LatentUMM: Dual Latent Alignment for Unified Multimodal Models

by [unverified] · free · Last verified 2026-06-21T03:07:54.893Z

Unified multimodal models (UMMs) achieve strong performance in both understanding and generation by learning a shared latent space, yet they often exhibit functional inconsistency between these two capabilities. We observe that this issue does not stem from a lack of shared representations, but f...