Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward

Excerpt

arXiv:2511.20561v3 Announce Type: replace-cross Abstract: Recent years have witnessed significant progress in Unified Multimodal Models, yet a fundamental question remains: Does understanding truly inform generation in Unified Multimodal Models? To investigate this, we introduce UniSandbox, a decoupled evaluation framework paired with controlled, synthetic datasets to avoid data leakage and enable detailed analysis. Our findings reveal a significant understanding-generation gap, which is mainly