Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models 事件

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models arXiv:2602.07026v3 Announce Type: replace Abstract: Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy systematically offset regions. Prior approaches to bridge this gap are largely limited by oversimplified isotropic a