Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models

ArXi:2604.10949v1 Announce Type: cross Unified multimodal models (UMMs) were designed to combine the reasoning ability of large language models (LLMs) with the generation capability of vision models. In practice, however, this synergy remains elusive: UMMs fail to transfer LLM-like reasoning to image synthesis and exhibit divergent response behaviors. We term this phenomenon pseudo-unification. Diagnosing its internal causes is important, but existing probing methods either lack model-internal insight or ignore prompt-response dependencies.