Adopting a single, unified architecture for both vision and generation tasks simplifies the engineering lifecycle. This approach reduces the cost and complexity of maintaining, updating, and deploying multiple specialized models, accelerating development.
The ability of a single encoder to excel at both understanding and generating images indicates these two tasks are not as distinct as they seem. It suggests they rely on a shared, fundamental structure of visual information that can be captured in one unified representation.
A unified tokenizer, while efficient, may not be optimal for both understanding and generation tasks. The ideal data representation for one task might differ from the other, potentially creating a performance bottleneck that specialized models would avoid.