Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models
For researchers building unified multimodal models, this work provides the first model-internal probing of unification, revealing that real synergy requires consistency in information flow, not just shared parameters.
The paper identifies and diagnoses 'pseudo-unification' in unified multimodal models (UMMs), where LLM reasoning fails to transfer to image synthesis. Using an information-theoretic probing framework on ten UMMs, it reveals dual divergence in encoding and response patterns, and shows that models with contextual prediction achieve more genuine unification, enabling stronger reasoning-based text-to-image generation even with fewer parameters.
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. To address these limitations, we propose an information-theoretic probing framework that jointly analyzes how UMMs encode inputs and generate outputs. Applied to ten representative UMMs, our framework reveals that pseudo-unification stems from a dual divergence: (i) Modality-Asymmetric Encoding, where vision and language follow different entropy trajectories, and (ii) Pattern-Split Response, where text generation exhibits high-entropy creativity while image synthesis enforces low-entropy fidelity. Only models that unify both sides (e.g., via contextual prediction) achieve more genuine unification, enabling stronger reasoning-based text-to-image generation even with fewer parameters. Our work provides the first model-internal probing of unification, demonstrating that real multimodal synergy requires consistency in information flow, not just shared parameters.