[1/5] Knowledge flow: Knowledge flow is highly asymmetric and concept-dependent. We demonstrate this in both real-world data and controlled synthetic environments: Language is a universal booster for all visual tasks. Understanding is a strong prior for generation, significantly boosting visual creation. Generation acts as a latent prior. it doesn’t yield instant zero-shot gains for understanding, but sharply accelerates low-level concept acquisition.

[2/5] Modality Synergy: Joint training isn't automatically synergistic; interaction depends heavily on task complexity and architecture. Key findings across our experimental axes: Task complexity: Simple tasks foster cross-modal synergy, while complex tasks trigger competition. Architecture sharing: Share Attention & Norms to drive cross-modal interaction and synergy; Decouple FFNs to eliminate capacity bottlenecks and parameter competition. Encoder generalization: These architectural guidelines (and knowledge flow results) consistently hold across diverse vision representations (continuous vs. discrete, pixel-level vs. semantic).

[3/5] Early Unification: Timing matters. Early unification with joint training allows modalities to better co-evolve. Simultaneous early fusion significantly outperforms late alignment or sequential training. Delayed integration causes "Vision Laziness": Pretraining on text first creates strong language priors, causing the model to perceive and learn fewer visual signals.

[4/5] Recipe: Translating physical mechanics into a practical scaling recipe: Data recipe: Allocating as little as 5% of the token budget to visual generation achieves competitive generative modeling while preserving strong language & understanding capabilities. Scale Verification: Validated on multiple 13.5B MoE models trained across 2T tokens , proving that early fusion + asymmetric data blend + MoE scales efficiently.