DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement 事件

DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement arXiv:2605.25328v1 Announce Type: new Abstract: Unified Multimodal models (UMMs) built on a single architecture have shown impressive performance in both understanding and generation. We identify a fundamental challenge that lies in inductive biases induced by distinct supervision signals: generation branch prefers high-fidelity, fine-grained representations capable of reconstruction, while the