# Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models

arXiv: https://arxiv.org/abs/2510.08492 · HTML: https://mlsanity.com/paper/2510.08492/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2025.

## Built on by (most cited first, 3 of 3)

- [ENIGMA: The Geometry of Reasoning and Alignment in Large-Language Models](https://mlsanity.com/paper/2510.11278/) (2025)
- [Representation Alignment Rests on Linear Structure](https://mlsanity.com/paper/2605.28870/) (2026)
- [Unpaired Canonical Correlation Analysis](https://mlsanity.com/paper/2610.09530/) (2026)

## Abstract (arXiv)

Traditional multimodal learners find unified representations for tasks like visual question answering, but rely heavily on paired datasets. However, an overlooked yet potentially powerful question is: can one leverage auxiliary unpaired multimodal data to directly enhance representation learning in a target modality? We introduce UML: Unpaired Multimodal Learner, a modality-agnostic training paradigm in which a single model alternately processes inputs from different modalities while sharing parameters across them. This design exploits the assumption that different modalities are projections of a shared underlying reality, allowing the model to benefit from cross-modal structure without requiring explicit pairs. Theoretically, under linear data-generating assumptions, we show that unpaired auxiliary data can yield representations strictly more informative about the data-generating process than unimodal training. Empirically, we show that using unpaired data from auxiliary modalities -- such as text, audio, or images -- consistently improves downstream performance across diverse unimodal targets such as image and audio. Our project page: https://unpaired-multimodal.github.io/