Work

SCOPE: Preserving Modality-Specific Cues to Mitigate Modality Laziness in Multimodal Learning

Year: 2026

Type: conference-paper

Abstract: Multimodal learning aims to learn unified multimodal representations from heterogeneous modalities and supports many natural language processing tasks.However, multimodal models often exhibit modality laziness: over-relying on a dominant modality and under-exploiting complementary signals.Existing approaches typically strengthen unimodal training or rebalance modality contributions, but they may still emphasize shared semantics and overlook modality-specific cues.To address this, we propose SCOPE, a unified framework for learning complete multimodal representations, achieving Shared-and-COmplementary cue PrEservation.Firstly, SCOPE uses a mutual informationguided disentanglement module to separate shared semantics from modality-specific cues and mitigate representation collapse.Secondly, SCOPE aligns modalities by enforcing structural consistency between modality-wise semantic graphs, avoiding brittle point-wise matching.Finally, SCOPE performs balanced fusion via structure-aware diffusion attention to integrate shared and complementary cues without feature homogenization.Experiments on five benchmark datasets show that SCOPE consistently outperforms SOTA baselines, achieving up to 27.10% accuracy improvement.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2026.findings-acl.1453

Authors: Jingfan Yang, Rui Zhang, Liang Hong, Ke Yuan

Institution: Wuhan University

Language: English

Topic: Multimodal Machine Learning Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Natural Science Foundation of China, Natural Science Foundation of Hubei Province

Award: G4554742357