Towards the Causal Complete Cause of Multi-Modal Representation Learning

Jingyao Wang; Siyu Zhao; Wenwen Qiang; Jiangmeng Li; Changwen Zheng; Fuchun Sun; Hui Xiong

ICML2025顶会

Towards the Causal Complete Cause of Multi-Modal Representation Learning

Jingyao Wang, Siyu Zhao, Wenwen Qiang, Jiangmeng Li, Changwen Zheng, Fuchun Sun, Hui Xiong

arXiv 出版方

2025年份

3顶会引用

摘要

Multi-Modal Learning (MML) aims to learn effective representations across modalities for accurate predictions. Existing methods typically focus on modality consistency and specificity to learn effective representations. However, from a causal perspective, they may lead to representa-* Equal contribution