C3-UniMM: Causal Cycle-Consistent Unified Multimodal Modeling via Super Alignment and Shared Decoding Space

Abstract

arXiv:2608.28603v1 Announce Type: new Abstract: Unified Multimodal Models aim to achieve any-to-any understanding and generation across arbitrary modalities. However, existing methods primarily rely on modeling implicit statistical correlations and lack cross-modal structural consistency constraints. This deficiency leads to profound issues, including semantic drift, poor compositional generalization, and instability under interventions. In this paper, we propose C3-UniMM, a unified multimodal m