mlsanity.com/paper/2607.01656/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 40 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Builds on (most cited first, 11 of 11)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Not Just a Black Box: Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1605.01713/) (2016)
- [Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction](https://mlsanity.com/paper/2304.06819/) (2023)
- [AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal Alignment](https://mlsanity.com/paper/2412.00833/) (2024)
- [Learning Unseen Modality Interaction](https://mlsanity.com/paper/2306.12795/) (2023)
- [G-MIND: An End-to-End Multimodal Imaging-Genetics Framework for Biomarker Identification and Disease Classification](https://mlsanity.com/paper/2101.11656/) (2021)
- [Learning Shared Representations from Unpaired Data](https://mlsanity.com/paper/2505.21524/) (2025)
- [Unsupervised Correlation Analysis](https://mlsanity.com/paper/1804.00347/) (2018)
- [Learning Explainable Imaging-Genetics Associations Related to a Neurological Disorder](https://mlsanity.com/paper/2508.18303/) (2025)

## Abstract (arXiv)

The interaction between brain structure and genetic influences is key to understanding neuropsychiatric disorders. However, most large-scale datasets are unimodal, providing either neuroimaging or genetics data. We propose CALM, a framework that learns interpretable associations between brain ROIs and genetic pathways from completely disjoint populations. CALM aligns the two modalities in a shared latent space via linear projections that simultaneously match the class-conditional latent distributions and ensure group separability. These projections provide interpretable pathway--ROI associations. When trained on unimodal imaging and genetics datasets, CALM generalizes to an unseen paired dataset, outperforming several state-of-the-art methods and ablation baselines. We also demonstrate stability of the learned associations against a paired baseline. Our experiments on autism spectrum disorder reveal immune and metabolic pathways linked to specific cortical regions and are consistent with established literature. Thus, CALM opens the door to leveraging large unimodal repositories for studying cross-modal interactions in brain disorders across disparate datasets.