Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2026

Abstract

Multimodal representation learning aims to construct a shared embedding space in which heterogeneous modalities are semantically aligned. Despite strong empirical results, InfoNCE-based objectives introduce inherent conflicts that yield distribution gaps across modalities. In this work, we identify two conflicts in the multimodal regime, both exacerbated as the number of modalities increases: (i) an alignment–uniformity conflict, whereby the repulsion of uniformity undermines pairwise alignment, and (ii) an intra-alignment conflict, where aligning multiple modalities induces competing alignment directions. To address these issues, we propose a principled decoupling of alignment and uniformity for multimodal representations, providing a conflict-free recipe for multimodal learning that simultaneously supports discriminative and generative use cases without task-specific modules. We then provide a theoretical guarantee that our method acts as an efficient proxy for a global Holder divergence over ¨ multiple modality distributions, and thus reduces the distribution gap among modalities. Extensive experiments on retrieval and UnCLIP-style generation demonstrate consistent gains.

Discipline

Artificial Intelligence and Robotics

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), Seoul, South Korea, July 6-11

First Page

1

Last Page

18

Publisher

IMLS

City or Country

Seoul, Korea

Additional URL

https://icml.cc/virtual/2026/poster/62197

Download

Share

COinS