Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward
This addresses a fundamental issue in multimodal AI for researchers, providing insights to improve model architectures, but it is incremental as it builds on existing paradigms.
The paper tackles the problem of whether understanding informs generation in unified multimodal models, finding a significant gap in reasoning generation and knowledge transfer, with explicit Chain-of-Thought bridging the gap and self-training enabling implicit reasoning.
Recent years have witnessed significant progress in Unified Multimodal Models, yet a fundamental question remains: Does understanding truly inform generation? 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 reflected in two key dimensions: reasoning generation and knowledge transfer. Specifically, for reasoning generation tasks, we observe that explicit Chain-of-Thought (CoT) in the understanding module effectively bridges the gap, and further demonstrate that a self-training approach can successfully internalize this ability, enabling implicit reasoning during generation. Additionally, for knowledge transfer tasks, we find that CoT assists the generative process by helping retrieve newly learned knowledge, and also discover that query-based architectures inherently exhibit latent CoT-like properties that affect this transfer. UniSandbox provides preliminary insights for designing future unified architectures and training strategies that truly bridge the gap between understanding and generation. Code and data are available at https://github.com/PKU-YuanGroup/UniSandBox