Anisotropic Modality Align

TL;DR

This paper investigates the geometric structure of the modality gap in multimodal models, revealing anisotropic residuals as key obstacles, and proposes a correction framework, AnisoAlign, for better modality alignment using geometric priors.

Contribution

It uncovers the anisotropic nature of the modality gap and introduces a geometric correction method, AnisoAlign, for improved unimodal training of multimodal models.

Findings

Modality representations share compatible semantic geometry.

The modality gap is due to anisotropic residuals along dominant directions.

AnisoAlign improves geometric alignment and text-only multimodal training.

Abstract

Training multimodal large language models has long been limited by the scarcity of high-quality paired multimodal data. Recent studies show that the shared representation space of pretrained multimodal contrastive models can serve as a bridge, enabling models to perform multimodal training with unimodal data. However, the key premise of this paradigm remains insufficiently understood: can representations from different modalities be reliably interchanged? The core obstacle lies in the persistent Modality Gap in the shared space. In this work, we revisit the geometric nature of the modality gap. We find that modality representations already share compatible dominant semantic geometry. What truly hinders modality interchangeability is not a simple global shift, but an anisotropic residual structure concentrated along a small number of dominant directions. Based on this finding, we further propose the principle of anisotropic modality gap alignment: effective modality alignment should align with the target-modality distribution while preserving the semantic structure of the source modality. Guided by this principle, we propose an anisotropic geometric correction framework, AnisoAlign, for unpaired modality alignment. This framework leverages the internal geometric prior of the target modality and performs bounded correction on source-modality representations, thereby constructing substitute representations in the target modality. Experiments confirm its benefits in both geometric diagnostics and text-only MLLM training. Overall, this work recasts the modality gap from an empirical observation into a correctable, structured geometric phenomenon and provides a new representation alignment perspective for training multimodal models with unimodal data.